Green Energy

Construction begins at new wind and battery project that will help power one of world's biggest mines and drive South Australia towards 100 pct net renewables. The post Construction begins on wind farm and big battery to power huge mine and push state closer to 100 pct renewables appeared first on Renew Economy.

Fusion energy company Xcimer Energy said it has finalized an agreement for up to $30.5 million in additional federal funding through the U.S. Department of Energy’s (DOE’s) Milestone-Based Fusion Development Program. The new DOE award, announced October 6, is for the program’s second budget period. It brings the total DOE funding for potential Milestone payments […] The post Denver-Based Fusion Group Receives $30.5-Million Award from DOE appeared first on POWER Magazine.

D3Energy, a U.S. floating solar developer and EPC contractor, has deployed a floating solar photovoltaic system at Universal Epic Universe theme park in Orlando, Florida. The 1.4-MW floating solar system was energized earlier this year and now operates as part of the new theme park’s broader renewable energy program. It is one of three on-site… The post Universal theme park thrills powered by floating solar project appeared first on Solar Power World.

Fit Energy, a developer of energy solutions for data center projects, has announced plans for a fuel cell power generation and data center project in Newport Township, Luzerne County, Pennsylvania. The project received township zoning approval for both uses in August of this year. Fit Energy on October 6 said engineering and the remaining permitting […] The post Fit Energy Will Use Gas-Powered Fuel Cells For Pennsylvania Data Center Project appeared first on POWER Magazine.

Demand for energy storage is surging, with capacity expected to grow eightfold in the next decade. To meet that demand, Moment Energy wants to shortcut a supply chain that now flows largely through China, by domestically repurposing EV batteries into new grid-connected storage systems. Moment Energy’s four founders met while studying mechatronics engineering in college…

There’s a growing need for long-duration storage to meet energy demand and balance out renewables on the grid. Energy Dome uses compressed carbon dioxide gas in its massive grid batteries, which can deliver power for up to 24 hours.  As the world races to meet growing electricity demand, solar and onshore wind power have become…

Form Energy is building iron-based batteries that can store energy for multiple days. The company is ramping up supply at its factory and signing deals for commercial projects. New solar and wind installations produce electricity more affordably than fossil fuels in most places, but their output varies based on season, time of day, and weather.…

WeLion New Energy is on a quest to make safer, better batteries. The company’s semi-solid-state cells could improve safety and offer greater energy density than lithium-ion batteries to power electric cars, boats, and drones. From the EVs that carry commuters home to the ships that transport goods across countries, more and more vehicles around us…

Manufacturers say they are close to perfecting a new, more efficient solar panel that could help the United States reclaim ground it lost.

The Australian arm of a French energy giant is seeking federal environmental approval to build a wind and battery project in one of state's most contentious renewable energy zones. The post French energy giant seeks federal green tick for wind farm and big battery in hotly contested REZ appeared first on Renew Economy.

Rooftop solar uptake has ridden the wave of Cheaper Home Batteries, but new data shows how changes to the rebate are also helping to dictate solar system size. The post Rooftop PV system sizes feel the battery effect, but it’s still a bumper year for home solar appeared first on Renew Economy.

Why does the expansion of wind energy sometimes meet with local resistance, even though renewable energy generally enjoys broad support? RIFS researcher Jörg Radtke used a representative survey of 6,284 people in North Rhine-Westphalia to investigate which social characteristics are linked to the acceptance of wind energy.

The bulk photovoltaic effect (BPVE), a photoelectric effect that generates photocurrent without a p–n junction, can persist even when a material's average crystal structure remains centrosymmetric, a study from Institute of Science Tokyo has found. Researchers demonstrated this in CuCrP2S6, a van der Waals material that transitions from a noncentrosymmetric to a centrosymmetric average structure. The finding challenges the conventional view of BPVE and suggests a new strategy for enhancing photoelectric conversion.

For more than 70 years, fusion energy researchers have used a particular equation to judge whether a plasma would stay hot and dense enough—for long enough—to reach a point where it could sustain itself without any more external power added. While that equation marks the finish line, also known as ignition, it says nothing about the best way to reach it. New research from the U.S. Department of Energy's (DOE) Princeton Plasma Physics Laboratory (PPPL) maps a path to ignition conditions using far less energy than any other path.

A weak car battery can cause slow starts, electrical problems, and eventually leave a vehicle unable to start.

First Solar has filed a lawsuit in U.S. district court against JA Solar, together with American Panel Solutions, alleging infringement of First Solar’s U.S. Patent No. 9,130,074. The ‘074 patent covers methods of manufacturing TOPCon silicon solar cells. “We have been clear that we will actively defend our intellectual property rights in the U.S. and… The post First Solar files TOPCon patent infringement lawsuit against JA Solar, American Panel Solutions appeared first on Solar Power World.

The Sisters of Charity of New York, a Catholic mission group that has spearheaded healthcare and affordable housing developments in the state, called on the power of the sun to reduce energy costs for elderly tenants in a Staten Island housing complex. PV consultancy firm Crauderueff Solar helped the mission group develop an adequate solar… The post Solar on Staten Island affordable housing serves community and tenants Solar Power World’s Projects of Impact appeared first on Solar Power World.

Manufacturers say they are close to perfecting a new, more efficient solar panel that could help the United States reclaim ground it lost.

arXiv:2610.03465v1 Announce Type: cross Abstract: K-fold cross-validation (CV) is widely used as evidence of out-of-sample performance, although folds are neither independent experiments nor equally informative under heterogeneous data. Cross Upper-Bound Validation (CUBV) replaces point-wise CV accuracy by conservative upper bounds on true risk. Here we generalise CUBV through a single exponential framework in which the moment-generating function of the generalisation gap is controlled by a cumulant envelope gamma(lambda). This yields a family of risk bounds covering Hoeffding-, Bernstein-, dependency-aware, PAC-Bayesian, and heterogeneous source-fusion settings. For K-fold CV, dependence between fold-wise gaps is modelled through a joint sub-Gaussian proxy matrix. Under equicorrelation, this gives an effective number of folds, Keff = K/[1+(K-1)rho], showing that increasing K does not necessarily increase statistical evidence when folds are strongly dependent. The framework is also

arXiv:2610.03508v1 Announce Type: new Abstract: Multi-timescale systems present a fundamental challenge, where fast operational decisions must coexist with long-horizon sustainability targets. In this work, we propose a new hierarchical control framework via Model Predictive Control (MPC) and Reinforcement Learning (RL) to separate decision-making on two distinct timescales. The high-level MPC optimizes long-horizon setpoints at the slow dynamic and on a fast timescale, a low-level pretrained RL agent tracks these setpoints in real time to maximize short-term objectives. RL is introduced to learn nonlinear control policies, without relying on model linearizations or requiring the heavy online computation from solving repeated optimal control problems. The framework is applied to a Battery Energy Storage System (BESS) operating in frequency regulation markets to balance fast profit opportunities (seconds) and slow battery degradation (weeks to months). The design employs a

arXiv:2610.03505v1 Announce Type: new Abstract: Post-exposure microscopy is central to qualification of fusion materials. However, manual analysis does not scale to the volume, heterogeneity, and multiresolution character of modern fusion-materials campaigns. To address this challenge, we present a reproducible workflow, implemented in the Galaxy scientific workflow environment, for automated crack identification and quantitative damage assessment from scanning electron microscopy images. The workflow processes SEM images and experimental metadata to identify cracks, quantify damage, and retain the intermediate products and processing history needed for reproducibility. Outputs include crack masks, skeletonized crack networks, quality-control visualizations, and scalar damage descriptors. The method is designed to operate without image-specific parameter tuning across tungsten grades, microstructures, magnifications, and damage states. We demonstrate the workflow on a sparse

arXiv:2610.03473v1 Announce Type: new Abstract: We propose UniDynamics, a diffusion-based framework for future 4D dynamic scenes (RGB, depth, and optical flow) generation from a single event-RGB pair, without requiring long histories or control priors as in existing methods, while explicitly modeling future motion fields. The core idea is to leverage event streams to offer an alternative motion prior for single-RGB extrapolation, and to enforce geometric and motion constraints throughout generation via multimodal modeling. Specifically, we design an Event Latent Enhancement (ELE) module to align and enhance event latents into diffusion-injectable conditioning features, providing robust initial motion priors and reliable texture/structure cues. We further introduce a Perceptual Dynamics Space (PDS) embedded in the multi-scale U-Net, which decouples and adaptively interacts depth and flow while continuously feeding back constraints to appearance features, improving geometric-motion

arXiv:2610.03289v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance across vision-language tasks, yet the internal mechanisms by which visual and textual information are fused across layers remain insufficiently understood. We investigate representative MLLMs from two architectural paradigms: concatenation architectures and native multimodal architectures. We conduct three progressively connected analyses: alignment decoupling identifies which modality changes, attention routing and entropy characterize how cross-modal information is distributed, and intrinsic dimensionality examines how fusion reshapes feature spaces. Separately, we perform causal intervention experiments as a validation of the resulting interpretation. As a supplementary analysis, we use visual CKA to examine the Platonic Representation Hypothesis. Together, these analyses reveal two distinct fusion pathways: concatenation models follow a text-first, vision-later

arXiv:2610.03261v1 Announce Type: new Abstract: Solving severely ill-posed imaging inverse problems requires recovering image structures that are unobservable or weakly constrained by the measurements. Diffusion models provide expressive learned priors for inferring such missing information, while posterior sampling incorporates measurement consistency along the reverse process. Standard diffusion posterior samplers, however, rely on instantaneous measurement-aware estimates, without explicitly exploiting information carried by previous posterior corrections. We introduce Consecutive Posterior Fusion Denoising Diffusion Null-Space Models (CPF-DDNM), an inference-time strategy that fuses consecutive measurement-aware estimates to improve the diffusive recovery of unobservable image structures, without requiring retraining or additional denoiser evaluations. We instantiate this principle within DDNM, whose range/null-space decomposition reveals that consecutive fusion preserves the

arXiv:2610.02813v1 Announce Type: new Abstract: Visuomotor imitation policies combine high-dimensional visual observations with compact signals such as proprioception, and their fusion topology determines when and through which tokens these streams interact. In dense token fusion, visual tokens may attend directly to compact tokens from the first encoder layer, allowing action-predictive compact cues to influence spatial visual representations early in their formation. We ask whether controlling this route improves visual responsiveness and policy behavior. We introduce Register-Routed Delayed Fusion (RRDF), which masks direct compact-visual attention and stages cross-modal interaction through a learned register workspace. Its isolate-collect-route schedule protects an early stream-separated prefix and later permits only register-mediated exchange, while compact conditioning remains available to the native action generator. Across five simulation tasks and three real-robot tasks, RRDF

arXiv:2610.02447v1 Announce Type: new Abstract: A battery-powered device, such as a delivery drone that works from a depot, must stop to recharge between jobs, and the time spent recharging delays every job that follows. Scheduling models that fix the duration of a recharge do not describe a device whose recharge takes longer when it acquires more energy. We study a single device that executes a batch of non-preemptive jobs with known execution times, energy demands, and optional deadlines. Under \emph{partial recharging} the device may acquire any amount of energy between jobs; under \emph{complete recharging} every recharge fills the battery. Four objectives and four relationships between execution time and energy demand give 32 variants. When acquiring $q$ units of energy takes $q$ time units, we show that 14 of the 16 partial-recharging variants are polynomial, and we give a tight 2-approximation for the average completion time, one of the two NP-hard variants. Under complete

Using data from the Japan-led XRISM observatory, astronomers have directly observed a giant star’s stellar wind captured by its compact companion (triggering X-ray flares) for the first time.

Beijing wants large-scale production, but the world’s biggest EV battery maker warns that making the technology affordable is another matter.

Researchers from the LIMNO laboratory at EPFL have uncovered how different halides modify the surface chemistry of organic semiconductor nanoparticle photocatalysts. By controlling these phenomena, they have significantly improved the solar hydrogen production efficiency of these materials.

Broccoli grown under magenta solar panels absorbed sunlight more efficiently than plants grown out in the open, according to a study to be published Oct. 2 in Cell Reports Physical Science.

Windpower Monthly rounds up the latest patents for wind power technology granted and applied for in the last week.

Germany’s new 365-metre wind turbine in Schipkau is the world’s tallest, designed to capture stronger winds and start operating in November.

arXiv:2610.00845v1 Announce Type: cross Abstract: Machine learning models are increasingly used in feedback control loops for nuclear fusion, where inference speed and predictable timing are critical. We summarize lessons from models deployed for control on the DIII-D tokamak and develop a benchmark to compare inference backends across ten neural networks and model components from fusion control and diagnostic pipelines. For models greater than five million parameters, the CPU backends take tens to thousands of milliseconds, while GPU inference is substantially faster, suggesting an upper limit on CPU-oriented development for control. These results show why the deployment backend must be selected together with the model and its control-cycle budget.

arXiv:2610.00535v1 Announce Type: cross Abstract: Uncertainty quantification is critical in scientific machine learning, where black-box, image-based models are increasingly deployed in high-stakes settings. In many such applications, model outputs inform costly decisions, yet most methods provide only point estimates without quantifying predictive uncertainty. This challenge is compounded by the limited accessibility and interpretability of model internals, making it difficult to assess reliability across different regions of the input space. As a result, there is a growing need for methods that can provide input-dependent uncertainty estimates to guide both model development and downstream experimentation. To address this need, we propose Adaptive Conformal Prediction using Nearest Neighbors (ACPNN), an input-adaptive conformal framework for image regression. ACPNN leverages information from neighboring samples to produce locally adaptive uncertainty estimates while maintaining low

arXiv:2610.01705v1 Announce Type: new Abstract: LLM-based personal agents are emerging as persistent carriers of user semantics and intermediaries between users and recommendation platforms, maintaining richer user knowledge locally. As agents interact with one another, the conventional \textit{User--Platform} relation evolves into a \textit{User--Agent Web--Platform} information pathway, enabling distributed user-side information to complement item-side information. This new pathway, however, defies conventional recommendation: evidence is scattered across mutually opaque agents and reachable only through bounded queries, only a small portion of it is relevant to the current recommendation decision, and the responses returned by different agents are semantically heterogeneous. We therefore recast recommendation over the agent web as a \emph{task-time evidence acquisition and fusion} problem under a finite evidence budget by deciding what to ask and what to keep, rather than learning

arXiv:2610.00408v1 Announce Type: new Abstract: This paper describes the approach of the UniBuc team in tackling the SemEval 2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. We used SOLAR Instruct, without any fine-tuning, while focusing on input manipulation and tailored prompting. By customizing prompts for individual CTR sections, in both zero-shot and few-shots settings, we managed to achieve a consistency score of 0.72, ranking 14th in the leaderboard. Our thorough error analysis revealed that our model has a tendency to take shortcuts and rely on simple heuristics, especially when dealing with semantic-preserving changes.

arXiv:2610.00380v1 Announce Type: new Abstract: Depression is a mental condition that can lead to suicide and self-harm. Predicting the outcome of depression treatment is one of the most difficult tasks for clinicians. Among various treatment options, repetitive Transcranial Magnetic Stimulation (rTMS) is a widely used non-invasive method. Predicting rTMS response using Electroencephalogram (EEG) data is difficult because of high inter-subject variability and limited features from single-domain analysis. We introduce two fusion techniques, montage and blending, to overcome these limitations and extract richer features from EEG-derived Time-Frequency (TF) images. We then propose a lightweight custom Convolutional Neural Network (CNN) trained on fused TF representations. \textcolor{black}{We use a primary dataset of 15 patients and a secondary dataset of 46 patients. We run two sets of experiments. The first set uses segment-level 10-fold cross-validation. In this setup segments from

arXiv:2610.00319v1 Announce Type: new Abstract: Collaborative perception enables connected agents to share complementary observations for 3D object detection, extending sensing range and mitigating occlusion. Under asynchronous communication, however, cooperative features arrive with temporal delay. Existing prediction-based methods compensate for these features mainly from the transmitting agent's own history, leaving residual misalignment with the ego agent's current observation; subsequent fusion also often overlooks spatial variations in alignment quality. We propose EgoRefine, an ego-referenced predictive alignment and reliability-aware fusion framework for asynchronous collaborative perception. Its Ego-referenced Predictive Alignment module uses the current ego feature to guide cooperative trajectory-field prediction and refines the sampling offsets along an ego-referenced trajectory direction. Its Trajectory-conditioned Reliability-aware Fusion module treats the trajectory

arXiv:2610.00294v1 Announce Type: new Abstract: Automated acne severity grading requires both whole-face context and fine-grained lesion evidence. We propose LENS-GRF (Lesion Evidence Network with Set-Transformer and Gated Residual Fusion), an interpretable multi-stage framework for four-class acne severity grading. The method combines Adaptive Facial Skin Segmentation and a global Vision Transformer prior with a permutation-invariant Lesion Set Transformer that encodes localized lesion patches and spatial geometry. Gated Residual Fusion adaptively controls the local residual contribution and reduces to the global prediction when the gate is zero. On ACNE04, fully automated LENS-GRF with YOLOv11s achieved 80.82% accuracy; with ground-truth lesion annotations, it achieved 95.89% +/- 0.59% accuracy and a Quadratic Weighted Kappa of 0.9753. A data-integrity audit identified 15 cross-split duplicate image pairs, including five with conflicting severity labels. In locked zero-shot

arXiv:2610.00279v1 Announce Type: new Abstract: The segmentation of anatomical structures in medical images and particularly in MRI scans, is essential for clinical diagnosis and monitoring disease progression. While Deep Learning (DL) architectures, such as U-Net and its extensions are very effective in medical image segmentation tasks, they often struggle with preserving fine-grained details and global contextual information. This is especially challenging for MRI data segmentation, where anatomical structures are characterized by irregular boundaries and variations in shape, contrast, and scale. To address this challenge, we propose a novel DL architecture for MRI segmentation across different anatomical structures. Specifically, the architecture introduces a module, named Multi-Resolution Feature Fusion (MRFF), that can be easily integrated into any U-Net-like architecture. The MRFF is integrated in all levels of an encode-decoder structure, along with attention mechanisms and

arXiv:2610.00055v1 Announce Type: new Abstract: The two critical strains of pavement design, under the asphalt layer and on the subgrade, are conventionally obtained by backcalculating layer moduli from a falling weight deflectometer (FWD) basin and propagating them through layered-elastic analysis. That route is ill-posed and confined to the office. We propose the deflection-basin fusion transformer (DBFT), a 0.22M-parameter attention model predicting both strains in one step from the basin and the layer thicknesses, read as a sequence indexed by offset. One objective spans 14,174 layered-elastic solutions and 7,651 field measurements from 96 Thai highway sections, three routes withheld entirely. On exact theory DBFT reaches R^2 >= 0.9998 at RMSE <= 1.24 microstrain, an order of magnitude better than published index equations. Trained on that factorial alone it fails on measured basins, R^2 <= 0.14: the field domain inverts the sign of the outer-basin correlation. The combined

arXiv:2610.00053v1 Announce Type: new Abstract: Four-bit floating-point (FP4) Tensor Cores accelerate matrix multiplication, but scale computation, operand packing, layout construction, and saved backward state can erase the gain. We present \emph{format-aware fusion}, which co-designs each quantization producer with its scale domain and consumer layout for native \mxfp{}, global \nvfp{}, and cooperative-thread-array-local \nvfp{}. We evaluate Llama-3-family 8B pretraining through 160 billion tokens using bfloat16 output projections and compiled cross entropy. In matched same-accelerator probes, bfloat16 and Transformer Engine \nvfp{} reach 18.8K and 27.6K tokens/s/GPU, while our fastest custom route reaches 37.9K. \mxfp{} with row-gradient stochastic rounding and fixed-sign 32-value Hadamard weight-gradient preconditioning reaches 37.2K tokens/s/GPU (86.3\% bfloat16 model FLOP utilization) and ends 2.11\% above the raw bfloat16 training-loss endpoint. A Transformer Engine recipe with

Author(s): V. I. LyashukThere is much interest and activity in identifying transuranium isotopes and determining their cosmological origins, such as neutron star mergers. This paper studies how one could determine the production of transuranium isotopes in pulse nucleosynthesis based on isotopic yield ratios, a process that is very dependent on neutron fluence. The relationship between the neutron flux and abundances is determined in a rather unique way: by looking at yields from nuclear tests conducted during the Plowshares program. Making use of these nuclear tests (indicated in the figure) may help determine whether the periodic table has been extended in natural events in space. [Phys. Rev. C 114, 044603] Published Thu Oct 01, 2026

One of Australia's largest technology companies has signed a decade-long deal with a community-owned solar farm to help power a landmark building. The post Cannon-Brookes’ Atlassian signs deal with groundbreaking community solar farm to power its new green HQ appeared first on Renew Economy.

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. An AI “mind-reading” tool can reconstruct what you’re looking at based on a brain scan A new AI tool can guess what you’re looking at just by analyzing your brain scans—and…

If you want to install a big battery in New York City, you have to cut through a notoriously tough tangle of regulations. That’s made it difficult to get large energy storage projects on the grid. Faced with those obstacles, some startups are getting creative, finding ways to use relatively small batteries in unexpected places,…

Origin Energy has dropped plans to develop a major wind farm intended for 10 kms west of Walcha in NSW's New England region. The post Origin Energy drops plan for massive wind project in New England, citing rising costs appeared first on Renew Economy.

CSIRO study finds households with solar and batteries are enjoying periods of "limitless" electricity, a shift that clashes head on with concepts of energy sharing and efficiency. The post “It’s made us more wasteful:” Solar and battery homes plug in to a new age of abundant energy appeared first on Renew Economy.

State quietly launches its own version of the Solar Sharer offer, giving households the option to access three hours of free power between 11am-2pm, daily. The post Another state launches Solar Sharer offer, amid fresh warnings of drawbacks to three hours of free power appeared first on Renew Economy.

arXiv:2609.22107v2 Announce Type: replace Abstract: Making prediction with multimodal data is widely used in diverse scenarios. Existing multimodal fusion models, once deployed, can only handle predefined modalities (e.g., vision, text and audio) and single task, making it difficult to quickly adapt to new downstream applications. Therefore, a natural yet aggressive question arises - whether there exists a general multimodal fusion model that can be applied to arbitrary modality combinations and arbitrary prediction tasks. We argue that a unified multimodal fusion model should not depend on specific modalities and should instead encode transferable patterns of multimodal correlation. To this end, we propose a simple and effective learning paradigm based on training on large-scale synthetic multimodal datasets generated with Structural Multimodal Causal Models (SMCMs), which formally characterizes the generative processes of real-world multimodal data. Building on this framework, we

arXiv:2609.40157v1 Announce Type: cross Abstract: The Wind Farm Layout Optimization problem consists of placing a given number of turbines within a given area so as to maximize energy production. One of its main challenges is the wake effect between turbines, which can strongly affect production and is a cumbersome function to evaluate and to embed in an optimization framework. In this paper we introduce a new endogenous wake model (EndoWake), based on the idea of treating the wind speed at every grid point as a decision variable, linked to its upwind neighbors through linear propagation constraints. This makes it possible to incorporate the wake equations directly into a Mixed-Integer Linear Programming (MILP) model. We then develop such a MILP model and, in particular, introduce a new class of valid "band" inequalities, showing that they substantially strengthen the root bound. Building on this, we design a branch-and-check scheme: the master problem retains only the site variables

arXiv:2609.40092v1 Announce Type: new Abstract: Long-term battery energy storage system (BESS) planning often relies on simplified degradation, operational, and temporal representations to maintain computational tractability, yet their effects on lifecycle conclusions are not well understood. This paper assesses the modeling fidelity needed for long-term lifecycle evaluation of BESS designs used in planning studies. A 20-year grid-connected microgrid is sized using a degradation-naive planning model, after which the installed portfolio is fixed and evaluated through sequential lifecycle validation. The reference representation combines nonlinear calendar and cycle aging, C-rate-dependent efficiencies, state-of-health-dependent performance, self-discharge, battery replacement, and full 8,760-h chronology. Battery-model hierarchies, targeted ablations, linear degradation surrogates, health-update intervals, temporal reductions, and combined simplifications are compared using lifecycle

arXiv:2609.40091v1 Announce Type: new Abstract: Automated report generation can ease the burden radiolo gists face when interpreting multi-sequence MRI studies. Unlike CT, MRI examinations comprise multiple sequences and imaging planes, each con tributing complementary diagnostic information. Existing methods en code a study as a single volume and combine multiple acquisitions by fixed rules. Findings visible in only one plane are thus diluted and of ten missed, lowering recall on clinical efficacy metrics, where a missed abnormality is most costly. We propose GateSPINE, a vision-language framework that fuses sagittal T1 and T2 volumes with a training-free operator, encodes the fused sagittal and axial volumes with two parallel 3D encoders, and decodes their combined representation into a report. Its core mechanism is a gated cross view fusion module that predicts, per feature channel and token, how much of each view to admit, so the more informative view dominates at each spatial

arXiv:2609.40082v1 Announce Type: new Abstract: Cloud agents run each task in an isolated MicroVM. The trouble is the harness loop inside that guest: the harness is nearly idle while it waits on the model, then usage rises on a tool whose size is known only at run time, which complicates memory management from the host. Existing approaches infer reclaim targets from access frequency and memory footprint while the guest allocator places the idle harness and the short-lived tool on the same pages. Therefore, reclamation either selects the wrong pages, fixes on an incorrect capacity, or partially reclaims a huge page, splitting its transparent huge page. This paper proposes Tide, a proactive memory reclamation technique for agent MicroVMs. Our key insight is that the harness already knows each phase's memory intent (which memory, when, and whether its contents must survive), so the guest can report that intent as an exclusive guest-physical region for the host to reclaim directly. To

arXiv:2609.39950v1 Announce Type: new Abstract: Continuum robots are well suited for gentle manipulation because of their inherent compliance and ability to adapt to complex environments. However, their continuously deformable structure makes accurate configuration estimation challenging, particularly when external vision systems are unavailable or obstructed. In this work, we present an embedded pose sensing framework that combines inertial measurement units (IMUs) and active magnetic fields to estimate the robot configuration without relying on external cameras. The angular measurements from the IMU and magnetic-field references are fused to improve local orientation estimation and reduce accumulated orientation error during operation. This pose sensing scheme achieves an update rate of 16.7~Hz, allowing real-time feedback. The proposed system is experimentally validated through closed-loop control, where the estimated robot configuration is used to maintain the end-effector at a

arXiv:2609.39898v1 Announce Type: new Abstract: Marine litter is a growing threat to the underwater ecosystem, driving demand for autonomous survey methods that can locate debris efficiently over large areas. Existing survey methods typically follow predefined paths or operate with a single sensing modality, typically a camera (with image quality suffering in poor-visibility conditions) or sonar (usually noisy and low-resolution). We present an active mapping framework in which a forward-looking sonar and a camera both feed into a shared Bayesian occupancy map, and an optimization problem is solved at each step to decide on the next best view. Candidate viewpoints are scored by a two-term utility that balances exploration of uncertain regions via voxel entropy against exploitation of likely objects. Each sensor is characterized by range- and bearing-dependent detection and false-alarm probability tables determined from data. We evaluate the approach in a realistic underwater

arXiv:2609.39645v1 Announce Type: new Abstract: Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion couples correction with exposure to the same mistakes, which can erode the diversity needed for voting. Self-consistency offers sampling diversity without feedback, while single-pair Actor-Critic collaboration refines only one candidate. We introduce SEPAL, which assigns three private Actor-Critic teams to direct reasoning, evidence grounding, and verification. Role-specific training gives the teams different reasoning objectives beyond sampling variation. Each Critic guides revisions within its own team, preventing feedback from carrying errors across candidates. Once revision ends, majority voting combines only the final answers, keeping the reasoning histories separate until the decision. Across five open-weight backbones and five question-answering benchmarks, SEPAL improves mean accuracy by

arXiv:2609.39162v1 Announce Type: new Abstract: Speaker diarization systems based on speaker embeddings and neural diarization exploit complementary forms of speaker information, but their intermediate representations are not directly compatible. We introduce Training-Free Affinity Fusion (TFAF), which integrates the speaker structure inferred by a neural diarizer into an embedding-based diarization system. The neural speaker partition is used to condition local speaker representations, from which we construct a continuous affinity matrix and combine it with the embedding-based acoustic affinity before a single global clustering step. The method requires no additional training, shared embedding space, speaker-label alignment, or hard transfer of the neural diarizer's speaker count. Experiments on AMI and CALLHOME show consistent DER improvements over both constituent systems; on AMI, fusion also improves speaker-attributed transcription. Ablations show that the neural speaker

arXiv:2609.39004v1 Announce Type: new Abstract: Multimodal image fusion (MMIF) aims to integrate complementary information from different modalities into a high-quality fused image and support downstream tasks. Recently, feature decomposition has become an important paradigm by separating source images into common and modality-specific unique features. However, existing methods lack clear supervision because ground-truth (GT) decomposition feature maps are unavailable. They usually combine multiple image-level metrics as losses, which are inherently incomplete and may conflict since each pixel couples attributes such as texture, edge, and contour. To address this, we propose a 1D signal-level self-supervised feature decomposition paradigm. Our core insight is to reformulate feature decomposition from unclear 2D image-level supervision into an integral-driven 1D signal-level optimization problem. This objective-level reformulation uses the 1D signal form to compute the integral

arXiv:2609.38968v1 Announce Type: new Abstract: Multi-modal image fusion (MMIF) aims to form a single image by integrating shared information, preserving complementary cues, and coordinating cross-modal conflicts across modalities. However, due to the absence of ground-truth fused images, existing MMIF supervision commonly uses spatial-domain sources or gradient variants as surrogate ground truth, making the supervision mechanism inherently misaligned with the goal of MMIF and causing pixel-level compromise or modality bias. To address this, we propose a relation-constrained supervision paradigm that moves fusion supervision from the spatial domain to a learned relation space. Rather than relying solely on direct source approximation, we further leverage frozen pretrained representation models as information providers and design a learnable feature adapter to align heterogeneous DINO and CLIP features into a unified supervision space. The adapter infers three relation parameters,

arXiv:2609.38747v1 Announce Type: new Abstract: Reference-guided camouflaged object detection aims to segment a target whose visual appearance closely resembles its surroundings by exploiting auxiliary reference samples. The task remains difficult because reference samples contain inconsistent target cues, while generic visual representations are not inherently aligned with the target specified by the references. To handle these problems, we present a consensus-aware multi-source fusion framework. Reference-Conditioned Dual-Backbone Fusion (RCDF) couples trainable PVTv2 query features with frozen DINOv3 representations and uses reference-conditioned correlation to select foundation-model evidence before multi-scale fusion. The framework also aggregates multiple references through cross-reference consensus aggregation and injects reference information at semantic depths matched to the query features. Extensive experiments demonstrate the effectiveness of the proposed method. The

Latest nuclear status report details the glum state of affairs for the far right's favourite clean power source. It's already been overtaken by solar for the first time. The post Nuclear power’s quarter-century of stagnation has no end in sight, and has been overtaken by solar PV appeared first on Renew Economy.

Federal rooftop solar rebate officially opens to systems sized between 100 kW and 1 MW, extending a roughly 20 per cent discount to farms, factories and all sorts of businesses in-between. The post Supersized rooftop solar rebates go live in bid to tap into an 80 gigawatt goldmine appeared first on Renew Economy.

A team of researchers led by the National Astronomical Observatory of Japan discovered unexpectedly intricate magnetic structures above quiet-sun regions by observing the sun with the balloon-borne solar observatory Sunrise-III during its 2024 flight in Earth's stratosphere. The work is published in The Astrophysical Journal Letters.

Silfab Solar has outlined a plan to bring online its solar cell production facility in Fort Mill, South Carolina. The community on the North Carolina border has vocalized safety concerns about the operation of the plant. Silfab voluntarily retained TRC Engineers to provide third-party engineering evaluation of the leak prevention and response methods and procedures… The post After third-party safety tests, Silfab will start solar cell production in SC next month appeared first on Solar Power World.

Grid-scale EPC Linxon, power electronics manufacturer Hitachi Energy and tracker producer FTC Solar are packaging their services for solar projects in North America. “The energy transition is no longer constrained by demand,” Stefan Reisacher, CEO of Linxon. It is increasingly constrained by execution capacity, supply chain availability and the industry’s ability to scale. This collaboration… The post FTC Solar, Hitachi Energy, Linxon collaborate on PV project service appeared first on Solar Power World.

The automaker has a novel solution to slow down battery degradation. Here's what we know.

As battery energy storage systems move into larger and denser configurations, fire and explosion risk has become one of the industry’s most closely scrutinized engineering challenges. At Wärtsilä Energy Storage, Mishaal SyedNaveed has focused his work on that challenge. That combination of utility experience, product engineering, testing, and standards work has made SyedNaveed a finalist […] The post Rising Star Finalist: Mishaal SyedNaveed Advances Battery Storage Fire Safety appeared first on POWER Magazine.

BYD Dates Its Solid-State Debut Solid-state batteries have spent more than a decade as the next big thing

Battery technology has become a key part of modern energy systems, powering everything from recreational vehicles and boats

arXiv:2410.09166v2 Announce Type: replace Abstract: Battery energy storage systems (BESS) play an increasingly vital role in integrating renewable generation into power grids due to their ability to dynamically balance supply. Grid-tied batteries typically employ power converters, where part-load efficiencies vary non-linearly. While this non-linearity can be modeled with high accuracy, it poses challenges for optimization, particularly in ensuring computational tractability. In this paper, we consider a non-linear BESS formulation based on the Energy Reservoir Model (ERM). A data-driven approach is introduced with the input-convex neural network (ICNN) to approximate the nonlinear efficiency with a convex function. The epigraph of the convex function is used to engender a convex program for battery ERM optimization. This relaxed ICNN method is applied to two battery optimization use-cases: PV smoothing and revenue maximization, and it is compared with three other ERM formulations

arXiv:2609.36754v1 Announce Type: cross Abstract: Explicit prosodic cues may help automatic speech recognition (ASR) of spontaneous speech, but auxiliary representations typically require additional trainable components, making it unclear whether gains come from the auxiliary information or the fusion mechanism. We address this using a frozen HuBERT backbone and a 64-dimensional representation trained to predict log F0, voicing, Delta log F0, log energy, and spectral tilt. We compare a frozen-backbone recognizer (Baseline), trainable fusion with zero auxiliary input (Null), and the same fusion supplied with the learned representation (Learned). Across Buckeye, Switchboard, and AMI IHM, Null reduces WER by 0.71-1.45 points over Baseline, whereas Learned differs from Null by +0.07, -0.09, and +0.00 points, with no significant differences. However, removing or mismatching the representation at inference increases Learned WER. Thus, Learned depends on the representation yet shows no

arXiv:2609.35863v1 Announce Type: cross Abstract: Modern bioacoustic foundation models like Perch and BirdNET can identify species with high discriminative accuracy, yet their confidence scores are often uncalibrated and difficult to interpret as probabilities of real-world occurrence. This limits their use for ecological inference beyond threshold-based detection. We leverage a global annotated acoustic dataset (WABAD) to produce calibration priors for an acoustic model, optionally incorporating species-level information. We introduce new methods of fusing the acoustic predictions with geopriors, which empirically improves calibration while preserving discrimination. Together, these results suggest a path to simpler and more reliable acoustic monitoring for broad biodiversity.

arXiv:2609.37742v1 Announce Type: new Abstract: Modern cameras widely use temporal High Dynamic Range (HDR) to improve visibility by capturing a sequence of exposures with different integration times and fusing them into a single image. This process implicitly assumes that scene illumination remains sufficiently stable during capture. We introduce FLASH (Fusion-Level Attack by Saturating HDR), an external pulsed-light attack that deliberately attacks this assumption by creating cross-exposure inconsistency before downstream perception. FLASH exploits an algorithmic assumption rather than relying on sensor damage or hardware failure, and requires neither physical camera access, access to raw exposure brackets, knowledge of the fusion algorithm, nor exact phase lock to the camera. Across eight physical camera platforms spanning embedded, surveillance, photography, smartphone, and automotive use cases, and matched optical controls, FLASH causes pipeline-dependent darkening, overexposure,

arXiv:2609.37485v1 Announce Type: new Abstract: Bi-temporal change understanding, which localizes and characterizes what changed between two satellite images, is central to disaster response and environmental monitoring, spanning change detection, building localization, and damage assessment. Strong vision-language models address these tasks, but adapting them typically requires full fine-tuning or reinforcement learning, which is costly and unstable. We propose PoE-Fuse, a parameter-efficient framework that instead composes frozen foundation experts for geometry, grounding, and language, resampling their features onto a shared spatial grid and training only a lightweight fusion trunk. PoE-Fuse treats the aligned features as Gaussian observations of a latent scene state and fuses them by learned per-cell precision. This product-of-experts estimator strictly generalizes uniform summation and scalar gating, and extends to change fields by composing the precisions of the two timestamps.

arXiv:2609.37316v1 Announce Type: new Abstract: Agile flight tasks such as drone racing and pursuit-evasion require strong acceleration and precise turns, but the available thrust changes as the battery discharges and voltage drops under load. Conservative command limits make this variation easier to tolerate, at the cost of unused performance. We investigate how learned controllers can use that additional thrust while retaining the flight controller's voltage compensation and rate control. Our training simulator couples an identified load-transient battery model to rotor dynamics and firmware saturation. The feedforward policy receives filtered voltage during both training and deployment. Controlled ablations distinguish the benefit of a larger thrust-command range from that of voltage information. On a 38 g Crazyflie Brushless, the resulting policy reduces circle tracking error by 49% relative to stock-authority RL at 3.84 m/s, while preserving easy-task precision. Mean 20-lap race

arXiv:2609.37171v1 Announce Type: new Abstract: Retrieval-Augmented Generation has established itself as a fundamental framework in natural language processing, seamlessly integrating information retrieval with the generative capabilities of large language models. However, this process is fundamentally constrained by a critical challenge: semantic space mismatch between queries and retrieved contexts. We propose Knowledge-Aware Semantic Bridging (KASB), a novel framework that improves passage selection quality through semantic space alignment between queries and retrieved documents through intelligent knowledge fusion. Our approach leverages the complementary strengths of generative and retrieval-based knowledge through a multistage process that enhances both relevance and accuracy. We evaluate KASB on three popular open-domain Question Answering datasets to demonstrate the effectiveness of our approach.

arXiv:2609.37047v1 Announce Type: new Abstract: We propose a new spiking neural network (SNN) design to process static images and event streams using time-to-first-spike (TTFS) latencies. Our key research question is which architectural choices best accommodate local and online learning in multi-layer convolutional SNNs. This question is addressed via an original framework combining residual-like connections with multi-depth feature aggregation and consensus. The full SNN pipeline features an early-vision front end, to convert raw visual data into sparse spike latencies, a four-layer convolutional backbone trained layerwise with unsupervised spike-timing-dependent plasticity (STDP), a deterministic Multi-Depth Temporal Fusion (MDTF) and a final classifier trained with reward-modulated spike-timing-dependent plasticity (R-STDP). Rather than replacing early features in deeper layers, the proposed MDTF preserves early temporal evidence, adding sparse residual events from intermediate

arXiv:2609.36844v1 Announce Type: new Abstract: Transparent surfaces are ubiquitous in built environments, yet they remain a persistent failure case for robotic perception. RGB cameras perceive the background behind glass rather than the surface itself, while depth sensors such as LiDAR, time-of-flight, and RGB-D often return invalid or background measurements in transparent regions. As a result, systems that rely solely on optical sensing may misinterpret glass walls, doors, or mirrors as free space, compromising safe and reliable navigation. Existing glass segmentation approaches address this by learning visual cues such as reflections, boundaries, and semantic context from RGB images. While effective under favourable lighting and viewing conditions, these cues degrade in low-light environments, under glare, or when glass surfaces are featureless or partially occluded. In this work, we propose a multimodal framework that fuses millimetre-wave radar with RGB-D sensing for real-time

arXiv:2609.36432v1 Announce Type: new Abstract: LiDAR relocalization aims to estimate the global 6-DoF pose of a sensor in the environment. However, existing regression-based approaches often encounter limitations in dynamic or ambiguous scenarios, as they typically prioritize single-frame inference, leaving the potential of spatio-temporal consistency across scans not fully explored. In this paper, we propose a Temporal-aware Localization framework (TempLoc) designed to enhance the robustness of outdoor localization by effectively modeling sequential consistency. Specifically, a Global Coordinate Estimation module is first introduced to predict point-wise global coordinates and associated uncertainties for each LiDAR scan. A Prior Coordinate Generation module is then presented to estimate inter-frame point correspondences by the attention mechanism. Lastly, an Uncertainty-Guided Coordinate Fusion module is deployed to integrate both predictions of point correspondence in an

arXiv:2609.36056v1 Announce Type: new Abstract: In urban low-altitude flight, buildings reshape ambient wind into spatially varying 3D flow, making unmanned aerial vehicle (UAV) energy depend on local wind exposure as well as path length. However, building-resolved wind information is rarely available when a mission must be planned. Computational fluid dynamics (CFD) can produce high-fidelity urban flow fields, but each simulation is tied to a fixed inflow boundary condition and can take hours to days, which is incompatible with urban UAV missions that typically last minutes to tens of minutes. We present GeoWind2Plan, a geometry-to-wind-to-planning framework for mission-time 3D urban wind prediction and energy-efficient UAV planning. Given only a background wind vector, 3D building geometry, and a start-goal pair, GeoWind2Plan transforms the building geometry into a reference-wind frame, predicts mission-relevant 3D wind patches with a localized geometry-conditioned neural operator,

The new BMW i3 40 xDrive still comes with dual-motor all-wheel drive, but its battery has been downsized.

CleanCo annual loss comes as it ditches plans to buy large wind farm and convert a gold mine into pumped hydro project, and commits to 20 year extension of gas-fired generator. The post CleanCo posts loss as it exits wind and pumped hydro investments, doubles down on gas generator appeared first on Renew Economy.

The automaker has confirmed the factory where it will mass-produce the lithium-manganese-rich cells.

ibV Energy Partners, a developer of integrated solar and storage power plants across the U.S., and Exus Renewables North America, an independent owner, developer and operator of utility-scale renewable energy and energy storage projects, on September 29 announced that Exus has acquired four solar projects totaling 715 MWp from ibV. The deal builds on years […] The post Renewable Energy Group Acquires 715-MW Solar Power Portfolio appeared first on POWER Magazine.

Heliene today launches a new solar panel for the residential market — Heliene 108HC All-Black. The module will use American-made polysilicon, wafers and solar cells, bringing a fully American solar panel to the residential market for the first time. Sunrun has executed a purchase agreement of the Heliene 108HC All-Black module for residential solar projects… The post Heliene produces fully American solar panel for residential market appeared first on Solar Power World.

Using solar energy is good for the environment, but look down, and the grass isn't always greener. Solar farms can generate massive amounts of renewable energy, but when they're built in natural areas, they change the growing conditions underneath the panels. That can make it easy for native grasses to be squeezed out by invasive weeds and non-native plants. On top of that, fast-growing turf or other non-native grasses are often used as a less costly, more convenient replacement in reclamation efforts.

Windpower Monthly rounds up the latest wind power technology patents filed and granted in the past week.

Germany generated as much solar energy by the end of September as it did during the whole of 2025, according to industry association BSW-Solar – and almost three times more than has been produced in Australia over the same period. By 27 September, Germany’s net electricity generation from solar in 2026 had reached 90.2 terawatt […] The post Germany smashes PV record, produces three times more solar power than Australia so far this year appeared first on Renew Economy.

Most sensors can measure only one thing at a time, like a thermometer for temperature or a pressure gauge for pressure. Measuring two properties accurately from the same surface at the same moment usually means using two separate instruments—adding cost and complexity to the process.

Volkswagen announced multiple deals with China's Gotion to make LFP batteries for mass-market EVs.

In a recent interview, BYD's Stella Li said that the company will "have one model" with solid-state batteries next year.

CertainTeed has launched a new solar roofing system, Landmark PWR. Built on CertainTeed’s Landmark roofing portfolio, Landmark PWR combines roof protection with solar power in a single integrated solution. “The Landmark PWR solar roof represents the next evolution of our integrated roofing and solar strategy,” said Andrew Wickham, director of product management. “As homeowner demand… The post CertainTeed releases new solar roofing system Landmark PWR appeared first on Solar Power World.

Quantum batteries are an emerging area of research, with progress coming from theoretical studies and proof-of-principle experiments in small quantum systems. Unlike conventional chemical batteries used in everyday life, they use quantum systems to store and transfer energy. Researchers are exploring them as potential future energy sources for quantum processors and other quantum technologies.

Elisha Brabin, 36, and three of her children, died after a blaze at their home in Bootle, Merseyside.

Australian households have installed a record number of rooftop solar systems and home batteries so far this year, well above official forecasts. The post Australian households installed record amount of rooftop solar and home batteries in first half of 2026 appeared first on Renew Economy.

Next-generation geothermal is moving from technical promise to commercial deployment. Advances in drilling and reservoir engineering are making it possible to reach heat resources in more locations. The post From Underground Heat to Reliable Power: Engineering Geothermal for the Field appeared first on POWER Magazine.

Trump administration appears to have bet on the wrong horse, with renewables surging and coal power shrinking despite his bluster and conspiracy theories. The post Trump unable to stop clean energy revolution, as wind and solar output surges and coal shrinks appeared first on Renew Economy.

arXiv:2608.02769v2 Announce Type: replace-cross Abstract: Multimodal supervised learning seeks to leverage multiple heterogeneous data sources to improve predictive performance. A central challenge is determining the fusion granularity across modalities: over-integration may amplify noise while under-integration fails to exploit cross-modal dependence. Existing approaches rely on pre-specified fusion architectures, from early to late fusion, that may not adapt to the underlying dependence structure among modalities. We propose DAIF, a data adaptive intermediate fusion framework that combines random matrix theory and non-parametric dependence measures to learn fusion structure directly from data. We operate under a Bayesian multimodal factor model where the prior on the latent factors determines the cross-modal dependence. Our method clusters modalities based on estimated intermodal dependence, then performs clusterwise empirical Bayes estimation of the priors. These estimated priors