# Research Papers — 2026-03 · bundle page 196 of 243 > Full-text markdown of papers #9751–9800 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/196 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/195.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/197.md) ### ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins Authors: Yichen Zhou, Jonathan Golob, Amir Karimi, Stefan Bauer, Patrick Schwab Published: 2026-03-06 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2603.06740v2 Protein language models (pLMs) have shown strong potential for zero-shot prediction of missense variant effects, yet systematic benchmarking on viral proteins remains limited, a critical gap given the need for proactive tools that can anticipate emerging mutations ahead of experimental validation. Here we introduce ViroGym, a comprehensive benchmark evaluating pLMs across three tasks: 79 deep mutational scanning (DMS) assays covering eukaryotic viruses with 552,065 mutated sequences across 7 phenotypic readouts, 21 influenza neutralisation tasks, and a real-world pandemic prediction task for SARS-CoV-2. We benchmark well-established pLMs on fitness landscapes, antigenic diversity, and pandemic forecasting, and find that the ProGen2 family consistently achieves the strongest performance across all three tasks. Crucially, DMS and neutralisation performance reliably identifies models that generalise to real-world emergence, even though the mutation sets they surface barely overlap, revealing that complementary in vitro benchmarks capture the evolutionary constraints needed for real-world mutation forecasting. --- ### ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution Authors: Yubang Wang, Chenxi Zhang, Bowen Chen, Zezheng Huai, Zihao Dai, Xinchi Chen, Yuxin Wang, Yining Zheng, Jingjing Gong, Xipeng Qiu Published: 2026-03-06 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.06739v2 Autonomous agents are increasingly expected to support scientific research, and recent benchmarks report progress in code repair and autonomous experimentation. However, these evaluations typically assume a pre-configured execution environment, which requires resolving complex software dependencies, aligning hardware and framework versions, and configuring distributed execution, yet this capability remains largely unbenchmarked. We introduce ResearchEnvBench, a benchmark for environment synthesis in research code execution. Given a research repository, documentation, and a target execution setting, agents must construct an environment that successfully executes at runtime. Evaluations on diverse research repositories reveal a substantial gap in current SOTA agents, with failures dominated by incomplete dependency resolution and brittle version coupling. ResearchEnvBench provides a realistic testbed for advancing autonomous agents toward reproducible scientific research. --- ### Rank-Factorized Implicit Neural Bias: Scaling Super-Resolution Transformer with FlashAttention Authors: Dongheon Lee, Seokju Yun, Jaegyun Im, Youngmin Ro Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06738v2 Recent Super-Resolution~(SR) methods mainly adopt Transformers for their strong long-range modeling capability and exceptional representational capacity. However, most SR Transformers rely heavily on relative positional bias~(RPB), which prevents them from leveraging hardware-efficient attention kernels such as FlashAttention. This limitation imposes a prohibitive computational burden during both training and inference, severely restricting attempts to scale SR Transformers by enlarging the training patch size or the self-attention window. Consequently, unlike other domains that actively exploit the inherent scalability of Transformers, SR Transformers remain heavily focused on effectively utilizing limited receptive fields. In this paper, we propose Rank-factorized Implicit Neural Bias~(RIB), an alternative to RPB that enables FlashAttention in SR Transformers. Specifically, RIB approximates positional bias using low-rank implicit neural representations and concatenates them with pixel content tokens in a channel-wise manner, turning the element-wise bias addition in attention score computation into a dot-product operation. Further, we introduce a convolutional local attention and a cyclic window strategy to fully leverage the advantages of long-range interactions enabled by RIB and FlashAttention. We enlarge the window size up to \textbf{96$\times$96} while jointly scaling the training patch size and the dataset size, maximizing the benefits of Transformers in the SR task. As a result, our network achieves \textbf{35.63\,dB PSNR} on Urban100$\times$2, while reducing training and inference time by \textbf{2.1$\times$} and \textbf{2.9$\times$}, respectively, compared to the RPB-based SR Transformer~(PFT). --- ### Agent Hunt: Bounty Based Collaborative Autoformalization With LLM Agents Authors: Chad E. Brown, Cezary Kaliszyk, Josef Urban Published: 2026-03-06 Categories: cs.LO, cs.AI, cs.SC arXiv: https://arxiv.org/abs/2603.06737v1 We describe an experiment in large-scale autoformalization of algebraic topology in an Interactive Theorem Proving (ITP) environment, where the workload is distributed among multiple LLM-based coding agents. Rather than relying on static central planning, we implement a simulated bounty-based marketplace in which agents dynamically propose new lemmas (formal statements), attach bounties to them, and compete to discharge these proof obligations and claim the bounties. The agents interact directly with the interactive proof system: they can invoke tactics, inspect proof states and goals, analyze tactic successes and failures, and iteratively refine their proof scripts. In addition to constructing proofs, agents may introduce new formal definitions and intermediate lemmas to structure the development. All accepted proofs are ultimately checked and verified by the underlying proof assistant. This setting explores collaborative, decentralized proof search and theory building, and the use of market-inspired mechanisms to scale autoformalization in ITP. --- ### Vessel-Aware Deep Learning for OCTA-Based Detection of AMD Authors: Margalit G. Mitzner, Moinak Bhattacharya, Zhilin Zou, Chao Chen, Prateek Prasanna Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06735v1 Age-related macular degeneration (AMD) is characterized by early micro-vascular alterations that can be captured non-invasively using optical coherence tomography angiography (OCTA), yet most deep learning (DL) models rely on global features and fail to exploit clinically meaningful vascular biomarkers. We introduce an external multiplicative attention framework that incorporates vessel-specific tortuosity maps and vasculature dropout maps derived from arteries, veins, and capillaries. These biomarker maps are generated from vessel segmentations and smoothed across multiple spatial scales to highlight coherent patterns of vascular remodeling and capillary rarefaction. Tortuosity reflects abnormalities in vessel geometry linked to impaired auto-regulation, while dropout maps capture localized perfusion deficits that precede structural retinal damage. The maps are fused with the OCTA projection to guide a deep classifier toward physiologically relevant regions. Arterial tortuosity provided the most consistent discriminative value, while capillary dropout maps performed best among density-based variants, especially at larger smoothing scales. Our proposed method offers interpretable insights aligned with known AMD pathophysiology. --- ### Calibrated Credit Intelligence: Shift-Robust and Fair Risk Scoring with Bayesian Uncertainty and Gradient Boosting Authors: Srikumar Nayak Published: 2026-03-06 Categories: q-fin.RM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.06733v1 Credit risk scoring must support high-stakes lending decisions where data distributions change over time, probability estimates must be reliable, and group-level fairness is required. While modern machine learning models improve default prediction accuracy, they often produce poorly calibrated scores under distribution shift and may create unfair outcomes when trained without explicit constraints. This paper proposes Calibrated Credit Intelligence (CCI), a deployment-oriented framework that combines (i) a Bayesian neural risk scorer to capture epistemic uncertainty and reduce overconfident errors, (ii) a fairnessconstrained gradient boosting model to control group disparities while preserving strong tabular performance, and (iii) a shiftaware fusion strategy followed by post-hoc probability calibration to stabilize decision thresholds in later time periods. We evaluate CCI on the Home Credit Credit Risk Model Stability benchmark using a time-consistent split to reflect real-world drift. Compared with strong baselines (LightGBM, XGBoost, CatBoost, TabNet, and a standalone Bayesian neural model), CCI achieves the best overall trade-off between discrimination, calibration, stability, and fairness. In particular, CCI reaches an AUC-ROC of 0.912 and an AUC-PR of 0.438, improves operational performance with Recall@1%FPR = 0.509, and reduces calibration error (Brier score 0.087, ECE 0.015). Under temporal shift, CCI shows a smaller AUC-PR drop from early to late periods (0.017), and it lowers group disparities (demographic parity gap 0.046, equal opportunity gap 0.037) compared to unconstrained boosting. These results indicate that CCI produces risk scores that are accurate, reliable, and more equitable under realistic deployment conditions. --- ### HERO: Hierarchical Embedding-Refinement for Open-Vocabulary Temporal Sentence Grounding in Videos Authors: Tingting Han, Xinsong Tao, Yufei Yin, Min Tan, Sicheng Zhao, Zhou Yu Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06732v1 Temporal Sentence Grounding in Videos (TSGV) aims to temporally localize segments of a video that correspond to a given natural language query. Despite recent progress, most existing TSGV approaches operate under closed-vocabulary settings, limiting their ability to generalize to real-world queries involving novel or diverse linguistic expressions. To bridge this critical gap, we introduce the Open-Vocabulary TSGV (OV-TSGV) task and construct the first dedicated benchmarks--Charades-OV and ActivityNet-OV--that simulate realistic vocabulary shifts and paraphrastic variations. These benchmarks facilitate systematic evaluation of model generalization beyond seen training concepts. To tackle OV-TSGV, we propose HERO(Hierarchical Embedding-Refinement for Open-Vocabulary grounding), a unified framework that leverages hierarchical linguistic embeddings and performs parallel cross-modal refinement. HERO jointly models multi-level semantics and enhances video-language alignment via semantic-guided visual filtering and contrastive masked text refinement. Extensive experiments on both standard and open vocabulary benchmarks demonstrate that HERO consistently surpasses state-of-the-art methods, particularly under open-vocabulary scenarios, validating its strong generalization capability and underscoring the significance of OV-TSGV as a new research direction. --- ### PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks Authors: Uday Bondhugula, Akshay Baviskar, Navdeep Katel, Vimal Patel, Anoop JS, Arnab Dutta Published: 2026-03-06 Categories: cs.PL, cs.LG arXiv: https://arxiv.org/abs/2603.06731v2 We present the design and implementation of PolyBlocks, a modular and reusable MLIR-based compiler infrastructure for AI programming frameworks and AI chips. PolyBlocks is based on pass pipelines that compose transformations on loop nests and SSA, primarily relying on lightweight affine access analysis; the transformations are stitched together in specialized ways to realize high-performance code automatically by the use of analytical cost models and heuristics. The optimizations in these passes include multi-level tiling, fusion, on-chip scratchpad usage, mapping matmuls and convolutions to matrix units, fusing the attention layer, and several other transformations for parallelism and locality. They have been developed in a way that makes it easy to build PolyBlocks-based compilers to target new chips, reusing much of the infrastructure. PolyBlocks' design and architecture enable fully automatic code generation from high-level frameworks to low-level target-specific intrinsics. Experimental results from evaluating PolyBlocks-powered just-in-time compilation for PyTorch and JAX targeting NVIDIA GPUs show that it is able to match or outperform Torch Inductor and XLA in several cases, although the latter rely on a combination of vendor libraries and code generation. For individual operators like matmuls and convolutions, PolyBlocks-generated code is competitive with the best vendor-tuned libraries or hand-written kernels. --- ### Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds Authors: Jiefu Zhang, Yang Xu, Vaneet Aggarwal Published: 2026-03-06 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2603.06729v1 Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical solvers often remain safe but freeze in tight interactions. We propose a reinforcement learning approach for dense, variable-density navigation that attains zero-shot density generalization using a density-invariant observation encoding with density-randomized training and physics-informed proxemic reward shaping with density-adaptive scaling. The encoding represents the distance-sorted $K$ nearest pedestrians plus bounded crowd summaries, keeping input statistics stable as crowd size grows. Trained with $N\!\in\!(11,16)$ pedestrians in a $3\mathrm{m}\times3\mathrm{m}$ arena and evaluated up to $N\!=\!21$ pedestrians ($1.3\times$ denser), our policy reaches the goal in $>99\%$ of episodes and achieves $86\%$ collision-free success in random crowds, with markedly less freezing than analytical methods and a $>\!60$-point collision-free margin over learning-based benchmark methods. Codes are available at \href{https://github.com/jznmsl/PSS-Social}{https://github.com/jznmsl/PSS-Social}. --- ### Orion: Characterizing and Programming Apple's Neural Engine for LLM Training and Inference Authors: Ramchand Kumaresan Published: 2026-03-06 Categories: cs.LG, cs.AR, cs.CL arXiv: https://arxiv.org/abs/2603.06728v1 Over two billion Apple devices ship with a Neural Processing Unit (NPU) - the Apple Neural Engine (ANE) - yet this accelerator remains largely unused for large language model workloads. CoreML, Apple's public ML framework, imposes opaque abstractions that prevent direct ANE programming and do not support on-device training. We present Orion, to our knowledge the first open end-to-end system that combines direct ANE execution, a compiler pipeline, and stable multi-step training with checkpoint resume in a single native runtime, bypassing CoreML entirely via Apple's private _ANEClient and _ANECompiler APIs. Building on prior characterization work by maderix, we extend public knowledge of ANE constraints to a catalog of 20 restrictions on MIL IR programs, memory layout, compilation limits, and numerical behavior, including 14 previously undocumented constraints discovered during Orion development. Orion includes a compiler that lowers a graph IR through five optimization passes to ANE-native MIL and a runtime that manages IOSurface-backed zero-copy tensor I/O, program caching, and delta compilation for weight updates. Because the ANE bakes weights at compile time, naive training normally requires full recompilation per step (~4.2 s). We show that compiled programs can instead be updated by unloading, patching weight files, and reloading, bypassing ANECCompile() and reducing recompilation from 4,200 ms to 494 ms per step (8.5x), yielding a 3.8x training speedup. On an M4 Max, Orion achieves 170+ tokens/s for GPT-2 124M inference and demonstrates stable training of a 110M-parameter transformer on TinyStories for 1,000 steps in 22 minutes with zero NaN occurrences. We also present LoRA adapter-as-input, enabling hot-swap of adapters via IOSurface inputs without recompilation. --- ### Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment Authors: Jingyuan Feng, Andrew Gambardella, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06727v1 Current safety alignment methods encode safe behavior implicitly within model parameters, creating a fundamental opacity: we cannot easily inspect why a model refuses a request, nor intervene when its safety judgments fail. We propose Safe Transformer, a modular approach that augments pre-trained language models by inserting a discrete information bottleneck containing an explicit safety bit between transformer layers. The safety bit serves as both an interpretable signal of the model's safety classification and a controllable switch: through contrastive training, the model learns disentangled representations where the safety bit governs the behavioral mode - producing helpful responses when $s=1$ and refusals when $s=0$ - while additional unsupervised bits $u$ encode semantic content for generation. Additional unsupervised bits in the information bottleneck allow semantic information to flow through, preserving the model's generation capabilities. This design achieves both interpretability (the safety decision is directly readable) and controllability (the safety bit can be manually overridden), requiring only lightweight fine-tuning without pre-training from scratch. In red-team benchmarks, Safe Transformer achieves near-zero Attack Success Rate, substantially outperforming base models and safety fine-tuning baselines. --- ### Regression Models Meet Foundation Models: A Hybrid-AI Approach to Practical Electricity Price Forecasting Authors: Yunzhong Qiu, Binzhu Li, Hao Wei, Shenglin Weng, Chen Wang, Zhongyi Pei, Mingsheng Long, Jianmin Wang Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06726v1 Electricity market prices exhibit extreme volatility, nonlinearity, and non-stationarity, making accurate forecasting a significant challenge. While cutting-edge time series foundation models (TSFMs) effectively capture temporal dependencies, they typically underutilize cross-variate correlations and non-periodic patterns that are essential for price forecasting. Conversely, regression models excel at capturing feature interactions but are limited to future-available inputs, ignoring crucial historical drivers that are unavailable at forecast time. To bridge this gap, we propose FutureBoosting, a novel paradigm that enhances regression-based forecasts by integrating forecasted features generated from a frozen TSFM. This approach leverages the TSFM's ability to model historical patterns and injects these insights as enriched inputs into a downstream regression model. We instantiate this paradigm into a lightweight, plug-and-play framework for electricity price forecasting. Extensive evaluations on real-world electricity market data demonstrate that our framework consistently outperforms state-of-the-art TSFMs and regression baselines, achieving reductions in Mean Absolute Error (MAE) of more than 30% at most. Through ablation studies and explainable AI (XAI) techniques, we validate the contribution of forecasted features and elucidate the model's decision-making process. FutureBoosting establishes a robust, interpretable, and effective solution for practical market participation, offering a general framework for enhancing regression models with temporal context. --- ### Bi Directional Feedback Fusion for Activity Aware Forecasting of Indoor CO2 and PM2.5 Authors: Harshala Gammulle, Lidia Morawska, Sridha Sridharan, Clinton Fookes Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06724v1 Indoor air quality (IAQ) forecasting plays a critical role in safeguarding occupant health, ensuring thermal comfort, and supporting intelligent building control. However, predicting future concentrations of key pollutants such as carbon dioxide (CO2) and fine particulate matter (PM2.5) remains challenging due to the complex interplay between environmental factors and highly dynamic occupant behaviours. Traditional data driven models primarily rely on historical sensor trajectories and often fail to anticipate behaviour induced emission spikes or rapid concentration shifts. To address these limitations, we present a dual stream bi directional feedback fusion framework that jointly models indoor environmental evolution and action derived embeddings representing human activities. The proposed architecture integrates a context aware modulation mechanism that adaptively scales and shifts each stream based on a shared, evolving fusion state, enabling the model to selectively emphasise behavioural cues or long term environmental trends. Furthermore, we introduce dual timescale temporal modules that independently capture gradual CO2 accumulation patterns and short term PM2.5 fluctuations. A composite loss function combining weighted mean squared error, spike aware penalties, and uncertainty regularisation facilitates robust learning under volatile indoor conditions. Extensive validation on real-world IAQ datasets demonstrates that our approach significantly outperforms state of the art forecasting baselines while providing interpretable uncertainty estimates essential for practical deployment in smart buildings and health-aware monitoring systems. --- ### AWPD: Frequency Shield Network for Agnostic Watermark Presence Detection Authors: Xiang Ao, Yilin Du, Zidan Wang, Mengru Chen, Siyang Lu Published: 2026-03-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06723v3 Invisible watermarks, as an essential technology for image copyright protection, have been widely deployed with the rapid development of social media and AIGC. However, existing invisible watermark detection heavily relies on prior knowledge of specific algorithms, leading to limited detection capabilities for ``unknown watermarks'' in open environments. To this end, we propose a novel task named Agnostic Watermark Presence Detection (AWPD), which aims to identify whether an image carries a copyright mark without requiring decoding information. We construct the UniFreq-100K dataset, comprising large-scale samples across various invisible watermark embedding algorithms. Furthermore, we propose the Frequency Shield Network (FSNet). This model deploys an Adaptive Spectral Perception Module (ASPM) in the shallow layers, utilizing learnable frequency gating to dynamically amplify high-frequency watermark signals while suppressing low-frequency semantics. In the deep layers, the network introduces Dynamic Multi-Spectral Attention (DMSA) combined with tri-stream extremum pooling to deeply mine watermark energy anomalies, forcing the model to precisely focus on sensitive frequency bands. Extensive experiments demonstrate that FSNet exhibits superior zero-shot detection capabilities on the AWPD task, outperforming existing baseline models. Code and datasets will be released upon acceptance. --- ### ProtAlign: Contrastive learning paradigm for Sequence and structure alignment Authors: Aditya Ranganath, Hasin Us Sami, Kowshik Thopalli, Bhavya Kailkhura, Wesam Sakla Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06722v1 Protein language models often take into consideration the alignment between a protein sequence and its textual description. However, they do not take structural information into consideration. Traditional methods treat sequence and structure separately, limiting the ability to exploit the alignment between the structure and protein sequence embeddings. In this paper, we introduce a sequence structure contrastive alignment framework, which learns a shared embedding space where proteins are represented consistently across modalities. By training on large-scale pairs of sequences and experimentally resolved or predicted structures, the model maximizes agreement between matched sequence structure pairs while pushing apart unrelated pairs. This alignment enables cross-modal retrieval (e.g., finding structural neighbors given a sequence), improves downstream prediction tasks such as function annotation and stability estimation, and provides interpretable links between sequence variation and structural organization. Our results demonstrate that contrastive learning can serve as a powerful bridge between protein sequences and structures, offering a unified representation for understanding and engineering proteins. --- ### From Statistical Fidelity to Clinical Consistency: Scalable Generation and Auditing of Synthetic Patient Trajectories Authors: Guanglin Zhou, Armin Catic, Motahare Shabestari, Matthew Young, Chaiquan Li, Katrina Poppe, Sebastiano Barbieri Published: 2026-03-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06720v1 Access to electronic health records (EHRs) for digital health research is often limited by privacy regulations and institutional barriers. Synthetic EHRs have been proposed as a way to enable safe and sovereign data sharing; however, existing methods may produce records that capture overall statistical properties of real data but present inconsistencies across clinical processes and observations. We developed an integrated pipeline to make synthetic patient trajectories clinically consistent through two synergistic steps: high-fidelity generation and scalable auditing. Using the MIMIC-IV database, we trained a knowledge-grounded generative model that represents nearly 32,000 distinct clinical events, including demographics, laboratory measurements, medications, procedures, and diagnoses, while enforcing structural integrity. To support clinical consistency at scale, we incorporated an automated auditing module leveraging large language models to filter out clinical inconsistencies (e.g., contraindicated medications) that escape probabilistic generation. We generated 18,071 synthetic patient records derived from a source cohort of 180,712 real patients. While synthetic clinical event probabilities demonstrated robust agreement (mean bias effectively 0.00) and high correlation (R2=0.99) with the real counterparts, review of a random sample of synthetic records (N=20) by three clinicians identified inconsistencies in 45-60% of them. Automated auditing reduced the difference between real and synthetic data (Cohen's effect size d between 0.59 and 1.60 before auditing, and between 0.18 and 0.67 after auditing). Downstream models trained on audited data matched or even exceeded real-data performance. We found no evidence of privacy risks, with membership inference performance indistinguishable from random guessing (F1-score=0.51). --- ### Multimodal Large Language Models as Image Classifiers Authors: Nikita Kisel, Illia Volkov, Klara Janouskova, Jiri Matas Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06578v2 Multimodal Large Language Models (MLLM) classification performance depends critically on evaluation protocol and ground truth quality. Studies comparing MLLMs with supervised and vision-language models report conflicting conclusions, and we show these conflicts stem from protocols that either inflate or underestimate performance. Across the most common evaluation protocols, we identify and fix key issues: model outputs that fall outside the provided class list and are discarded, inflated results from weak multiple-choice distractors, and an open-world setting that underperforms only due to poor output mapping. We additionally quantify the impact of commonly overlooked design choices - batch size, image ordering, and text encoder selection - showing they substantially affect accuracy. Evaluating on ReGT, our multilabel reannotation of 625 ImageNet-1k classes, reveals that MLLMs benefit most from corrected labels (up to +10.8%), substantially narrowing the perceived gap with supervised models. Much of the reported MLLMs underperformance on classification is thus an artifact of noisy ground truth and flawed evaluation protocol rather than genuine model deficiency. Models less reliant on supervised training signals prove most sensitive to annotation quality. Finally, we show that MLLMs can assist human annotators: in a controlled case study, annotators confirmed or integrated MLLMs predictions in approximately 50% of difficult cases, demonstrating their potential for large-scale dataset curation. This work is part of the Aiming for Perfect ImageNet-1k project, see https://klarajanouskova.github.io/ImageNet/. --- ### Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion Authors: Lijiang Li, Zuwei Long, Yunhang Shen, Heting Gao, Haoyu Cao, Xing Sun, Caifeng Shan, Ran He, Chaoyou Fu Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06577v2 While recent multimodal large language models (MLLMs) have made impressive strides, they predominantly employ a conventional autoregressive architecture as their backbone, leaving significant room to explore effective and efficient alternatives in architectural design. Concurrently, recent studies have successfully applied discrete diffusion models to various domains, such as visual understanding and image generation, revealing their considerable potential as a promising backbone for multimodal systems. Drawing inspiration from these pioneering studies, we introduce Omni-Diffusion, the first any-to-any multimodal language model built entirely on mask-based discrete diffusion models, which unifies understanding and generation across text, speech, and images. Omni-Diffusion employs a unified mask-based discrete diffusion model to directly capture the joint distribution over discrete multimodal tokens. This approach supports not only bimodal tasks but also more complex scenarios involving multiple modalities. On a diverse set of benchmarks, our method outperforms or performs on par with existing multimodal systems that process two or more modalities, highlighting the significant promise of diffusion models in powering the next generation of multimodal foundation models. Project webpage: https://omni-diffusion.github.io. --- ### BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations Authors: Thomas Monninger, Shaoyuan Xie, Qi Alfred Chen, Sihao Ding Published: 2026-03-06 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.06576v2 The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic understanding abilities, which are essential for handling complex decision-making and long-tail scenarios. However, existing methods typically feed LLMs with tokens from multi-view and multi-frame images independently, leading to redundant computation and limited spatial consistency. This separation in visual processing hinders accurate 3D spatial reasoning and fails to maintain geometric coherence across views. On the other hand, Bird's-Eye View (BEV) representations learned from geometrically annotated tasks (e.g., object detection) provide spatial structure but lack the semantic richness of foundation vision encoders. To bridge this gap, we propose BEVLM, a framework that connects a spatially consistent and semantically distilled BEV representation with LLMs. Through extensive experiments, we show that BEVLM enables LLMs to reason more effectively in cross-view driving scenes, improving accuracy by 46.0%, by leveraging BEV features as unified inputs. Furthermore, by distilling semantic knowledge from LLMs into BEV representations, BEVLM significantly improves closed-loop end-to-end driving performance in safety-critical scenarios across UniAD and VAD, with gains of up to 28.2%. --- ### Fly360: Omnidirectional Obstacle Avoidance within Drone View Authors: Xiangkai Zhang, Dizhe Zhang, WenZhuo Cao, Zhaoliang Wan, Yingjie Niu, Lu Qi, Xu Yang, Zhiyong Liu Published: 2026-03-06 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.06573v1 Obstacle avoidance in unmanned aerial vehicles (UAVs), as a fundamental capability, has gained increasing attention with the growing focus on spatial intelligence. However, current obstacle-avoidance methods mainly depend on limited field-of-view sensors and are ill-suited for UAV scenarios which require full-spatial awareness when the movement direction differs from the UAV's heading. This limitation motivates us to explore omnidirectional obstacle avoidance for panoramic drones with full-view perception. We first study an under explored problem setting in which a UAV must generate collision-free motion in environments with obstacles from arbitrary directions, and then construct a benchmark that consists of three representative flight tasks. Based on such settings, we propose Fly360, a two-stage perception-decision pipeline with a fixed random-yaw training strategy. At the perception stage, panoramic RGB observations are input and converted into depth maps as a robust intermediate representation. For the policy network, it is lightweight and used to output body-frame velocity commands from depth inputs. Extensive simulation and real-world experiments demonstrate that Fly360 achieves stable omnidirectional obstacle avoidance and outperforms forward-view baselines across all tasks. Our model is available at https://zxkai.github.io/fly360/ --- ### SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation Authors: Vishal Thengane, Zhaochong An, Tianjin Huang, Son Lam Phung, Abdesselam Bouzerdoum, Lu Yin, Na Zhao, Xiatian Zhu Published: 2026-03-06 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.06572v2 Incremental Few-Shot (IFS) segmentation aims to learn new categories over time from only a few annotations. Although widely studied in 2D, it remains underexplored for 3D point clouds. Existing methods suffer from catastrophic forgetting or fail to learn discriminative prototypes under sparse supervision, and often overlook a key cue: novel categories frequently appear as unlabelled background in base-training scenes. We introduce SCOPE (Scene-COntextualised Prototype Enrichment), a plug-and-play background-guided prototype enrichment framework that integrates with any prototype-based 3D segmentation method. After base training, a class-agnostic segmentation model extracts high-confidence pseudo-instances from background regions to build a prototype pool. When novel classes arrive with few labelled samples, relevant background prototypes are retrieved and fused with few-shot prototypes to form enriched representations without retraining the backbone or adding parameters. Experiments on ScanNet and S3DIS show that SCOPE achieves SOTA performance, improving novel-class IoU by up to 6.98% and 3.61%, and mean IoU by 2.25% and 1.70%, respectively, while maintaining low forgetting. Code is available https://github.com/Surrey-UP-Lab/SCOPE. --- ### SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning Authors: Alejandra Perez, Anita Rau, Lee White, Busisiwe Mlambo, Chinedu Nwoye, Muhammad Abdullah Jamal, Omid Mohareri Published: 2026-03-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06570v1 Surgeons don't just see -- they interpret. When an expert observes a surgical scene, they understand not only what instrument is being used, but why it was chosen, what risk it poses, and what comes next. Current surgical AI cannot answer such questions, largely because training data that explicitly encodes surgical reasoning is immensely difficult to annotate at scale. Yet surgical video lectures already contain exactly this -- explanations of intent, rationale, and anticipation, narrated by experts for the purpose of teaching. Though inherently noisy and unstructured, these narrations encode the reasoning that surgical AI currently lacks. We introduce SUREON, a large-scale video QA dataset that systematically harvests this training signal from surgical academic videos. SUREON defines 12 question categories covering safety assessment, decision rationale, and forecasting, and uses a multi-agent pipeline to extract and structure supervision at scale. Across 134.7K clips and 170 procedure types, SUREON yields 206.8k QA pairs and an expert-validated benchmark of 354 examples. To evaluate the extent to which this supervision translates to surgical reasoning ability, we introduce two models: SureonVLM, a vision-language model adapted through supervised fine-tuning, and SureonVLM-R1, a reasoning model trained with Group Relative Policy Optimization. Both models can answer complex questions about surgery and substantially outperform larger general-domain models, exceeding 84% accuracy on the SUREON benchmark while outperforming general-domain models on standard surgical perception tasks. Qualitative analysis of SureonVLM-R1 reveals explicit reasoning behavior, such as inferring operative intent from visual context. --- ### Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders Authors: Boqiang Zhang, Lei Ke, Ruihan Yang, Qi Gao, Tianyuan Qu, Rossell Chen, Dong Yu, Leoweiliang Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06569v2 Vision Language Model (VLM) development has largely relied on scaling model size, which hinders deployment on compute-constrained mobile and edge devices such as smartphones and robots. In this work, we explore the performance limits of compact (e.g., 2B and 8B) VLMs. We challenge the prevailing practice that state-of-the-art VLMs must rely on vision encoders initialized via massive contrastive pretraining (e.g., CLIP/SigLIP). We identify an objective mismatch: contrastive learning, optimized for discrimination, enforces coarse and category-level invariances that suppress fine-grained visual cues needed for dense captioning and complex VLM reasoning. To address this issue, we present Penguin-VL, whose vision encoder is initialized from a text-only LLM. Our experiments reveal that Penguin-Encoder serves as a superior alternative to traditional contrastive pretraining, unlocking a higher degree of visual fidelity and data efficiency for multimodal understanding. Across various image and video benchmarks, Penguin-VL achieves performance comparable to leading VLMs (e.g., Qwen3-VL) in mathematical reasoning and surpasses them in tasks such as document understanding, visual knowledge, and multi-perspective video understanding. Notably, these gains are achieved with a lightweight architecture, demonstrating that improved visual representation rather than model scaling is the primary driver of performance. Our ablations show that Penguin-Encoder consistently outperforms contrastive-pretrained encoders, preserving fine-grained spatial and temporal cues that are critical for dense perception and complex reasoning. This makes it a strong drop-in alternative for compute-efficient VLMs and enables high performance in resource-constrained settings. Code: https://github.com/tencent-ailab/Penguin-VL --- ### A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attention Authors: Eric Qu, Brandon M. Wood, Aditi S. Krishnapriyan, Zachary W. Ulissi Published: 2026-03-06 Categories: cs.LG, cond-mat.mtrl-sci, cs.CE, physics.chem-ph, q-bio.QM arXiv: https://arxiv.org/abs/2603.06567v1 Machine-learning interatomic potentials (MLIPs) have advanced rapidly, with many top models relying on strong physics-based inductive biases. However, as models scale to larger systems like biomolecules and electrolytes, they struggle to accurately capture long-range (LR) interactions, leading current approaches to rely on explicit physics-based terms or components. In this work, we propose AllScAIP, a straightforward, attention-based, and energy-conserving MLIP model that scales to O(100 million) training samples. It addresses the long-range challenge using an all-to-all node attention component that is data-driven. Extensive ablations reveal that in low-data/small-model regimes, inductive biases improve sample efficiency. However, as data and model size scale, these benefits diminish or even reverse, while all-to-all attention remains critical for capturing LR interactions. Our model achieves state-of-the-art energy/force accuracy on molecular systems, as well as a number of physics-based evaluations (OMol25), while being competitive on materials (OMat24) and catalysts (OC20). Furthermore, it enables stable, long-timescale MD simulations that accurately recover experimental observables, including density and heat of vaporization predictions. --- ### Boosting deep Reinforcement Learning using pretraining with Logical Options Authors: Zihan Ye, Phil Chau, Raban Emunds, Jannis Blüml, Cedric Derstroff, Quentin Delfosse, Oleg Arenz, Kristian Kersting Published: 2026-03-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.06565v1 Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encoding sparse objectives along with aligned plans. However, purely symbolic architectures are complex to scale and difficult to apply to continuous settings. Hence, we propose a hybrid approach, inspired by humans' ability to acquire new skills. We use a two-stage framework that injects symbolic structure into neural-based reinforcement learning agents without sacrificing the expressivity of deep policies. Our method, called Hybrid Hierarchical RL (H^2RL), introduces a logical option-based pretraining strategy to steer the learning policy away from short-term reward loops and toward goal-directed behavior while allowing the final policy to be refined via standard environment interaction. Empirically, we show that this approach consistently improves long-horizon decision-making and yields agents that outperform strong neural, symbolic, and neuro-symbolic baselines. --- ### EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinking Authors: Fangrui Zhu, Yunfeng Xi, Jianmo Ni, Mu Cai, Boqing Gong, Long Zhao, Chen Qu, Ian Miao, Yi Li, Cheng Zhong, Huaizu Jiang, Shwetak Patel Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06561v2 Egocentric video understanding is inherently complex due to the dynamic 4D nature of the environment, where camera motion and object displacements necessitate a continuous re-evaluation of spatial relations. In this work, we target a suite of under-explored egocentric 4D reasoning tasks, including fixture interaction counting, viewpoint-relative fixture location, object movement itinerary tracking, and stationary object localization, that require fundamentally different cognitive operations: spatial anchoring, temporal tracking, and duration reasoning. We observe that these structural differences make task-agnostic approaches insufficient: generic Chain-of-Thought methods lack task-appropriate reasoning primitives, and uniform reinforcement learning actively destabilizes performance on spatial tasks. To address this, we propose EgoReasoner, a two-stage framework that aligns both the reasoning scaffold and the reward signal to each task's cognitive structure. In the first stage, Task-Adaptive Thinking Templates guide the synthesis of structured CoT traces that teach the model to reason adaptively across task types via supervised fine-tuning. In the second stage, task-aware reward functions verify entity grounding, temporal alignment, and task-adaptive logical consistency, selectively strengthening each reasoning pathway via reinforcement fine-tuning with GRPO. Our 3B-parameter model, trained on only 16K samples, achieves 37.5% average accuracy on the challenging HD-EPIC benchmark, surpassing Qwen2.5-VL-7B (25.7%) by over 10 points. --- ### Causal Interpretation of Neural Network Computations with Contribution Decomposition Authors: Joshua Brendan Melander, Zaki Alaoui, Shenghua Liu, Surya Ganguli, Stephen A. Baccus Published: 2026-03-06 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2603.06557v1 Understanding how neural networks transform inputs into outputs is crucial for interpreting and manipulating their behavior. Most existing approaches analyze internal representations by identifying hidden-layer activation patterns correlated with human-interpretable concepts. Here we take a direct approach to examine how hidden neurons act to drive network outputs. We introduce CODEC (Contribution Decomposition), a method that uses sparse autoencoders to decompose network behavior into sparse motifs of hidden-neuron contributions, revealing causal processes that cannot be determined by analyzing activations alone. Applying CODEC to benchmark image-classification networks, we find that contributions grow in sparsity and dimensionality across layers and, unexpectedly, that they progressively decorrelate positive and negative effects on network outputs. We further show that decomposing contributions into sparse modes enables greater control and interpretation of intermediate layers, supporting both causal manipulations of network output and human-interpretable visualizations of distinct image components that combine to drive that output. Finally, by analyzing state-of-the-art models of neural activity in the vertebrate retina, we demonstrate that CODEC uncovers combinatorial actions of model interneurons and identifies the sources of dynamic receptive fields. Overall, CODEC provides a rich and interpretable framework for understanding how nonlinear computations evolve across hierarchical layers, establishing contribution modes as an informative unit of analysis for mechanistic insights into artificial neural networks. --- ### Hierarchical Industrial Demand Forecasting with Temporal and Uncertainty Explanations Authors: Harshavardhan Kamarthi, Shangqing Xu, Xinjie Tong, Xingyu Zhou, James Peters, Joseph Czyzyk, B. Aditya Prakash Published: 2026-03-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06555v1 Hierarchical time-series forecasting is essential for demand prediction across various industries. While machine learning models have obtained significant accuracy and scalability on such forecasting tasks, the interpretability of their predictions, informed by application, is still largely unexplored. To bridge this gap, we introduce a novel interpretability method for large hierarchical probabilistic time-series forecasting, adapting generic interpretability techniques while addressing challenges associated with hierarchical structures and uncertainty. Our approach offers valuable interpretative insights in response to real-world industrial supply chain scenarios, including 1) the significance of various time-series within the hierarchy and external variables at specific time points, 2) the impact of different variables on forecast uncertainty, and 3) explanations for forecast changes in response to modifications in the training dataset. To evaluate the explainability method, we generate semi-synthetic datasets based on real-world scenarios of explaining hierarchical demands for over ten thousand products at a large chemical company. The experiments showed that our explainability method successfully explained state-of-the-art industrial forecasting methods with significantly higher explainability accuracy. Furthermore, we provide multiple real-world case studies that show the efficacy of our approach in identifying important patterns and explanations that help stakeholders better understand the forecasts. Additionally, our method facilitates the identification of key drivers behind forecasted demand, enabling more informed decision-making and strategic planning. Our approach helps build trust and confidence among users, ultimately leading to better adoption and utilization of hierarchical forecasting models in practice. --- ### KCLarity at SemEval-2026 Task 6: Encoder and Zero-Shot Approaches to Political Evasion Detection Authors: Archie Sage, Salvatore Greco Published: 2026-03-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.06552v2 This paper describes the KCLarity team's participation in CLARITY, a shared task at SemEval 2026 on classifying ambiguity and evasion techniques in political discourse. We investigate two modelling formulations: (i) directly predicting the clarity label, and (ii) predicting the evasion label and deriving clarity through the task taxonomy hierarchy. We further explore several auxiliary training variants and evaluate decoder-only models in a zero-shot setting under the evasion-first formulation. Overall, the two formulations yield comparable performance. Among encoder-based models, RoBERTa-large achieves the strongest results on the public test set, while zero-shot GPT-5.2 generalises better on the hidden evaluation set. --- ### LiveSense: A Real-Time Wi-Fi Sensing Platform for Range-Doppler on COTS Laptop Authors: Jessica Sanson, Rahul C. Shah, Maximilian Pinaroc, Cagri Tanriover, Valerio Frascolla Published: 2026-03-06 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2603.06545v2 We present LiveSense - a cross-platform that transforms a commercial off-the-shelf (COTS) Wi-Fi Network Interface Card (NIC) on a laptop into a centimeter-level Range-Doppler sensor while preserving simultaneous communication capability. The laptops are equipped with COTS Intel AX211 (Wi-Fi 6E) or Intel BE201 (Wi-Fi 7) NICs. LiveSense can (i) Extract fully-synchronized channel state information (CSI) at >= 40 Hz, (ii) Perform time-phase alignment and self-interference cancellation on-device, and (iii) Provide a real-time stream of range, Doppler, subcarrier magnitude/phase and annotated video frames to a Python/Qt Graphical User Interface (GUI). The demo will showcase the ability to detect (i) Distance and radial velocity of attendees within a few meters of the device, (ii) Micro-motion (respiration), and (iii) Hand-gesture ranging. To the best of our knowledge, this is the first-ever demo to obtain accurate range information of targets from commercial Wi-Fi, despite the limited 160 MHz bandwidth. --- ### Modeling and Measuring Redundancy in Multisource Multimodal Data for Autonomous Driving Authors: Yuhan Zhou, Mehri Sattari, Haihua Chen, Kewei Sha Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06544v1 Next-generation autonomous vehicles (AVs) rely on large volumes of multisource and multimodal ($M^2$) data to support real-time decision-making. In practice, data quality (DQ) varies across sources and modalities due to environmental conditions and sensor limitations, yet AV research has largely prioritized algorithm design over DQ analysis. This work focuses on redundancy as a fundamental but underexplored DQ issue in AV datasets. Using the nuScenes and Argoverse 2 (AV2) datasets, we model and measure redundancy in multisource camera data and multimodal image-LiDAR data, and evaluate how removing redundant labels affects the YOLOv8 object detection task. Experimental results show that selectively removing redundant multisource image object labels from cameras with shared fields of view improves detection. In nuScenes, mAP${50}$ gains from $0.66$ to $0.70$, $0.64$ to $0.67$, and from $0.53$ to $0.55$, on three representative overlap regions, while detection on other overlapping camera pairs remains at the baseline even under stronger pruning. In AV2, $4.1$-$8.6\%$ of labels are removed, and mAP${50}$ stays near the $0.64$ baseline. Multimodal analysis also reveals substantial redundancy between image and LiDAR data. These findings demonstrate that redundancy is a measurable and actionable DQ factor with direct implications for AV performance. This work highlights the role of redundancy as a data quality factor in AV perception and motivates a data-centric perspective for evaluating and improving AV datasets. Code, data, and implementation details are publicly available at: https://github.com/yhZHOU515/RedundancyAD --- ### SurgFormer: Scalable Learning of Organ Deformation with Resection Support and Real-Time Inference Authors: Ashkan Shahbazi, Elaheh Akbari, Kyvia Pereira, Jon S. Heiselman, Annie C. Benson, Garrison L. H. Johnston, Jie Ying Wu, Nabil Simaan, Michael I. Miga, Soheil Kolouri Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06543v1 We introduce SurgFormer, a multiresolution gated transformer for data driven soft tissue simulation on volumetric meshes. High fidelity biomechanical solvers are often too costly for interactive use, so we train SurgFormer on solver generated data to predict nodewise displacement fields at near real time rates. SurgFormer builds a fixed mesh hierarchy and applies repeated multibranch blocks that combine local message passing, coarse global self attention, and pointwise feedforward updates, fused by learned per node, per channel gates to adaptively integrate local and long range information while remaining scalable on large meshes. For cut conditioned simulation, resection information is encoded as a learned cut embedding and provided as an additional input, enabling a unified model for both standard deformation prediction and topology altering cases. We also introduce two surgical simulation datasets generated under a unified protocol with XFEM based supervision: a cholecystectomy resection dataset and an appendectomy manipulation and resection dataset with cut and uncut cases. To our knowledge, this is the first learned volumetric surrogate setting to study XFEM supervised cut conditioned deformation within the same volumetric pipeline as standard deformation prediction. Across diverse baselines, SurgFormer achieves strong accuracy with favorable efficiency, making it a practical backbone for both tasks. {Code, data, and project page: \href{https://mint-vu.github.io/SurgFormer/}{available here}} --- ### RAMoEA-QA: Hierarchical Specialization for Robust Respiratory Audio Question Answering Authors: Gaia A. Bertolino, Yuwei Zhang, Tong Xia, Domenico Talia, Cecilia Mascolo Published: 2026-03-06 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.06542v2 Conversational generative AI is increasingly explored in healthcare, where models must integrate heterogeneous patient signals and support diverse interaction styles while producing clinically meaningful outputs. In respiratory care, non-invasive audio recordings captured with sensing devices offer a scalable route to screening and longitudinal monitoring, but heterogeneity is particularly acute: recordings vary across devices, environments, and acquisition protocols, and queries may vary in intent, answer format, and prediction objective. Existing biomedical audio-language question answering systems for respiratory assessment are starting to emerge, but they are typically built as single-path models, processing all inputs through the same acoustic and language pathway despite variation in recording conditions and query types. They are also usually evaluated in relatively limited settings, leaving open their robustness under realistic distribution shifts, including changes in acquisition domains, modality, and clinical task. To address this gap, we introduce RAMoEA-QA, the first RA QA model designed to support input-dependent specialization across heterogeneous recordings and query types within a unified hierarchical two-stage framework. We study this design in a unified RA QA setting spanning clinical and self-recorded, multi-device acquisition settings, question formats, and both discrete and continuous targets. Across in-domain and controlled-shift evaluations, RAMoEA-QA improves over matched monolithic baselines and routing controls, reaching 0.72 in in-domain test accuracy (vs. 0.61 and 0.67 for single-path baselines) on discriminative tasks, while also achieving the best regression performance and stronger average transfer under dataset, modality, and task shifts, including gains of up to 23 percentage points in accuracy on the COPD modality-shift setting. --- ### NEGATE: Constrained Semantic Guidance for Linguistic Negation in Text-to-Video Diffusion Authors: Taewon Kang, Ming C. Lin Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06533v1 Negation is a fundamental linguistic operator, yet it remains inadequately modeled in diffusion-based generative systems. In this work, we present a formal treatment of linguistic negation in diffusion-based generative models by modeling it as a structured feasibility constraint on semantic guidance within diffusion dynamics. Rather than introducing heuristics or retraining model parameters, we reinterpret classifier-free guidance as defining a semantic update direction and enforce negation by projecting the update onto a convex constraint set derived from linguistic structure. This novel formulation provides a unified framework for handling diverse negation phenomena, including object absence, graded non-inversion semantics, multi-negation composition, and scope-sensitive disambiguation. Our approach is training-free, compatible with pretrained diffusion backbones, and naturally extends from image generation to temporally evolving video trajectories. In addition, we introduce a structured negation-centric benchmark suite that isolates distinct linguistic failure modes in generative systems, to further research in this area. Experiments demonstrate that our method achieves robust negation compliance while preserving visual fidelity and structural coherence, establishing the first unified formulation of linguistic negation in diffusion-based generative models beyond representation-level evaluation. --- ### Spatial Calibration of Diffuse LiDARs Authors: Nikhil Behari, Ramesh Raskar Published: 2026-03-06 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.06531v1 Diffuse direct time-of-flight LiDARs report per-pixel depth histograms formed by aggregating photon returns over a wide instantaneous field of view, violating the single-ray assumption behind standard LiDAR-RGB calibration. We present a simple spatial calibration procedure that estimates, for each diffuse LiDAR pixel, its footprint (effective support region) and relative spatial sensitivity in a co-located RGB image plane. Using a scanned retroreflective patch with background subtraction, we recover per-pixel response maps that provide an explicit LiDAR-to-RGB correspondence for cross-modal alignment and fusion. We demonstrate the method on the ams OSRAM TMF8828. --- ### AV-Unified: A Unified Framework for Audio-visual Scene Understanding Authors: Guangyao Li, Xin Wang, Wenwu Zhu Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06530v1 When humans perceive the world, they naturally integrate multiple audio-visual tasks within dynamic, real-world scenes. However, current works such as event localization, parsing, segmentation and question answering are mostly explored individually, making it challenging to comprehensively understand complex audio-visual scenes and explore inter-task relationships. Hence, we propose \textbf{AV-Unified}, a unified framework that enables joint learning across a wide range of audio-visual scene understanding tasks. AV-Unified standardizes the diverse input-output formats of each task and incorporates a multi-scale spatiotemporal perception network to effectively capture audio-visual associations. Specifically, we unify the inputs and outputs of all supported tasks by converting them into sequences of discrete tokens, establishing a shared representation that allows a single architecture to be trained jointly across heterogeneous varied datasets. Considering the varying temporal granularity of audio-visual events, a multi-scale temporal perception module is designed to capture key cues. Meanwhile, to overcome the lack of auditory supervision in the visual domain, we design a cross-modal guidance-based spatial perception module that models spatial audio-visual associations. Furthermore, task-specific text prompts are employed to enhance the model's adaptability and task-awareness. Extensive experiments on benchmark datasets (e.g., AVE, LLP, MUSIC-AVQA, VGG-SS and AVS) demonstrate the effectiveness of AV-Unified across temporal, spatial, and spatiotemporal tasks. --- ### Artificial Intelligence for Detecting Fetal Orofacial Clefts and Advancing Medical Education Authors: Yuanji Zhang, Yuhao Huang, Haoran Dou, Xiliang Zhu, Chen Ling, Zhong Yang, Lianying Liang, Jiuping Li, Siying Liang, Rui Li, Yan Cao, Yuhan Zhang et al. Published: 2026-03-06 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.06522v1 Orofacial clefts are among the most common congenital craniofacial abnormalities, yet accurate prenatal detection remains challenging due to the scarcity of experienced specialists and the relative rarity of the condition. Early and reliable diagnosis is essential to enable timely clinical intervention and reduce associated morbidity. Here we show that an artificial intelligence system, trained on over 45,139 ultrasound images from 9,215 fetuses across 22 hospitals, can diagnose fetal orofacial clefts with sensitivity and specificity exceeding 93% and 95% respectively, matching the performance of senior radiologists and substantially outperforming junior radiologists. When used as a medical copilot, the system raises junior radiologists' sensitivity by more than 6%. Beyond direct diagnostic assistance, the system also accelerates the development of clinical expertise. A pilot study involving 24 radiologists and trainees demonstrated that the model can improve the expertise development for rare conditions. This dual-purpose approach offers a scalable solution for improving both diagnostic accuracy and specialist training in settings where experienced radiologists are scarce. --- ### SG-DOR: Learning Scene Graphs with Direction-Conditioned Occlusion Reasoning for Pepper Plants Authors: Rohit Menon, Niklas Mueller-Goldingen, Sicong Pan, Gokul Krishna Chenchani, Maren Bennewitz Published: 2026-03-06 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.06512v1 Robotic harvesting in dense crop canopies requires effective interventions that depend not only on geometry, but also on explicit, direction-conditioned relations identifying which organs obstruct a target fruit. We present SG-DOR (Scene Graphs with Direction-Conditioned Occlusion Reasoning), a relational framework that, given instance-segmented organ point clouds, infers a scene graph encoding physical attachments and direction-conditioned occlusion. We introduce an occlusion ranking task for retrieving and ranking candidate leaves for a target fruit and approach direction, and propose a direction-aware graph neural architecture with per-fruit leaf-set attention and union-level aggregation. Experiments on a multi-plant synthetic pepper dataset show improved occlusion prediction (F1=0.73, NDCG@3=0.85) and attachment inference (edge F1=0.83) over strong ablations, yielding a structured relational signal for downstream intervention planning. --- ### When One Modality Rules Them All: Backdoor Modality Collapse in Multimodal Diffusion Models Authors: Qitong Wang, Haoran Dai, Haotian Zhang, Christopher Rasmussen, Binghui Wang Published: 2026-03-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06508v1 While diffusion models have revolutionized visual content generation, their rapid adoption has underscored the critical need to investigate vulnerabilities, e.g., to backdoor attacks. In multimodal diffusion models, it is natural to expect that attacking multiple modalities simultaneously (e.g., text and image) would yield complementary effects and strengthen the overall backdoor. In this paper, we challenge this assumption by investigating the phenomenon of Backdoor Modality Collapse, a scenario where the backdoor mechanism degenerates to rely predominantly on a subset of modalities, rendering others redundant. To rigorously quantify this behavior, we introduce two novel metrics: Trigger Modality Attribution (TMA) and Cross-Trigger Interaction (CTI). Through extensive experiments across diverse training configurations in multimodal conditional diffusion, we consistently observe a ``winner-takes-all'' dynamic in backdoor behavior. Our results reveal that (1) attacks often collapse into subset-modality dominance, and (2) cross-modal interaction is negligible or even negative, contradicting the intuition of synergistic vulnerability. These findings highlight a critical blind spot in current assessments, suggesting that high attack success rates often mask a fundamental reliance on a subset of modalities. This establishes a principled foundation for mechanistic analysis and future defense development. --- ### Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis Authors: Hila Chefer, Patrick Esser, Dominik Lorenz, Dustin Podell, Vikash Raja, Vinh Tong, Antonio Torralba, Robin Rombach Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06507v1 Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit unexpected scaling behavior. We argue that this dependence arises from the model's training objective, which poses a denoising task with little incentive to learn semantic representations. We introduce Self-Flow: a self-supervised flow matching paradigm that integrates representation learning within the generative framework. Our key mechanism, Dual-Timestep Scheduling, applies heterogeneous noise levels across tokens, creating an information asymmetry that forces the model to infer missing information from corrupted inputs. This drives learning strong representations alongside generative capabilities without external supervision. Our method generalizes across modalities and enables multi-modal training while following expected scaling laws, achieving superior image, video, and audio generation. --- ### Semantics-Aware Caching for Concept Learning Authors: Louis Mozart Kamdem Teyou, Caglar Demir, Axel-Cyrille Ngonga Ngomo Published: 2026-03-06 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.06506v2 Concept learning is a form of supervised machine learning that operates on knowledge bases in description logics. State-of-the-art concept learners often rely on an iterative search through a countably infinite concept space. In each iteration, they retrieve instances of candidate solutions to select the best concept for the next iteration. While simple learning problems might require a few dozen instance retrieval calls to find a fitting solution, complex learning problems might necessitate thousands of calls. We alleviate the resulting runtime challenge by presenting a semantics-aware caching approach. Our cache is essentially a subsumption-aware map that links concepts to a set of instances via crisp set operations. Our experiments on 5 datasets with 4 symbolic reasoners, a neuro-symbolic reasoner, and 5 popular pagination policies demonstrate that our cache can reduce the runtime of concept retrieval and concept learning by an order of magnitude while being effective for both symbolic and neuro-symbolic reasoners. --- ### Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning Authors: Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar Published: 2026-03-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.06505v2 Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR show promise, two key challenges persist: limited multilingual support and the absence of principled alignment between speech and contextual representations. In this paper, we introduce a context-aware multilingual ASR framework that supports diverse languages and accents while preserving the modularity of pretrained models. Our approach combines a frozen speech encoder and a decoder-only language model via a lightweight projection module, allowing structured context prompts, including dialogue history and biasing words, to guide transcription. To improve interaction between speech and context, we employ a contrastive learning objective that aligns their representations in a shared embedding space. Evaluations on over 1,500 hours of real-world conversational speech across 11 languages and 5 English dialects show that contextual input consistently improves recognition quality. Contrastive alignment provides additional gains when applied to different context types, with an overall performance gain of over 5%. These results highlight the importance of both contextual modeling and cross-modal alignment in multilingual ASR. --- ### Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning Authors: Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar Published: 2026-03-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.06505v1 Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR show promise, two key challenges persist: limited multilingual support and the absence of principled alignment between speech and contextual representations. In this paper, we introduce a context-aware multilingual ASR framework that supports diverse languages and accents while preserving the modularity of pretrained models. Our approach combines a frozen speech encoder and a decoder-only language model via a lightweight projection module, allowing structured context prompts, including dialogue history and biasing words, to guide transcription. To improve interaction between speech and context, we employ a contrastive learning objective that aligns their representations in a shared embedding space. Evaluations on over 1,500 hours of real-world conversational speech across 11 languages and 5 English dialects show that contextual input consistently improves recognition quality. Contrastive alignment provides additional gains when applied to different context types, with an overall performance gain of over 5%. These results highlight the importance of both contextual modeling and cross-modal alignment in multilingual ASR. --- ### Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editing Authors: Anmol Gulati, Sahil Sen, Waqar Sarguroh, Kevin Paul Published: 2026-03-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.06503v1 Recent advances in multimodal Retrieval-Augmented Generation (RAG) enable Large Language Models (LLMs) to analyze enterprise spreadsheet workbooks containing millions of cells, cross-sheet dependencies, and embedded visual artifacts. However, state-of-the-art approaches exclude critical context through single-pass retrieval, lose data resolution through compression, and exceed LLM context windows through naive full-context injection, preventing reliable multi-step reasoning over complex enterprise workbooks. We introduce Beyond Rows to Reasoning (BRTR), a multimodal agentic framework for spreadsheet understanding that replaces single-pass retrieval with an iterative tool-calling loop, supporting end-to-end Excel workflows from complex analysis to structured editing. Supported by over 200 hours of expert human evaluation, BRTR achieves state-of-the-art performance across three frontier spreadsheet understanding benchmarks, surpassing prior methods by 25 percentage points on FRTR-Bench, 7 points on SpreadsheetLLM, and 32 points on FINCH. We evaluate five multimodal embedding models, identifying NVIDIA NeMo Retriever 1B as the top performer for mixed tabular and visual data, and vary nine LLMs. Ablation experiments confirm that the planner, retrieval, and iterative reasoning each contribute substantially, and cost analysis shows GPT-5.2 achieves the best efficiency-accuracy trade-off. Throughout all evaluations, BRTR maintains full auditability through explicit tool-call traces. --- ### COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics Authors: Kartik Sharma, Rakshit S. Trivedi Published: 2026-03-06 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.06495v1 Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from labeled examples, while methods that better extract these signals require hundreds to thousands of examples. We introduce COLD-Steer, a training-free framework that steers LLM activations by approximating the representational changes that would result from gradient descent on in-context examples. Our key insight is that the effect of fine-tuning on a small set of examples can be efficiently approximated at inference time without actual parameter updates. We formalize this through two complementary approaches: (i) a unit kernel approximation method that updates the activations directly using gradients with respect to them, normalized across examples, and (ii) a finite-difference approximation requiring only two forward passes regardless of example count. Experiments across a variety of steering tasks and benchmarks demonstrate that COLD-Steer achieves upto 95% steering effectiveness while using 50 times fewer samples compared to the best baseline. COLD-Steer facilitates accommodating diverse perspectives without extensive demonstration data, which we validate through our experiments on pluralistic alignment tasks. Our framework opens new possibilities for adaptive, context-aware model control that can flexibly address varying loss-driven human preferences through principled approximation of learning dynamics rather than specialized training procedures. --- ### NOBLE: Accelerating Transformers with Nonlinear Low-Rank Branches Authors: Ethan Smith Published: 2026-03-06 Categories: cs.LG, cs.AI, cs.CL, cs.NE arXiv: https://arxiv.org/abs/2603.06492v1 We introduce NOBLE (Nonlinear lOw-rank Branch for Linear Enhancement), an architectural augmentation that adds nonlinear low-rank branches to transformer linear layers. Unlike LoRA and other parameter-efficient fine-tuning (PEFT) methods, NOBLE is designed for pretraining from scratch. The branch is a permanent part of the architecture as opposed to an adapter for finetuning on top of frozen weights. The branch computes σ(xWdown)Wup where σ is a learnable nonlinearity. We evaluate several activation functions and find that CosNet, a two-layer cosine nonlinearity with learnable frequency and phase with a linear projection in between them in the bottleneck space, performs best. NOBLE achieves substantial improvements with minimal overhead: up to 1.47x step speedup to reach baseline eval loss (up to 32% fewer training steps), with as low as 4% additional parameters and 7% step time overhead, resulting in up to 1.22x net wallclock speedup. Experiments on LLMs (250M and 1.5B parameters), BERT, VQGAN, and ViT consistently show improved training efficiency. We identify one caveat: Mixup/CutMix augmentation interferes with NOBLE's benefits in Imagenet classification along with other stochastic augmentations, but when disabled, ViT also improves. This discrepancy is possibly explained by regularization techniques that encourage smoother fits to the target function while NOBLE may specialize more in sharper aspects of the target function. --- ### Score Reversal Is Not Free for Quantum Diffusion Models Authors: Ammar Fayad Published: 2026-03-06 Categories: quant-ph, cs.LG, math-ph arXiv: https://arxiv.org/abs/2603.06488v3 Classical reverse diffusion is generated by changing the drift at fixed noise. We show that the quantum version of this principle obeys an exact law with a sharp phase boundary. For Gaussian pure-loss dynamics, the canonical model of continuous-variable decoherence, we prove that the unrestricted instantaneous reverse optimum exhibits a noiseless-to-noisy transition: below a critical squeezing-to-thermal ratio, reversal can be noiseless; above it, complete positivity forces irreducible reverse noise whose minimum cost we determine in closed form. The optimal reverse diffusion is uniquely covariance-aligned and simultaneously minimizes the geometric, metrological, and thermodynamic price of reversal. For multimode trajectories, the exact cost is additive in a canonical set of mode-resolved data, and a globally continuous protocol attains this optimum on every mixed-state interval. If a pure nonclassical endpoint is included, the same pointwise law holds for every $t>0$, but the optimum diverges as $2/t$: exact Gaussian reversal of a pure quantum state is dynamically unattainable. These results establish the exact Gaussian benchmark against which any broader theory of quantum reverse diffusion must be measured. --- ### PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations Authors: Vittoria Vineis, Matteo Silvestri, Lorenzo Antonelli, Filippo Betello, Gabriele Tolomei Published: 2026-03-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.06485v1 Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a one-size-fits-all paradigm that neglects user differences in expertise, goals, and cognitive needs. Although Large Language Models can translate technical explanations into natural language, they introduce challenges related to faithfulness and hallucinations. To address these challenges, we present PONTE (Personalized Orchestration for Natural language Trustworthy Explanations), a human-in-the-loop framework for adaptive and reliable XAI narratives. PONTE models personalization as a closed-loop validation and adaptation process rather than prompt engineering. It combines: (i) a low-dimensional preference model capturing stylistic requirements; (ii) a preference-conditioned generator grounded in structured XAI artifacts; and (iii) verification modules enforcing numerical faithfulness, informational completeness, and stylistic alignment, optionally supported by retrieval-grounded argumentation. User feedback iteratively updates the preference state, enabling quick personalization. Automatic and human evaluations across healthcare and finance domains show that the verification-refinement loop substantially improves completeness and stylistic alignment over validation-free generation. Human studies further confirm strong agreement between intended preference vectors and perceived style, robustness to generation stochasticity, and consistently positive quality assessments. --- ### Match4Annotate: Cross-Video Annotation Transfer in Ultrasound via Implicit Feature Flow-Guided Matching Authors: Zhuorui Zhang, Roger Pallarès-López, Praneeth Namburi, Brian W. Anthony Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06471v3 Acquiring per-frame annotations for ultrasound videos is costly and requires clinical expertise, limiting learning-based analysis. We study cross-video annotation transfer: propagating user-specified annotations from a labeled ultrasound video to an independently acquired target video with no target-side labels or manual initialization. Video trackers and segmentation propagators rely on temporal continuity and require a prompt in every new sequence, whereas cross-image feature matching and one-shot segmentation estimate correspondences independently, without enforcing coherent deformations or supporting both point and mask annotations. We present Match4Annotate, a test-time framework with three stages. A spatiotemporal implicit feature representation lifts frozen vision foundation-model features into a continuous field over space and time, enabling queries beyond the backbone resolution. A continuous implicit feature flow then aligns the source and target fields under a smooth-deformation prior, estimating correspondence in feature space rather than relying on intensity consistency, which is often violated in ultrasound by speckle and acquisition-dependent appearance. Finally, flow-guided annotation transfer uses the estimated flow as a spatial prior over feature similarity. This formulation unifies sparse point and dense mask transfer and includes unconstrained feature matching and direct flow warping as limiting cases. On four clinical ultrasound datasets spanning echocardiography and musculoskeletal imaging, Match4Annotate achieves state-of-the-art annotation transfer, outperforming dense feature-matching baselines across PCK thresholds and one-shot segmentation methods in Dice score. It also demonstrates bidirectional transfer of left-ventricular annotations across datasets. It requires no task-specific training and adapts to each video in minutes on a single consumer GPU. --- ### Match4Annotate: Propagating Sparse Video Annotations via Implicit Neural Feature Matching Authors: Zhuorui Zhang, Roger Pallarès-López, Praneeth Namburi, Brian W. Anthony Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06471v2 Acquiring per-frame video annotations remains a primary bottleneck for deploying computer vision in specialized domains such as medical imaging, where expert labeling is slow and costly. Label propagation offers a natural solution, yet existing approaches face fundamental limitations. Video trackers and segmentation models can propagate labels within a single sequence but require per-video initialization and cannot generalize across videos. Classic correspondence pipelines operate on detector-chosen keypoints and struggle in low-texture scenes, while dense feature matching and one-shot segmentation methods enable cross-video propagation but lack spatiotemporal smoothness and unified support for both point and mask annotations. We present Match4Annotate, a lightweight framework for both intra-video and inter-video propagation of point and mask annotations. Our method fits a SIREN-based implicit neural representation to DINOv3 features at test time, producing a continuous, high-resolution spatiotemporal feature field, and learns a smooth implicit deformation field between frame pairs to guide correspondence matching. We evaluate on three challenging clinical ultrasound datasets. Match4Annotate achieves state-of-the-art inter-video propagation, outperforming feature matching and one-shot segmentation baselines, while remaining competitive with specialized trackers for intra-video propagation. Our results show that lightweight, test-time-optimized feature matching pipelines have the potential to offer an efficient and accessible solution for scalable annotation workflows. ---