# Research Papers — 2026-03 · bundle page 186 of 243 > Full-text markdown of papers #9251–9300 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/186 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/185.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/187.md) ### Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems Authors: Zongqian Li, Tengchao Lv, Shaohan Huang, Yixuan Su, Qinzheng Sun, Qiufeng Yin, Ying Xin, Scarlett Li, Lei Cui, Nigel Collier, Furu Wei Published: 2026-03-08 Categories: cs.CL, cs.GL, cs.LG arXiv: https://arxiv.org/abs/2603.07779v1 Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing and difficulty scaling. We introduce a four-stage Data Processing Framework encompassing collection, processing, filtering, and verification, incorporating Automatic Difficulty Filtering via an LLM-based predict-calibrate-select framework that leverages multi-dimensional difficulty metrics across five weighted dimensions to retain challenging problems while removing simplistic ones. The resulting MicroCoder dataset comprises tens of thousands of curated real competitive programming problems from diverse platforms, emphasizing recency and difficulty. Evaluations on strictly unseen LiveCodeBench demonstrate that MicroCoder achieves 3x larger performance gains within 300 training steps compared to widely-used baseline datasets of comparable size, with consistent advantages under both GRPO and its variant training algorithms. The MicroCoder dataset delivers obvious improvements on medium and hard problems across different model sizes, achieving up to 17.2% relative gains in overall performance where model capabilities are most stretched. These results validate that difficulty-aware data curation improves model performance on challenging tasks, providing multiple insights for dataset creation in code generation. --- ### Lindbladian Learning with Neural Differential Equations Authors: Timothy Heightman, Roman Aseguinolaza Gallo, Edward Jiang, JRM Saavedra, Antonio Acín, Marcin Płodzień Published: 2026-03-08 Categories: quant-ph, cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2603.07778v1 Inferring the dynamical generator of a many-body quantum system from measurement data is essential for the verification, calibration, and control of quantum processors. When the system is open, this task becomes considerably harder than in the purely unitary case, because coherent and dissipative mechanisms can produce similar measurement statistics and long-time data can be insensitive to coherent couplings. Here we tackle this so-called Lindbladian learning problem of open-system characterisation with maximum-likelihood on Pauli measurements at multiple experimentally friendly \emph{transient} times, exploiting the richer information content of transient dynamics. To navigate the resulting non-convex likelihood loss-landscape, we augment the physical model neural differential-equation term, which is progressively removed during training to distil an interpretable Lindbladian solution. Our method reliably learns open-system dynamics across neutral-atom (with 2D connectivity) and superconducting Hamiltonians, as well as the Heisenberg XYZ, and PXP models on a spin-1/2 chain. For the dissipative part, we show robustness over phase noise, thermal noise, and their combination. Our algorithm can robustly infer these dissipative systems over noise-to-signal ratios spanning four orders of magnitude, and system sizes up to $N=6$ qubits with fewer than $5 \times 10^5$ shots. --- ### Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models Authors: Zongqian Li, Shaohan Huang, Zewen Chi, Yixuan Su, Lexin Zhou, Li Dong, Nigel Collier, Furu Wei Published: 2026-03-08 Categories: cs.LG, cs.CL, cs.GL arXiv: https://arxiv.org/abs/2603.07777v1 Modern code generation models exhibit longer outputs, accelerated capability growth, and changed training dynamics, rendering traditional training methodologies, algorithms, and datasets ineffective for improving their performance. To address these training bottlenecks, we propose MicroCoder-GRPO, an improved Group Relative Policy Optimization approach with three innovations: conditional truncation masking to improve long output potential while maintaining training stability, diversity-determined temperature selection to maintain and encourage output diversity, and removal of KL loss with high clipping ratios to facilitate solution diversity. MicroCoder-GRPO achieves up to 17.6% relative improvement over strong baselines on LiveCodeBench v6, with more pronounced gains under extended context evaluation. Additionally, we release MicroCoder-Dataset, a more challenging training corpus that achieves 3x larger performance gains than mainstream datasets on LiveCodeBench v6 within 300 training steps, and MicroCoder-Evaluator, a robust framework with approximately 25% improved evaluation accuracy and around 40% faster execution. Through comprehensive analysis across more than thirty controlled experiments, we reveal 34 training insights across seven main aspects, demonstrating that properly trained models can achieve competitive performance with larger counterparts. --- ### Parameterized Brushstroke Style Transfer Authors: Uma Meleti, Siyu Huang Published: 2026-03-08 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2603.07776v1 Computer Vision-based Style Transfer techniques have been used for many years to represent artistic style. However, most contemporary methods have been restricted to the pixel domain; in other words, the style transfer approach has been modifying the image pixels to incorporate artistic style. However, real artistic work is made of brush strokes with different colors on a canvas. Pixel-based approaches are unnatural for representing these images. Hence, this paper discusses a style transfer method that represents the image in the brush stroke domain instead of the RGB domain, which has better visual improvement over pixel-based methods. --- ### Geometric Knowledge-Assisted Federated Dual Knowledge Distillation Approach Towards Remote Sensing Satellite Imagery Authors: Luyao Zou, Fei Pan, Jueying Li, Yan Kyaw Tun, Apurba Adhikary, Zhu Han, Hayoung Oh Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07774v1 Federated learning (FL) has recently become a promising solution for analyzing remote sensing satellite imagery (RSSI). However, the large scale and inherent data heterogeneity of images collected from multiple satellites, where the local data distribution of each satellite differs from the global one, present significant challenges to effective model training. To address this issue, we propose a Geometric Knowledge-Guided Federated Dual Knowledge Distillation (GK-FedDKD) framework for RSSI analysis. In our approach, each local client first distills a teacher encoder (TE) from multiple student encoders (SEs) trained with unlabeled augmented data. The TE is then connected with a shared classifier to form a teacher network (TN) that supervises the training of a new student network (SN). The intermediate representations of the TN are used to compute local covariance matrices, which are aggregated at the server to generate global geometric knowledge (GGK). This GGK is subsequently employed for local embedding augmentation to further guide SN training. We also design a novel loss function and a multi-prototype generation pipeline to stabilize the training process. Evaluation over multiple datasets showcases that the proposed GK-FedDKD approach is superior to the considered state-of-the-art baselines, e.g., the proposed approach with the Swin-T backbone surpasses previous SOTA approaches by an average 68.89% on the EuroSAT dataset. --- ### ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs Authors: Yuzhuang Xu, Xu Han, Yuxuan Li, Wanxiang Che Published: 2026-03-08 Categories: cs.DC, cs.CL arXiv: https://arxiv.org/abs/2603.07770v2 Although existing frameworks for large language model (LLM) inference on CPUs are mature, they fail to fully exploit the computation potential of many-core CPU platforms. Many-core CPUs are widely deployed in web servers and high-end networking devices, and are typically organized into multiple NUMA nodes that group cores and memory. Current frameworks largely overlook the substantial overhead of cross-NUMA memory access, limiting inference scalability and intelligence enabling on such platforms. To address this limitation, we build ArcLight, a lightweight LLM inference architecture designed from the ground up for many-core CPUs. ArcLight integrates efficient memory management and thread scheduling, and introduces finely controlled tensor parallelism to mitigate the cross-node memory access wall. Experimental results show that ArcLight significantly surpasses the performance ceiling of mainstream frameworks, achieving up to 46% higher inference throughput. Moreover, ArcLight maintains compatibility with arbitrary CPU devices. ArcLight is publicly available at https://github.com/OpenBMB/ArcLight. --- ### MedQ-Deg: A Multidimensional Benchmark for Evaluating MLLMs Across Medical Image Quality Degradations Authors: Jiyao Liu, Junzhi Ning, Chenglong Ma, Wanying Qu, Jianghan Shen, Siqi Luo, Jinjie Wei, Jin Ye, Pengze Li, Tianbin Li, Jiashi Lin, Hongming Shan et al. Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07769v1 Despite impressive performance on standard benchmarks, multimodal large language models (MLLMs) face critical challenges in real-world clinical environments where medical images inevitably suffer various quality degradations. Existing benchmarks exhibit two key limitations: (1) absence of large-scale, multidimensional assessment across medical image quality gradients and (2) no systematic confidence calibration analysis. To address these gaps, we present MedQ-Deg, a comprehensive benchmark for evaluating medical MLLMs under image quality degradations. MedQ-Deg provides multi-dimensional evaluation spanning 18 distinct degradation types, 30 fine-grained capability dimensions, and 7 imaging modalities, with 24,894 question-answer pairs. Each degradation is implemented at 3 severity degrees, calibrated by expert radiologists. We further introduce Calibration Shift metric, which quantifies the gap between a model's perceived confidence and actual performance to assess metacognitive reliability under degradation. Our comprehensive evaluation of 40 mainstream MLLMs reveals several critical findings: (1) overall model performance degrades systematically as degradation severity increases, (2) models universally exhibit the AI Dunning-Kruger Effect, maintaining inappropriately high confidence despite severe accuracy collapse, and (3) models display markedly differentiated behavioral patterns across capability dimensions, imaging modalities, and degradation types. We hope MedQ-Deg drives progress toward medical MLLMs that are robust and trustworthy in real clinical practice. --- ### QuadAI at SemEval-2026 Task 3: Ensemble Learning of Hybrid RoBERTa and LLMs for Dimensional Aspect-Based Sentiment Analysis Authors: A. J. W. de Vink, Filippos Karolos Ventirozos, Natalia Amat-Lefort, Lifeng Han Published: 2026-03-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.07766v1 We present our system for SemEval-2026 Task 3 on dimensional aspect-based sentiment regression. Our approach combines a hybrid RoBERTa encoder, which jointly predicts sentiment using regression and discretized classification heads, with large language models (LLMs) via prediction-level ensemble learning. The hybrid encoder improves prediction stability by combining continuous and discretized sentiment representations. We further explore in-context learning with LLMs and ridge-regression stacking to combine encoder and LLM predictions. Experimental results on the development set show that ensemble learning significantly improves performance over individual models, achieving substantial reductions in RMSE and improvements in correlation scores. Our findings demonstrate the complementary strengths of encoder-based and LLM-based approaches for dimensional sentiment analysis. Our development code and resources will be shared at https://github.com/aaronlifenghan/ABSentiment --- ### Using GPUs And LLMs Can Be Satisfying for Nonlinear Real Arithmetic Problems Authors: Christopher Brix, Julia Walczak, Nils Lommen, Thomas Noll Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07764v1 Solving quantifier-free non-linear real arithmetic (NRA) problems is a computationally hard task. To tackle this problem, prior work proposed a promising approach based on gradient descent. In this work, we extend their ideas and combine LLMs and GPU acceleration to obtain an efficient technique. We have implemented our findings in the novel SMT solver GANRA (GPU Accelerated solving of Nonlinear Real Arithmetic problems). We evaluate GANRA on two different NRA benchmarks and demonstrate significant improvements over the previous state of the art. In particular, on the Sturm-MBO benchmark, we can prove satisfiability for more than five times as many instances in less than 1/20th of the previous state-of-the-art runtime. --- ### DECADE: A Temporally-Consistent Unsupervised Diffusion Model for Enhanced Rb-82 Dynamic Cardiac PET Image Denoising Authors: Yinchi Zhou, Liang Guo, Huidong Xie, Yuexi Du, Ashley Wang, Menghua Xia, Tian Yu, Ramesh Fazzone-Chettiar, Christopher Weyman, Bruce Spottiswoode, Vladimir Panin, Kuangyu Shi et al. Published: 2026-03-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.07759v1 Rb-82 dynamic cardiac PET imaging is widely used for the clinical diagnosis of coronary artery disease (CAD), but its short half-life results in high noise levels that degrade dynamic frame quality and parametric imaging. The lack of paired clean-noisy training data, rapid tracer kinetics, and frame-dependent noise variations further limit the effectiveness of existing deep learning denoising methods. We propose DECADE (A Temporally-Consistent Unsupervised Diffusion model for Enhanced Rb-82 CArdiac PET DEnoising), an unsupervised diffusion framework that generalizes across early- to late-phase dynamic frames. DECADE incorporates temporal consistency during both training and iterative sampling, using noisy frames as guidance to preserve quantitative accuracy. The method was trained and evaluated on datasets acquired from Siemens Vision 450 and Siemens Biograph Vision Quadra scanners. On the Vision 450 dataset, DECADE consistently produced high-quality dynamic and parametric images with reduced noise while preserving myocardial blood flow (MBF) and myocardial flow reserve (MFR). On the Quadra dataset, using 15%-count images as input and full-count images as reference, DECADE outperformed UNet-based and other diffusion models in image quality and K1/MBF quantification. The proposed framework enables effective unsupervised denoising of Rb-82 dynamic cardiac PET without paired training data, supporting clearer visualization while maintaining quantitative integrity. --- ### AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos Authors: Teng Yan, Yihan Liu, Jiongxu Chen, Teng Wang, Jiaqi Li, Bingzhuo Zhong Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07758v1 Long-term language-guided referring in fixed-view videos is challenging: the referent may be occluded or leave the scene for long intervals and later re-enter, while framewise referring pipelines drift as re-identification (ReID) becomes unreliable. AR2-4FV leverages background stability for long-term referring. An offline Anchor Bank is distilled from static background structures; at inference, the text query is aligned with this bank to produce an Anchor Map that serves as persistent semantic memory when the referent is absent. An anchor-based re-entry prior accelerates re-capture upon return, and a lightweight ReID-Gating mechanism maintains identity continuity using displacement cues in the anchor frame. The system predicts per-frame bounding boxes without assuming the target is visible in the first frame or explicitly modeling appearance variations. AR2-4FV achieves +10.3% Re-Capture Rate (RCR) improvement and -24.2% Re-Capture Latency (RCL) reduction over the best baseline, and ablation studies further confirm the benefits of the Anchor Map, re-entry prior, and ReID-Gating. --- ### Whitening Reveals Cluster Commitment as the Geometric Separator of Hallucination Types Authors: Matic Korun Published: 2026-03-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.07755v1 A geometric hallucination taxonomy distinguishes three failure types -- center-drift (Type~1), wrong-well convergence (Type~2), and coverage gaps (Type~3) -- by their signatures in embedding cluster space. Prior work found Types~1 and~2 indistinguishable in full-dimensional contextual measurement. We address this through PCA-whitening and eigenspectrum decomposition on GPT-2-small, using multi-run stability analysis (20 seeds) with prompt-level aggregation. Whitening transforms the micro-signal regime into a space where peak cluster alignment (max\_sim) separates Type~2 from Type~3 at Holm-corrected significance, with condition means following the taxonomy's predicted ordering: Type~2 (highest commitment) $>$ Type~1 (intermediate) $>$ Type~3 (lowest). A first directionally stable but underpowered hint of Type~1/2 separation emerges via the same metric, generating a capacity prediction for larger models. Prompt diversification from 15 to 30 prompts per group eliminates a false positive in whitened entropy that appeared robust at the smaller set, demonstrating prompt-set sensitivity in the micro-signal regime. Eigenspectrum decomposition localizes this artifact to the dominant principal components and confirms that Type~1/2 separation does not emerge in any spectral band, rejecting the spectral mixing hypothesis. The contribution is threefold: whitening as preprocessing that reveals cluster commitment as the theoretically correct separating metric, evidence that the Type~1/2 boundary is a capacity limitation rather than a measurement artifact, and a methodological finding about prompt-set fragility in near-saturated representation spaces. --- ### Uncertainty-Gated Generative Modeling Authors: Xingrui Gu, Haixi Zhang Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07753v1 Financial time-series forecasting is a high-stakes problem where regime shifts and shocks make point-accurate yet overconfident models dangerous. We propose Uncertainty-Gated Generative Modeling (UGGM), which treats uncertainty as an internal control signal that gates (i) representation via gated reparameterization, (ii) propagation via similarity and confidence routing, and (iii) generation via uncertainty-controlled predictive distributions, together with uncertainty-driven regularization and calibration to curb miscalibration. Instantiated on Weak Innovation AutoEncoder (WIAE-GPF), our UG-WIAE-GPF significantly improves risk-sensitive forecasting, delivering a 63.5\% MSE reduction on NYISO (0.3508 $\rightarrow$ 0.1281), with improved robustness under shock intervals (mSE: 0.2739 $\rightarrow$ 0.1748). --- ### 3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models Authors: Shaoxiong Zhan, Yanlin Lai, Zheng Liu, Hai Lin, Shen Li, Xiaodong Cai, Zijian Lin, Wen Huang, Hai-Tao Zheng Published: 2026-03-08 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2603.07751v2 Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical ``spatial intelligence gap,'' where models fail to construct coherent 3D mental representations from 2D observations. We uncover this gap via diagnostic analyses showing the bottleneck is a missing view-consistent spatial interface rather than insufficient visual features or weak reasoning. To bridge this, we introduce \textbf{3ViewSense}, a framework that grounds spatial reasoning in Orthographic Views. Drawing on engineering cognition, we propose a ``Simulate-and-Reason'' mechanism that decomposes complex scenes into canonical orthographic projections to resolve geometric ambiguities. By aligning egocentric perceptions with these allocentric references, our method facilitates explicit mental rotation and reconstruction. Empirical results on spatial reasoning benchmarks demonstrate that our method significantly outperforms existing baselines, with consistent gains on occlusion-heavy counting and view-consistent spatial reasoning. The framework also improves the stability and consistency of spatial descriptions, offering a scalable path toward stronger spatial intelligence in multimodal systems.~\footnote{https://github.com/Jasaxion/3ViewSense} --- ### Hide and Find: A Distributed Adversarial Attack on Federated Graph Learning Authors: Jinshan Liu, Ken Li, Jiazhe Wei, Bin Shi, Bo Dong Published: 2026-03-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.07743v1 Federated Graph Learning (FedGL) is vulnerable to malicious attacks, yet developing a truly effective and stealthy attack method remains a significant challenge. Existing attack methods suffer from low attack success rates, high computational costs, and are easily identified and smoothed by defense algorithms. To address these challenges, we propose \textbf{FedShift}, a novel two-stage "Hide and Find" distributed adversarial attack. In the first stage, before FedGL begins, we inject a learnable and hidden "shifter" into part of the training data, which subtly pushes poisoned graph representations toward a target class's decision boundary without crossing it, ensuring attack stealthiness during training. In the second stage, after FedGL is complete, we leverage the global model information and use the hidden shifter as an optimization starting point to efficiently find the adversarial perturbations. During the final attack, we aggregate these perturbations from multiple malicious clients to form the final effective adversarial sample and trigger the attack. Extensive experiments on six large-scale datasets demonstrate that our method achieves the highest attack effectiveness compared to existing advanced attack methods. In particular, our attack can effectively evade 3 mainstream robust federated learning defense algorithms and converges with a time cost reduction of over 90\%, highlighting its exceptional stealthiness, robustness, and efficiency. --- ### Large Language Model for Discrete Optimization Problems: Evaluation and Step-by-step Reasoning Authors: Tianhao Qian, Guilin Qi, Z. Y. Wu, Ran Gu, Xuanyi Liu, Canchen Lyu Published: 2026-03-08 Categories: cs.AI, cs.CL, math.OC arXiv: https://arxiv.org/abs/2603.07733v1 This work investigated the capabilities of different models, including the Llama-3 series of models and CHATGPT, with different forms of expression in solving discrete optimization problems by testing natural language datasets. In contrast to formal datasets with a limited scope of parameters, our dataset included a variety of problem types in discrete optimization problems and featured a wide range of parameter magnitudes, including instances with large parameter sets, integrated with augmented data. It aimed to (1) provide an overview of LLMs' ability in large-scale problems, (2) offer suggestions to those who want to solve discrete optimization problems automatically, and (3) regard the performance as a benchmark for future research. These datasets included original, expanded and augmented datasets. Among these three datasets, the original and augmented ones aimed for evaluation while the expanded one may help finetune a new model. In the experiment, comparisons were made between strong and week models, CoT methods and No-CoT methods on various datasets. The result showed that stronger model performed better reasonably. Contrary to general agreement, it also showed that CoT technique was not always effective regarding the capability of models and disordered datasets improved performance of models on easy to-understand problems, even though they were sometimes with high variance, a manifestation of instability. Therefore, for those who seek to enhance the automatic resolution of discrete optimization problems, it is recommended to consult the results, including the line charts presented in the Appendix, as well as the conclusions drawn in this study for relevant suggestions. --- ### A Novel Multi-Agent Architecture to Reduce Hallucinations of Large Language Models in Multi-Step Structural Modeling Authors: Ziheng Geng, Jiachen Liu, Ran Cao, Lu Cheng, Dan M. Frangopol, Minghui Cheng Published: 2026-03-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.07728v1 Large language models (LLMs) such as GPT and Gemini have demonstrated remarkable capabilities in contextual understanding and reasoning. The strong performance of LLMs has sparked growing interest in leveraging them to automate tasks traditionally dependent on human expertise. Recently, LLMs have been integrated into intelligent agents capable of operating structural analysis software (e.g., OpenSees) to construct structural models and perform analyses. However, existing LLMs are limited in handling multi-step structural modeling due to frequent hallucinations and error accumulation during long-sequence operations. To this end, this study presents a novel multi-agent architecture to automate the structural modeling and analysis using OpenSeesPy. First, problem analysis and construction planning agents extract key parameters from user descriptions and formulate a stepwise modeling plan. Node and element agents then operate in parallel to assemble the frame geometry, followed by a load assignment agent. The resulting geometric and load information is translated into executable OpenSeesPy scripts by code translation agents. The proposed architecture is evaluated on a benchmark of 20 frame problems over ten repeated trials, achieving 100% accuracy in 18 cases and 90% in the remaining two. The architecture also significantly improves computational efficiency and demonstrates scalability to larger structural systems. --- ### A Lightweight MPC Bidding Framework for Brand Auction Ads Authors: Yuanlong Chen, Bowen Zhu, Bing Xia, Yichuan Wang Published: 2026-03-08 Categories: cs.GT, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.07721v2 Brand advertising plays a critical role in building long-term consumer awareness and loyalty, making it a key objective for advertisers across digital platforms. Although real-time bidding has been extensively studied, there is limited literature on algorithms specifically tailored for brand auction ads that fully leverage their unique characteristics. In this paper, we propose a lightweight Model Predictive Control (MPC) framework designed for brand advertising campaigns, exploiting the inherent attributes of brand ads -- such as stable user engagement patterns and fast feedback loops -- to simplify modeling and improve efficiency. Our approach utilizes online isotonic regression to construct monotonic bid-to-spend and bid-to-conversion models directly from streaming data, eliminating the need for complex machine learning models. The algorithm operates fully online with low computational overhead, making it highly practical for real-world deployment. Simulation results demonstrate that our approach significantly improves spend efficiency and cost control compared to baseline strategies, providing a scalable and easily implementable solution for modern brand advertising platforms. --- ### Rigidity in LLM Bandits with Implications for Human-AI Dyads Authors: Haomiaomiao Wang, Tomás E Ward, Lili Zhang Published: 2026-03-08 Categories: cs.AI, cs.GT, cs.HC arXiv: https://arxiv.org/abs/2603.07717v1 We test whether LLMs show robust decision biases. Treating models as participants in two-arm bandits, we ran 20000 trials per condition across four decoding configurations. Under symmetric rewards, models amplified positional order into stubborn one-arm policies. Under asymmetric rewards, they exploited rigidly yet underperformed an oracle and rarely re-checked. The observed patterns were consistent across manipulations of temperature and top-p, with top-k held at the provider default, indicating that the qualitative behaviours are robust to the two decoding knobs typically available to practitioners. Crucially, moving beyond descriptive metrics to computational modelling, a hierarchical Rescorla-Wagner-softmax fit revealed the underlying strategies: low learning rates and very high inverse temperatures, which together explain both noise-to-bias amplification and rigid exploitation. These results position minimal bandits as a tractable probe of LLM decision tendencies and motivate hypotheses about how such biases could shape human-AI interaction. --- ### Reverse Distillation: Consistently Scaling Protein Language Model Representations Authors: Darius Catrina, Christian Bepler, Samuel Sledzieski, Rohit Singh Published: 2026-03-08 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2603.07710v1 Unlike the predictable scaling laws in natural language processing and computer vision, protein language models (PLMs) scale poorly: for many tasks, models within the same family plateau or even decrease in performance, with mid-sized models often outperforming the largest in the family. We introduce Reverse Distillation, a principled framework that decomposes large PLM representations into orthogonal subspaces guided by smaller models of the same family. The resulting embeddings have a nested, Matryoshka-style structure: the first k dimensions of a larger model's embedding are exactly the representation from the smaller model. This ensures that larger reverse-distilled models consistently outperform smaller ones. A motivating intuition is that smaller models, constrained by capacity, preferentially encode broadly-shared protein features. Reverse distillation isolates these shared features and orthogonally extracts additional contributions from larger models, preventing interference between the two. On ProteinGym benchmarks, reverse-distilled ESM-2 variants outperform their respective baselines at the same embedding dimensionality, with the reverse-distilled 15 billion parameter model achieving the strongest performance. Our framework is generalizable to any model family where scaling challenges persist. Code and trained models are available at https://github.com/rohitsinghlab/plm_reverse_distillation. --- ### YAQIN: Culturally Sensitive, Agentic AI for Mental Healthcare Support Among Muslim Women in the UK Authors: Yasmin Zaraket, Céline Mougenot Published: 2026-03-08 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.07709v1 Mental healthcare services in the UK lack tools and resources to address the cultural needs of Muslim women, often leaving them feeling as though their values are pathologised and limiting trust and engagement (1). Despite growing awareness of cultural competency, few interventions integrate Islamic frameworks into therapeutic support. This report investigates the design and evaluation of YAQIN, a co-designed AI-based application supporting culturally and faith-sensitive mental health engagement for Muslim women. With almost 1.9 million Muslim women in England in 2021, YAQIN responds to a gap in care (2). It leverages AIś anonymity and continuous support through a faith-aware chatbot and guided journaling tool grounded in user-centred design and Islamic psychology. The YAQIN design research methodology comprised three stages: contextual investigation and literature review, user research with N=14 stakeholders including Muslim women and mental health experts, and prototype development informed by deductive thematic analysis, personas, journey maps, and design specifications. Evaluation involved a co-designed user study with five participants: four Muslim women and one mental health expert who reviewed therapeutic alignment and cultural sensitivity after using the chatbot prototype. Feedback focused on tone, faith relevance, emotional resonance, and the Retrieval-Augmented Generation pipeline enabling contextual continuity. Participants highlighted YAQINś ability to bridge cultural gaps in trust and therapeutic confidence. Feedback included suggestions of including linguistic diversity and routine-based guidance. This project demonstrates how culturally sensitive AI can improve mental healthcare accessibility and trust for marginalised communities and highlights the potential of faith-integrated technology in healthcare innovation. --- ### VoiceSHIELD-Small: Real-Time Malicious Speech Detection and Transcription Authors: Sumit Ranjan, Sugandha Sharma, Ubaid Abbas, Puneeth N Ail Published: 2026-03-08 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.07708v1 Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt injection, social engineering, and harmful voice commands. Traditional security methods rely on converting speech to text and then filtering that text, which introduces delays and can ignore important audio cues. This paper introduces VoiceSHIELD-Small, a lightweight model that works in real time. It can transcribe speech and detect whether it is safe or harmful, all in one step. Built on OpenAI's Whisper-small encoder, VoiceSHIELD adds a mean-pooling layer and a simple classification head. It takes just 90-120 milliseconds to classify audio on mid-tier GPUs, while transcription happens at the same time. Tested on a balanced set of 947 audio clips, the model achieved 99.16 percent accuracy and an F1 score of 0.9865. At the default setting, it missed 2.33 percent of harmful inputs. Cross-validation showed consistent performance (F1 standard deviation = 0.0026). The paper also covers the model's design, training data, performance trade-offs, and responsible use guidelines. VoiceSHIELD is released under the MIT license to encourage further research and adoption in voice AI security. --- ### Deep Incentive Design with Differentiable Equilibrium Blocks Authors: Vinzenz Thoma, Georgios Piliouras, Luke Marris Published: 2026-03-08 Categories: cs.GT, cs.LG arXiv: https://arxiv.org/abs/2603.07705v2 Automated design of multi-agent interactions with desirable equilibrium outcomes is inherently difficult due to the computational hardness, non-uniqueness, and instability of the resulting equilibria. In this work, we propose the use of game-agnostic differentiable equilibrium blocks (DEBs) as modules in a novel, differentiable framework to address a wide variety of incentive design problems from economics and computer science. We call this framework deep incentive design (DID). To validate our approach, we examine three diverse, challenging incentive design tasks: contract design, machine scheduling, and inverse equilibrium problems. For each task, we train a single neural network using a unified pipeline and DEB. This architecture solves the full distribution of problem instances, parameterized by a context, handling all games across a wide range of scales (from two to sixteen actions per player). --- ### PARSE: Part-Aware Relational Spatial Modeling Authors: Yinuo Bai, Peijun Xu, Kuixiang Shao, Yuyang Jiao, Jingxuan Zhang, Kaixin Yao, Jiayuan Gu, Jingyi Yu Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07704v2 Inter-object relations underpin spatial intelligence, yet existing representations -- linguistic prepositions or object-level scene graphs -- are too coarse to specify which regions actually support, contain, or contact one another, leading to ambiguous and physically inconsistent layouts. To address these ambiguities, a part-level formulation is needed; therefore, we introduce PARSE, a framework that explicitly models how object parts interact to determine feasible and spatially grounded scene configurations. PARSE centers on the Part-centric Assembly Graph (PAG), which encodes geometric relations between specific object parts, and a Part-Aware Spatial Configuration Solver that converts these relations into geometric constraints to assemble collision-free, physically valid scenes. Using PARSE, we build PARSE-10K, a dataset of 10,000 3D indoor scenes constructed from real-image layout priors and a curated part-annotated shape database, each with dense contact structures and a part-level contact graph. With this structured, spatially grounded supervision, fine-tuning Qwen3-VL on PARSE-10K yields stronger object-level layout reasoning and more accurate part-level relation understanding; furthermore, leveraging PAGs as structural priors in 3D generation models leads to scenes with substantially improved physical realism and structural complexity. Together, these results show that PARSE significantly advances geometry-grounded spatial reasoning and supports the generation of physically consistent 3D scenes. --- ### Step-Size Decay and Structural Stagnation in Greedy Sparse Learning Authors: Pablo M. Berná Published: 2026-03-08 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2603.07703v1 Greedy algorithms are central to sparse approximation and stage-wise learning methods such as matching pursuit and boosting. It is known that the Power-Relaxed Greedy Algorithm with step sizes $m^{-α}$ may fail to converge when $α>1$ in general Hilbert spaces. In this work, we revisit this phenomenon from a sparse learning perspective. We study realizable regression problems with controlled feature coherence and derive explicit lower bounds on the residual norm, showing that over-decaying step-size schedules induce structural stagnation even in low-dimensional sparse settings. Numerical experiments confirm the theoretical predictions and illustrate the role of feature coherence. Our results provide insight into step-size design in greedy sparse learning. --- ### TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward Authors: Yihong Luo, Tianyang Hu, Weijian Luo, Jing Tang Published: 2026-03-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.07700v1 While few-step generative models have enabled powerful image and video generation at significantly lower cost, generic reinforcement learning (RL) paradigms for few-step models remain an unsolved problem. Existing RL approaches for few-step diffusion models strongly rely on back-propagating through differentiable reward models, thereby excluding the majority of important real-world reward signals, e.g., non-differentiable rewards such as humans' binary likeness, object counts, etc. To properly incorporate non-differentiable rewards to improve few-step generative models, we introduce TDM-R1, a novel reinforcement learning paradigm built upon a leading few-step model, Trajectory Distribution Matching (TDM). TDM-R1 decouples the learning process into surrogate reward learning and generator learning. Furthermore, we developed practical methods to obtain per-step reward signals along the deterministic generation trajectory of TDM, resulting in a unified RL post-training method that significantly improves few-step models' ability with generic rewards. We conduct extensive experiments ranging from text-rendering, visual quality, and preference alignment. All results demonstrate that TDM-R1 is a powerful reinforcement learning paradigm for few-step text-to-image models, achieving state-of-the-art reinforcement learning performances on both in-domain and out-of-domain metrics. Furthermore, TDM-R1 also scales effectively to the recent strong Z-Image model, consistently outperforming both its 100-NFE and few-step variants with only 4 NFEs. Project page: https://github.com/Luo-Yihong/TDM-R1 --- ### Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization Authors: Anirudh Satheesh, Pankaj Kumar Barman, Washim Uddin Mondal, Vaneet Aggarwal Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07698v1 We study infinite-horizon Constrained Markov Decision Processes (CMDPs) with general policy parameterizations and multi-layer neural network critics. Existing theoretical analyses for constrained reinforcement learning largely rely on tabular policies or linear critics, which limits their applicability to high-dimensional and continuous control problems. We propose a primal-dual natural actor-critic algorithm that integrates neural critic estimation with natural policy gradient updates and leverages Neural Tangent Kernel (NTK) theory to control function-approximation error under Markovian sampling, without requiring access to mixing-time oracles. We establish global convergence and cumulative constraint violation rates of $\tilde{\mathcal{O}}(T^-1/4)$ up to approximation errors induced by the policy and critic classes. Our results provide the first such guarantees for CMDPs with general policies and multi-layer neural critics, substantially extending the theoretical foundations of actor-critic methods beyond the linear-critic regime. --- ### Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregation Authors: Junkun Jiang, Jie Chen, Ho Yin Au, Jingyu Xiang Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07697v1 Vision-based motion capture solutions often struggle with occlusions, which result in the loss of critical joint information and hinder accurate 3D motion reconstruction. Other wearable alternatives also suffer from noisy or unstable data, often requiring extensive manual cleaning and correction to achieve reliable results. To address these challenges, we introduce the Masked Motion Diffusion Model (MMDM), a diffusion-based generative reconstruction framework that enhances incomplete or low-confidence motion data using partially available high-quality reconstructions within a Masked Autoencoder architecture. Central to our design is the Kinematic Attention Aggregation (KAA) mechanism, which enables efficient, deep, and iterative encoding of both joint-level and pose-level features, capturing structural and temporal motion patterns essential for task-specific reconstruction. We focus on learning context-adaptive motion priors, specialized structural and temporal features extracted by the same reusable architecture, where each learned prior emphasizes different aspects of motion dynamics and is specifically efficient for its corresponding task. This enables the architecture to adaptively specialize without altering its structure. Such versatility allows MMDM to efficiently learn motion priors tailored to scenarios such as motion refinement, completion, and in-betweening. Extensive evaluations on public benchmarks demonstrate that MMDM achieves strong performance across diverse masking strategies and task settings. The source code is available at https://github.com/jjkislele/MMDM. --- ### Compressed-Domain-Aware Online Video Super-Resolution Authors: Yuhang Wang, Hai Li, Shujuan Hou, Zhetao Dong, Xiaoyao Yang Published: 2026-03-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.07694v1 In bandwidth-limited online video streaming, videos are usually downsampled and compressed. Although recent online video super-resolution (online VSR) approaches achieve promising results, they are still compute-intensive and fall short of real-time processing at higher resolutions, due to complex motion estimation for alignment and redundant processing of consecutive frames. To address these issues, we propose a compressed-domain-aware network (CDA-VSR) for online VSR, which utilizes compressed-domain information, including motion vectors, residual maps, and frame types to balance quality and efficiency. Specifically, we propose a motion-vector-guided deformable alignment module that uses motion vectors for coarse warping and learns only local residual offsets for fine-tuned adjustments, thereby maintaining accuracy while reducing computation. Then, we utilize a residual map gated fusion module to derive spatial weights from residual maps, suppressing mismatched regions and emphasizing reliable details. Further, we design a frame-type-aware reconstruction module for adaptive compute allocation across frame types, balancing accuracy and efficiency. On the REDS4 dataset, our CDA-VSR surpasses the state-of-the-art method TMP, with a maximum PSNR improvement of 0.13 dB while delivering more than double the inference speed. The code will be released at https://github.com/sspBIT/CDA-VSR. --- ### RoboPCA: Pose-centered Affordance Learning from Human Demonstrations for Robot Manipulation Authors: Zhanqi Xiao, Ruiping Wang, Xilin Chen Published: 2026-03-08 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.07691v1 Understanding spatial affordances -- comprising the contact regions of object interaction and the corresponding contact poses -- is essential for robots to effectively manipulate objects and accomplish diverse tasks. However, existing spatial affordance prediction methods mainly focus on locating the contact regions while delegating the pose to independent pose estimation approaches, which can lead to task failures due to inconsistencies between predicted contact regions and candidate poses. In this work, we propose RoboPCA, a pose-centered affordance prediction framework that jointly predicts task-appropriate contact regions and poses conditioned on instructions. To enable scalable data collection for pose-centered affordance learning, we devise Human2Afford, a data curation pipeline that automatically recovers scene-level 3D information and infers pose-centered affordance annotations from human demonstrations. With Human2Afford, scene depth and the interaction object's mask are extracted to provide 3D context and object localization, while pose-centered affordance annotations are obtained by tracking object points within the contact region and analyzing hand-object interaction patterns to establish a mapping from the 3D hand mesh to the robot end-effector orientation. By integrating geometry-appearance cues through an RGB-D encoder and incorporating mask-enhanced features to emphasize task-relevant object regions into the diffusion-based framework, RoboPCA outperforms baseline methods on image datasets, simulation, and real robots, and exhibits strong generalization across tasks and categories. --- ### FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry Authors: Zhisong Xu, Takeshi Oishi Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07690v3 Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams, limiting practical deployment. We study bounded-memory streaming geometry from the perspective of memory organization: unlike language modeling, where useful information can often be compressed at token level, geometry-driven inference relies on coherent and mutually compatible observations across views. Under fixed memory budgets, retaining history as isolated entries can progressively fragment the geometric context needed for stable long-horizon matching and fusion. We therefore propose \textbf{FrameVGGT}, a bounded-memory framework that maintains a fixed-capacity set of complementary memory units for streaming geometry. In our implementation, each unit is instantiated as a frame-wise KV segment summarized by a compact key-space prototype, together with a sparse anchor tier for persistent long-range references. Across long-sequence 3D reconstruction, video depth estimation, and camera pose estimation, FrameVGGT achieves favorable accuracy--memory trade-offs under bounded budgets while maintaining more stable geometry over long streams. --- ### UniUncer: Unified Dynamic Static Uncertainty for End to End Driving Authors: Yu Gao, Jijun Wang, Zongzheng Zhang, Anqing Jiang, Yiru Wang, Yuwen Heng, Shuo Wang, Hao Sun, Zhangfeng Hu, Hao Zhao Published: 2026-03-08 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.07686v2 End-to-end (E2E) driving has become a cornerstone of both industry deployment and academic research, offering a single learnable pipeline that maps multi-sensor inputs to actions while avoiding hand-engineered modules. However, the reliability of such pipelines strongly depends on how well they handle uncertainty: sensors are noisy, semantics can be ambiguous, and interaction with other road users is inherently stochastic. Uncertainty also appears in multiple forms: classification vs. localization, and, crucially, in both static map elements and dynamic agents. Existing E2E approaches model only static-map uncertainty, leaving planning vulnerable to overconfident and unreliable inputs. We present UniUncer, the first lightweight, unified uncertainty framework that jointly estimates and uses uncertainty for both static and dynamic scene elements inside an E2E planner. Concretely: (1) we convert deterministic heads to probabilistic Laplace regressors that output per-vertex location and scale for vectorized static and dynamic entities; (2) we introduce an uncertainty-fusion module that encodes these parameters and injects them into object/map queries to form uncertainty-aware queries; and (3) we design an uncertainty-aware gate that adaptively modulates reliance on historical inputs (ego status or temporal perception queries) based on current uncertainty levels. The design adds minimal overhead and drops throughput by only $\sim$0.5 FPS while remaining plug-and-play for common E2E backbones. On nuScenes (open-loop), UniUncer reduces average L2 trajectory error by 7\%. On NavsimV2 (pseudo closed-loop), it improves overall EPDMS by 10.8\% and notable stage two gains in challenging, interaction-heavy scenes. Ablations confirm that dynamic-agent uncertainty and the uncertainty-aware gate are both necessary. --- ### Scalable Training of Mixture-of-Experts Models with Megatron Core Authors: Zijie Yan, Hongxiao Bai, Xin Yao, Dennis Liu, Tong Liu, Hongbin Liu, Pingtian Li, Evan Wu, Shiqing Fan, Li Tao, Robin Zhang, Yuzhong Wang et al. Published: 2026-03-08 Categories: cs.DC, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.07685v2 Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models. Because each token activates only a subset of experts, this sparsity allows total parameters to grow much faster than per-token computation, creating coupled constraints across memory, communication, and computation. Optimizing one dimension often shifts pressure to another, demanding co-design across the full system stack. We address these challenges for MoE training through integrated optimizations spanning memory (fine-grained recomputation, offloading, etc.), communication (optimized dispatchers, overlapping, etc.), and computation (Grouped GEMM, fusions, CUDA Graphs, etc.). The framework also provides Parallel Folding for flexible multi-dimensional parallelism, low-precision training support for FP8 and NVFP4, and efficient long-context training. On NVIDIA GB300 and GB200, it achieves 1,233/1,048 TFLOPS/GPU for DeepSeek-V3-685B and 974/919 TFLOPS/GPU for Qwen3-235B. As a performant, scalable, and production-ready open-source solution, it has been used across academia and industry for training MoE models ranging from billions to trillions of parameters on clusters scaling up to thousands of GPUs. This report explains how these techniques work, their trade-offs, and their interactions at the systems level, providing practical guidance for scaling MoE models with Megatron Core. --- ### Mitigating the Memory Bottleneck with Machine Learning-Driven and Data-Aware Microarchitectural Techniques Authors: Rahul Bera Published: 2026-03-08 Categories: cs.AR, cs.DC, cs.LG, cs.OS arXiv: https://arxiv.org/abs/2603.07683v1 Modern applications process massive data volumes that overwhelm the storage and retrieval capabilities of memory systems, making memory the primary performance and energy-efficiency bottleneck of computing systems. Although many microarchitectural techniques attempt to hide or tolerate long memory access latency, rapidly growing data footprints continue to outpace technology scaling, requiring more effective solutions. This dissertation shows that modern processors observe large amounts of application and system data during execution, yet many microarchitectural mechanisms make decisions largely independent of this information. Through four case studies, we demonstrate that such data-agnostic design leads to substantial missed opportunities for improving performance and energy efficiency. To address this limitation, this dissertation advocates shifting microarchitecture design from data-agnostic to data-informed. We propose mechanisms that (1) learn policies from observed execution behavior (data-driven design) and (2) exploit semantic characteristics of application data (data-aware design). We apply lightweight machine learning techniques and previously underexplored data characteristics across four processor components: a reinforcement learning-based hardware data prefetcher that learns memory access patterns online; a perceptron predictor that identifies memory requests likely to access off-chip memory; a reinforcement learning mechanism that coordinates data prefetching and off-chip prediction; and a mechanism that exploits repeatability in memory addresses and loaded values to eliminate predictable load instructions. Our extensive evaluation shows that the proposed techniques significantly improve performance and energy efficiency compared to prior state-of-the-art approaches. --- ### A Primer on Evolutionary Optimization Frameworks for Near-Field Multi-Source Localization Authors: Seyed Jalaleddin Mousavirad, Parisa Ramezani, Mattias O'Nils, Emil Björnson Published: 2026-03-08 Categories: cs.NE, eess.SP arXiv: https://arxiv.org/abs/2603.07676v2 This paper introduces evolutionary optimization as a grid-free training-free continuous-domain search mechanism for near-field multi-source localization, addressing the major limitations of grid-based subspace methods such as MUSIC and data-driven deep learning approaches. To this end, we develop two complementary evolutionary localization frameworks that operate directly on the continuous spherical-wave signal model and support arbitrary array geometries without requiring labeled data, discretized angle-range grids, or architectural constraints. The first framework, termed NEar-field MultimOdal DE (NEMO-DE) associates each individual in the evolutionary population to a single source and optimizes a residual least-squares objective in a sequential manner, updating the data residual and enforcing spatial separation to estimate multiple source locations. To overcome the limitation of NEMO-DE under large power imbalances among the sources, we propose the second framework, named NEar-field Eigen-subspace Fitting DE (NEEF-DE), which jointly encodes all source locations and minimizes a subspace-fitting criterion that aligns a model-based array response subspace with the received signal subspace. The proposed formulations are not intrinsically tied to a specific optimizer; however, this work adopts differential evolution (DE) as a representative evolutionary search strategy because of its simple implementation, small number of control parameters, and strong empirical performance in continuous nonconvex optimization problems. Numerical results show that the proposed frameworks provide competitive accuracy compared with MUSIC-type baselines while avoiding pre-defined grid construction and labeled training data. This work establishes evolutionary computation as a powerful and flexible paradigm for model-based near-field localization, paving the way for future innovations in this domain. --- ### Beyond Surrogates: A Quantitative Analysis for Inter-Metric Relationships Authors: Yuanhao Pu, Defu Lian, Enhong Chen Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07671v1 The Consistency property between surrogate losses and evaluation metrics has been extensively studied to ensure that minimizing a loss leads to metric optimality. However, the direct relationship between different evaluation metrics remains significantly underexplored. This theoretical gap results in the "Metric Mismatch" frequently observed in industrial applications, where gains in offline validation metrics fail to translate into online performance. To bridge this disconnection, this paper proposes a unified theoretical framework designed to quantify the relationships between metrics. We categorize metrics into different classes to facilitate a comparative analysis across different mathematical forms and interrogates these relationships through Bayes-Optimal Set and Regret Transfer. Through this framework, we provide a new perspective on identifying the structural asymmetry in regret transfer, enabling the design of evaluation systems that are theoretically guaranteed to align offline improvements with online objectives. --- ### Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers Authors: Pengfei Du Published: 2026-03-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.07670v1 Large language model (LLM) agents increasingly operate in settings where a single context window is far too small to capture what has happened, what was learned, and what should not be repeated. Memory -- the ability to persist, organize, and selectively recall information across interactions -- is what turns a stateless text generator into a genuinely adaptive agent. This survey offers a structured account of how memory is designed, implemented, and evaluated in modern LLM-based agents, covering work from 2022 through early 2026. We formalize agent memory as a \emph{write--manage--read} loop tightly coupled with perception and action, then introduce a three-dimensional taxonomy spanning temporal scope, representational substrate, and control policy. Five mechanism families are examined in depth: context-resident compression, retrieval-augmented stores, reflective self-improvement, hierarchical virtual context, and policy-learned management. On the evaluation side, we trace the shift from static recall benchmarks to multi-session agentic tests that interleave memory with decision-making, analyzing four recent benchmarks that expose stubborn gaps in current systems. We also survey applications where memory is the differentiating factor -- personal assistants, coding agents, open-world games, scientific reasoning, and multi-agent teamwork -- and address the engineering realities of write-path filtering, contradiction handling, latency budgets, and privacy governance. The paper closes with open challenges: continual consolidation, causally grounded retrieval, trustworthy reflection, learned forgetting, and multimodal embodied memory. --- ### FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration Authors: Congcong Bian, Haolong Ma, Hui Li, Zhongwei Shen, Xiaoqing Luo, Xiaoning Song, Xiao-Jun Wu Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07667v1 Spatial registration across different visual modalities is a critical but formidable step in multi-modality image fusion for real-world perception. Although several methods are proposed to address this issue, the existing registration-based fusion methods typically require extensive pre-registration operations, limiting their efficiency. To overcome these limitations, a general cross-modality registration method guided by visual priors is proposed for infrared and visible image fusion task, termed FusionRegister. Firstly, FusionRegister achieves robustness by learning cross-modality misregistration representations rather than forcing alignment of all differences, ensuring stable outputs even under challenging input conditions. Moreover, FusionRegister demonstrates strong generality by operating directly on fused results, where misregistration is explicitly represented and effectively handled, enabling seamless integration with diverse fusion methods while preserving their intrinsic properties. In addition, its efficiency is further enhanced by serving the backbone fusion method as a natural visual prior provider, which guides the registration process to focus only on mismatch regions, thereby avoiding redundant operations. Extensive experiments on three datasets demonstrate that FusionRegister not only inherits the fusion quality of state-of-the-art methods, but also delivers superior detail alignment and robustness, making it highly suitable for infrared and visible image fusion method. The code will be available at https://github.com/bociic/FusionRegister. --- ### AI-Driven Phase Identification from X-ray Hyperspectral Imaging of cycled Na-ion Cathode Materials Authors: Fayçal Adrar, Nicolas Folastre, Chloé Pablos, Stefan Stanescu, Sufal Swaraj, Raghvender Raghvender, François Cadiou, Laurence Croguennec, Matthieu Bugnet, Arnaud Demortière Published: 2026-03-08 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2603.07666v1 Na-ion batteries have emerged as viable candidates for large-scale energy storage applica- tions due to resource abundance and cost advantages. The constraints imposed on their performance and durability, for instance, by complex phase transformations in positive electrode materials during electrochemical cycling, can be addressed and are thus not detrimental to their development. However, diffusion-limited Na-ion transport can drive spatially heterogeneous phase nucleation and propagation, leading to multiphase coexis- tence and locally non-uniform electrochemical activity, generating complex reaction path- ways that challenge both mechanistic understanding and predictive material optimization. These challenges can be addressed by investigating single-crystalline regions of materials, i.e. down to the scale of individual particles, although such analyses are often constrained by energetically and/or spatially sparse hyperspectral datasets. Here, we developed an AI-driven method to process hyperspectral data under sparse sampling conditions and generate multiphase maps with nanometer-scale resolution over a micrometer-scale field of view. We applied this processing on scanning transmission X-ray microscopy (STXM) data to determine the distribution and coexistence of phases in individual particles of NaxV2(PO4)2F3 cathode materials, at different states of charge. The methodology relies on a workflow which combines a Gaussian mixture variational autoencoder (GMVAE) algorithm with the Pearson corre- lation coefficient to identify the sodium content and map their spatial distribution. Our approach reveals nanoscale phase heterogeneity and evolution within individual particles, and improves the reliability of phase detection by identifying ambiguity zones, false assign- ments, and transition phases localized at grain boundaries. --- ### Ref-DGS: Reflective Dual Gaussian Splatting Authors: Ningjing Fan, Yiqun Wang, Dong-Ming Yan, Peter Wonka Published: 2026-03-08 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2603.07664v3 The reflective appearance, especially strong and typically near-field specular reflections, poses a fundamental challenge for accurate surface reconstruction and novel view synthesis. Existing Gaussian splatting methods either fail to model near-field specular reflections or rely on explicit ray tracing at substantial computational cost. We present \textbf{Ref-DGS}, a reflective dual Gaussian splatting framework that addresses this trade-off by decoupling surface reconstruction from specular reflection within an efficient rasterization-based pipeline. Ref-DGS introduces a dual Gaussian scene representation consisting of geometry Gaussians and complementary local reflection Gaussians that capture near-field specular interactions without explicit ray tracing, along with a global environment reflection field for modeling far-field specular reflections. To predict specular radiance, we further propose a lightweight, physically-aware specular adaptive mixing shader that fuses global and local specular features. Experiments demonstrate that Ref-DGS achieves state-of-the-art performance on reflective scenes while training substantially faster than ray-based Gaussian methods. --- ### Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence Authors: Yuanyuan Gao, Hao Li, Yifei Liu, Xinhao Ji, Yuning Gong, Yuanjun Liao, Fangfu Liu, Manyuan Zhang, Yuchen Yang, Dan Xu, Xue Yang, Huaxi Huang et al. Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07660v1 The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding benchmarks by generating question-answer (QA) pairs from a limited number of manually annotated datasets, rather than systematically annotating new large-scale 3D scenes from raw web data. As a result, their scalability is severely constrained, and model performance is further hindered by domain gaps inherent in these narrowly curated datasets. In this work, we propose Holi-Spatial, the first fully automated, large-scale, spatially-aware multimodal dataset, constructed from raw video inputs without human intervention, using the proposed data curation pipeline. Holi-Spatial supports multi-level spatial supervision, ranging from geometrically accurate 3D Gaussian Splatting (3DGS) reconstructions with rendered depth maps to object-level and relational semantic annotations, together with corresponding spatial Question-Answer (QA) pairs. Following a principled and systematic pipeline, we further construct Holi-Spatial-4M, the first large-scale, high-quality 3D semantic dataset, containing 12K optimized 3DGS scenes, 1.3M 2D masks, 320K 3D bounding boxes, 320K instance captions, 1.2M 3D grounding instances, and 1.2M spatial QA pairs spanning diverse geometric, relational, and semantic reasoning tasks. Holi-Spatial demonstrates exceptional performance in data curation quality, significantly outperforming existing feed-forward and per-scene optimized methods on datasets such as ScanNet, ScanNet++, and DL3DV. Furthermore, fine-tuning Vision-Language Models (VLMs) on spatial reasoning tasks using this dataset has also led to substantial improvements in model performance. --- ### Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework Authors: Kaihua Tang, Jiaxin Qi, Jinli Ou, Yuhua Zheng, Jianqiang Huang Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07659v2 The emergence of Large Language Models (LLMs) has driven rapid progress in multi-modal learning, particularly in the development of Large Vision-Language Models (LVLMs). However, existing LVLM training paradigms place excessive reliance on the LLM component, giving rise to two critical robustness challenges: language bias and language sensitivity. To address both issues simultaneously, we propose a novel Self-Critical Inference (SCI) framework that extends Visual Contrastive Decoding by conducting multi-round counterfactual reasoning through both textual and visual perturbations. This process further introduces a new strategy for improving robustness by scaling the number of counterfactual rounds. Moreover, we also observe that failure cases of LVLMs differ significantly across models, indicating that fixed robustness benchmarks may not be able to capture the true reliability of LVLMs. To this end, we propose the Dynamic Robustness Benchmark (DRBench), a model-specific evaluation framework targeting both language bias and sensitivity issues. Extensive experiments show that SCI consistently outperforms baseline methods on DRBench, and that increasing the number of inference rounds further boosts robustness beyond existing single-step counterfactual reasoning methods. --- ### Partial Differential Equations in the Age of Machine Learning: A Critical Synthesis of Classical, Machine Learning, and Hybrid Methods Authors: Mohammad Nooraiepour, Jakub Wiktor Both, Teeratorn Kadeethum, Saeid Sadeghnejad Published: 2026-03-08 Categories: cs.LG, math.AP arXiv: https://arxiv.org/abs/2603.07655v1 Partial differential equations (PDEs) govern physical phenomena across the full range of scientific scales, yet their computational solution remains one of the defining challenges of modern science. This critical review examines two mature but epistemologically distinct paradigms for PDE solution, classical numerical methods and machine learning approaches, through a unified evaluative framework organized around six fundamental computational challenges. Classical methods are assessed for their structure-preserving properties, rigorous convergence theory, and scalable solver design; their persistent limitations in high-dimensional and geometrically complex settings are characterized precisely. Machine learning approaches are introduced under a taxonomy organized by the degree to which physical knowledge is incorporated and subjected to the same critical evaluation applied to classical methods. Classical methods are deductive -- errors are bounded by quantities derivable from PDE structure and discretization parameters -- while machine learning methods are inductive -- accuracy depends on statistical proximity to the training distribution. This epistemological distinction is the primary criterion governing responsible method selection. We identify three genuine complementarities between the paradigms and develop principles for hybrid design, including a framework for the structure inheritance problem that addresses when classical guarantees propagate through hybrid couplings, and an error budget decomposition that separates discretization, neural approximation, and coupling contributions. We further assess emerging frontiers, including foundation models, differentiable programming, quantum algorithms, and exascale co-design, evaluating each against the structural constraints that determine whether current barriers are fundamental or contingent on engineering progress. --- ### Compressed Proximal Federated Learning for Non-Convex Composite Optimization on Heterogeneous Data Authors: Pu Qiu, Chen Ouyang, Yongyang Xiong, Keyou You, Wanquan Liu, Yang Shi Published: 2026-03-08 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2603.07654v1 Federated Composite Optimization (FCO) has emerged as a promising framework for training models with structural constraints (e.g., sparsity) in distributed edge networks. However, simultaneously achieving communication efficiency and convergence robustness remains a significant challenge, particularly when dealing with non-smooth regularizers, statistical heterogeneity, and the restrictions of biased compression. To address these issues, we propose FedCEF (Federated Composite Error Feedback), a novel algorithm tailored for non-convex FCO. FedCEF introduces a decoupled proximal update scheme that separates the proximal operator from communication, enabling clients to handle non-smooth terms locally while transmitting compressed information. To mitigate the noise from aggressive quantization and the bias from non-IID data, FedCEF integrates a rigorous error feedback mechanism with control variates. Furthermore, we design a communication-efficient pre-proximal downlink strategy that allows clients to exactly reconstruct global control variables without explicit transmission. We theoretically establish that FedCEF achieves sublinear convergence to a bounded residual error under general non-convexity, which is controllable via the step size and batch size. Extensive experiments on real datasets validate FedCEF maintains competitive model accuracy even under extreme compression ratios (e.g., 1%), significantly reducing the total communication volume compared to uncompressed baselines. --- ### GLASS: Graph and Vision-Language Assisted Semantic Shape Correspondence Authors: Qinfeng Xiao, Guofeng Mei, Qilong Liu, Chenyuan Yi, Fabio Poiesi, Jian Zhang, Bo Yang, Yick Kit-lun Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07652v1 Establishing dense correspondence across 3D shapes is crucial for fundamental downstream tasks, including texture transfer, shape interpolation, and robotic manipulation. However, learning these mappings without manual supervision remains a formidable challenge, particularly under severe non-isometric deformations and in inter-class settings where geometric cues are ambiguous. Conventional functional map methods, while elegant, typically struggle in these regimes due to their reliance on isometry. To address this, we present GLASS, a framework that bridges the gap by integrating geometric spectral analysis with rich semantic priors from vision-language foundation models. GLASS introduces three key innovations: (i) a view-consistent strategy that enables robust multi-view visual feature extraction from powerful vision foundation models; (ii) the injection of language embeddings into vertex descriptors via zero-shot 3D segmentation, capturing high-level part semantics; and (iii) a graph-assisted contrastive loss that enforces structural consistency between regions (e.g., source's head'' $\leftrightarrow$ target's head'') by leveraging geodesic and topological relationships between regions. This design allows GLASS to learn globally coherent and semantically consistent maps without ground-truth supervision. Extensive experiments demonstrate that GLASS achieves state-of-the-art performance across all regimes, maintaining high accuracy on standard near-isometric tasks while significantly advancing performance in challenging settings. Specifically, it achieves average geodesic errors of 0.21, 4.5, and 5.6 on the inter-class benchmark SNIS and non-isometric benchmarks SMAL and TOPKIDS, reducing errors from URSSM baselines of 0.49, 6.0, and 8.9 by 57%, 25%, and 37%, respectively. --- ### AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots Authors: Likui Zhang, Tao Tang, Zhihao Zhan, Xiuwei Chen, Zisheng Chen, Jianhua Han, Jiangtong Zhu, Pei Xu, Hang Xu, Hefeng Wu, Liang Lin, Xiaodan Liang Published: 2026-03-08 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.07648v2 Recent advances in Visual-Language-Action (VLA) models have shown promising potential for robotic manipulation tasks. However, real-world robotic tasks often involve long-horizon, multi-step problem-solving and require generalization for continual skill acquisition, extending beyond single actions or skills. These challenges present significant barriers for existing VLA models, which use monolithic action decoders trained on aggregated data, resulting in poor scalability. To address these challenges, we propose AtomicVLA, a unified planning-and-execution framework that jointly generates task-level plans, atomic skill abstractions, and fine-grained actions. AtomicVLA constructs a scalable atomic skill library through a Skill-Guided Mixture-of-Experts (SG-MoE), where each expert specializes in mastering generic yet precise atomic skills. Furthermore, we introduce a flexible routing encoder that automatically assigns dedicated atomic experts to new skills, enabling continual learning. We validate our approach through extensive experiments. In simulation, AtomicVLA outperforms $π_{0}$ by 2.4\% on LIBERO, 10\% on LIBERO-LONG, and outperforms $π_{0}$ and $π_{0.5}$ by 0.22 and 0.25 in average task length on CALVIN. Additionally, our AtomicVLA consistently surpasses baselines by 18.3\% and 21\% in real-world long-horizon tasks and continual learning. These results highlight the effectiveness of atomic skill abstraction and dynamic expert composition for long-horizon and lifelong robotic tasks. The project page is \href{https://zhanglk9.github.io/atomicvla-web/}{here}. --- ### AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots Authors: Likui Zhang, Tao Tang, Zhihao Zhan, Xiuwei Chen, Zisheng Chen, Jianhua Han, Jiangtong Zhu, Pei Xu, Hang Xu, Hefeng Wu, Liang Lin, Xiaodan Liang Published: 2026-03-08 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.07648v1 Recent advances in Visual-Language-Action (VLA) models have shown promising potential for robotic manipulation tasks. However, real-world robotic tasks often involve long-horizon, multi-step problem-solving and require generalization for continual skill acquisition, extending beyond single actions or skills. These challenges present significant barriers for existing VLA models, which use monolithic action decoders trained on aggregated data, resulting in poor scalability. To address these challenges, we propose AtomicVLA, a unified planning-and-execution framework that jointly generates task-level plans, atomic skill abstractions, and fine-grained actions. AtomicVLA constructs a scalable atomic skill library through a Skill-Guided Mixture-of-Experts (SG-MoE), where each expert specializes in mastering generic yet precise atomic skills. Furthermore, we introduce a flexible routing encoder that automatically assigns dedicated atomic experts to new skills, enabling continual learning. We validate our approach through extensive experiments. In simulation, AtomicVLA outperforms $π_{0}$ by 2.4\% on LIBERO, 10\% on LIBERO-LONG, and outperforms $π_{0}$ and $π_{0.5}$ by 0.22 and 0.25 in average task length on CALVIN. Additionally, our AtomicVLA consistently surpasses baselines by 18.3\% and 21\% in real-world long-horizon tasks and continual learning. These results highlight the effectiveness of atomic skill abstraction and dynamic expert composition for long-horizon and lifelong robotic tasks. The project page is \href{https://zhanglk9.github.io/atomicvla-web/}{here}. --- ### Evaluating Synthetic Data for Baggage Trolley Detection in Airport Logistics Authors: Abdeldjalil Taibi, Mohmoud Badlis, Amina Bensalem, Belkacem Zouilekh, Mohammed Brahimi Published: 2026-03-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07645v1 Efficient luggage trolley management is critical for reducing congestion and ensuring asset availability in modern airports. Automated detection systems face two main challenges. First, strict security and privacy regulations limit large-scale data collection. Second, existing public datasets lack the diversity, scale, and annotation quality needed to handle dense, overlapping trolley arrangements typical of real-world operations. To address these limitations, we introduce a synthetic data generation pipeline based on a high-fidelity Digital Twin of Algiers International Airport using NVIDIA Omniverse. The pipeline produces richly annotated data with oriented bounding boxes, capturing complex trolley formations, including tightly nested chains. We evaluate YOLO-OBB using five training strategies: real-only, synthetic-only, linear probing, full fine-tuning, and mixed training. This allows us to assess how synthetic data can complement limited real-world annotations. Our results show that mixed training with synthetic data and only 40 percent of real annotations matches or exceeds the full real-data baseline, achieving 0.94 mAP@50 and 0.77 mAP@50-95, while reducing annotation effort by 25 to 35 percent. Multi-seed experiments confirm strong reproducibility with a standard deviation below 0.01 on mAP@50, demonstrating the practical effectiveness of synthetic data for automated trolley detection. --- ### Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving Authors: Chang Su, Zhongkai Hao, Zhizhou Zhang, Zeyu Xia, Youjia Wu, Hang Su, Jun Zhu Published: 2026-03-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07642v1 Large language models (LLMs) with reasoning abilities have demonstrated growing promise for tackling complex scientific problems. Yet such tasks are inherently domain-specific, unbounded and open-ended, demanding exploration across vast and flexible solution spaces. Existing approaches, whether purely learning-based or reliant on carefully designed workflows, often suffer from limited exploration efficiency and poor generalization. To overcome these challenges, we present HELIX -- a Hierarchical Evolutionary reinforcement Learning framework with In-context eXperiences. HELIX introduces two key novelties: (i) a diverse yet high-quality pool of candidate solutions that broadens exploration through in-context learning, and (ii) reinforcement learning for iterative policy refinement that progressively elevates solution quality. This synergy enables the discovery of more advanced solutions. On the circle packing task, HELIX achieves state-of-the-art result with a sum of radii of 2.63598308 using only a 14B model. Across standard machine learning benchmarks, HELIX further surpasses GPT-4o with a carefully engineered pipeline, delivering an average F1 improvement of 5.95 points on the Adult and Bank Marketing datasets. --- ### Real-Time Glottis Detection Framework via Spatial-decoupled Feature Learning for Nasal Transnasal Intubation Authors: Jinyu Liu, Gaoyang Zhang, Yang Zhou, Ruoyi Hao, Yang Zhang, Hongliang Ren Published: 2026-03-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07630v1 Nasotracheal intubation (NTI) is a vital procedure in emergency airway management, where rapid and accurate glottis detection is essential to ensure patient safety. However, existing machine assisted visual detection systems often rely on high performance computational resources and suffer from significant inference delays, which limits their applicability in time critical and resource constrained scenarios. To overcome these limitations, we propose Mobile GlottisNet, a lightweight and efficient glottis detection framework designed for real time inference on embedded and edge devices. The model incorporates structural awareness and spatial alignment mechanisms, enabling robust glottis localization under complex anatomical and visual conditions. We implement a hierarchical dynamic thresholding strategy to enhance sample assignment, and introduce an adaptive feature decoupling module based on deformable convolution to support dynamic spatial reconstruction. A cross layer dynamic weighting scheme further facilitates the fusion of semantic and detail features across multiple scales. Experimental results demonstrate that the model, with a size of only 5MB on both our PID dataset and Clinical datasets, achieves inference speeds of over 62 FPS on devices and 33 FPS on edge platforms, showing great potential in the application of emergency NTI. ---