# Research Papers — 2026-02 · bundle page 17 of 210 > Full-text markdown of papers #801–850 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/17 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/16.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/18.md) ### Skarimva: Skeleton-based Action Recognition is a Multi-view Application Authors: Daniel Bermuth, Alexander Poeppel, Wolfgang Reif Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23231v2 Human action recognition plays an important role when developing intelligent interactions between humans and machines. While there is a lot of active research on improving the machine learning algorithms for skeleton-based action recognition, not much attention has been given to the quality of the input skeleton data itself. This work demonstrates that by making use of multiple camera views to triangulate more accurate 3D~skeletons, the performance of state-of-the-art action recognition models can be improved significantly. This suggests that the quality of the input data is currently a limiting factor for the performance of these models. Based on these results, it is argued that the cost-benefit ratio of using multiple cameras is very favorable in most practical use-cases, therefore future research in skeleton-based action recognition should consider multi-view applications as the standard setup. --- ### Large Multimodal Models as General In-Context Classifiers Authors: Marco Garosi, Matteo Farina, Alessandro Conti, Massimiliano Mancini, Elisa Ricci Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23229v1 Which multimodal model should we use for classification? Previous studies suggest that the answer lies in CLIP-like contrastive Vision-Language Models (VLMs), due to their remarkable performance in zero-shot classification. In contrast, Large Multimodal Models (LMM) are more suitable for complex tasks. In this work, we argue that this answer overlooks an important capability of LMMs: in-context learning. We benchmark state-of-the-art LMMs on diverse datasets for closed-world classification and find that, although their zero-shot performance is lower than CLIP's, LMMs with a few in-context examples can match or even surpass contrastive VLMs with cache-based adapters, their "in-context" equivalent. We extend this analysis to the open-world setting, where the generative nature of LMMs makes them more suitable for the task. In this challenging scenario, LMMs struggle whenever provided with imperfect context information. To address this issue, we propose CIRCLE, a simple training-free method that assigns pseudo-labels to in-context examples, iteratively refining them with the available context itself. Through extensive experiments, we show that CIRCLE establishes a robust baseline for open-world classification, surpassing VLM counterparts and highlighting the potential of LMMs to serve as unified classifiers, and a flexible alternative to specialized models. --- ### MovieTeller: Tool-augmented Movie Synopsis with ID Consistent Progressive Abstraction Authors: Yizhi Li, Xiaohan Chen, Miao Jiang, Wentao Tang, Gaoang Wang Published: 2026-02-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.23228v2 With the explosive growth of digital entertainment, automated video summarization has become indispensable for applications such as content indexing, personalized recommendation, and efficient media archiving. Automatic synopsis generation for long-form videos, such as movies and TV series, presents a significant challenge for existing Vision-Language Models (VLMs). While proficient at single-image captioning, these general-purpose models often exhibit critical failures in long-duration contexts, primarily a lack of ID-consistent character identification and a fractured narrative coherence. To overcome these limitations, we propose MovieTeller, a novel framework for generating movie synopses via tool-augmented progressive abstraction. Our core contribution is a training-free, tool-augmented, fact-grounded generation process. Instead of requiring costly model fine-tuning, our framework directly leverages off-the-shelf models in a plug-and-play manner. We first invoke a specialized face recognition model as an external "tool" to establish Factual Groundings--precise character identities and their corresponding bounding boxes. These groundings are then injected into the prompt to steer the VLM's reasoning, ensuring the generated scene descriptions are anchored to verifiable facts. Furthermore, our progressive abstraction pipeline decomposes the summarization of a full-length movie into a multi-stage process, effectively mitigating the context length limitations of current VLMs. Experiments demonstrate that our approach yields significant improvements in factual accuracy, character consistency, and overall narrative coherence compared to end-to-end baselines. --- ### Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding? Authors: Pengxiang Li, Dilxat Muhtar, Tianlong Chen, Lu Yin, Shiwei Liu Published: 2026-02-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.23225v2 Diffusion Language Models (DLMs) are often advertised as enabling parallel token generation, yet practical fast DLMs frequently converge to left-to-right, autoregressive (AR)-like decoding dynamics. In contrast, genuinely non-AR generation is promising because it removes AR's sequential bottleneck, better exploiting parallel hardware to reduce synchronization/communication overhead and improve latency scaling with output length. We argue that a primary driver of AR-like decoding is a mismatch between DLM objectives and the highly sequential structure of widely used training data, including standard pretraining corpora and long chain-of-thought (CoT) supervision. Motivated by this diagnosis, we propose NAP (Non-Autoregressive Parallel DLMs), a proof-of-concept, data-centric approach that better aligns supervision with non-AR parallel decoding. NAP curates examples as multiple independent reasoning trajectories and couples them with a parallel-forced decoding strategy that encourages multi-token parallel updates. Across math reasoning benchmarks, NAP yields stronger performance under parallel decoding than DLMs trained on standard long CoT data, with gains growing as parallelism increases. Our results suggest that revisiting data and supervision is a principled direction for mitigating AR-like behavior and moving toward genuinely non-autoregressive parallel generation in DLMs. Our code is available at https://github.com/pixeli99/NAP. --- ### UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception Authors: Mohammad Mahdavian, Gordon Tan, Binbin Xu, Yuan Ren, Dongfeng Bai, Bingbing Liu Published: 2026-02-26 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.23224v1 We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semantically informed design. In vision-based robotic navigation, the accurate extraction of environmental structure from raw image sequences is critical for downstream tasks. UniScale addresses this challenge with a single feed-forward network that jointly estimates camera intrinsics and extrinsics, scale-invariant depth and point maps, and the metric scale of a scene from multi-view images, while optionally incorporating auxiliary geometric priors when available. By combining global contextual reasoning with camera-aware feature representations, UniScale is able to recover the metric-scale of the scene. In robotic settings where camera intrinsics are known, they can be easily incorporated to improve performance, with additional gains obtained when camera poses are also available. This co-design enables robust, metric-aware 3D reconstruction within a single unified model. Importantly, UniScale does not require training from scratch, and leverages world priors exhibited in pre-existing models without geometric encoding strategies, making it particularly suitable for resource-constrained robotic teams. We evaluate UniScale on multiple benchmarks, demonstrating strong generalization and consistent performance across diverse environments. We will release our implementation upon acceptance. --- ### Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime Authors: Hiroki Naganuma, Taiji Suzuki, Rio Yokota, Masahiro Nomura, Kohta Ishikawa, Ikuro Sato Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.23219v1 Generalization measures have been studied extensively in the machine learning community to better characterize generalization gaps. However, establishing a reliable generalization measure for statistically singular models such as deep neural networks (DNNs) is difficult due to their complex nature. This study focuses on Takeuchi's information criterion (TIC) to investigate the conditions under which this classical measure can effectively explain the generalization gaps of DNNs. Importantly, the developed theory indicates the applicability of TIC near the neural tangent kernel (NTK) regime. In a series of experiments, we trained more than 5,000 DNN models with 12 architectures, including large models (e.g., VGG-16), on four datasets, and estimated the corresponding TIC values to examine the relationship between the generalization gap and the TIC estimates. We applied several TIC approximation methods with feasible computational costs and assessed the accuracy trade-off. Our experimental results indicate that the estimated TIC values correlate well with the generalization gap under conditions close to the NTK regime. However, we show both theoretically and empirically that outside the NTK regime such correlation disappears. Finally, we demonstrate that TIC provides better trial pruning ability than existing methods for hyperparameter optimization. --- ### Multidimensional Task Learning: A Unified Tensor Framework for Computer Vision Tasks Authors: Alaa El Ichi, Khalide Jbilou Published: 2026-02-26 Categories: cs.CV, math.NA arXiv: https://arxiv.org/abs/2602.23217v2 This paper introduces Multidimensional Task Learning (MTL), a unified mathematical framework based on Generalized Einstein MLPs (GE-MLPs) that operate directly on tensors via the Einstein product. We argue that current computer vision task formulations are inherently constrained by matrix-based thinking: standard architectures rely on matrix-valued weights and vectorvalued biases, requiring structural flattening that restricts the space of naturally expressible tasks. GE-MLPs lift this constraint by operating with tensor-valued parameters, enabling explicit control over which dimensions are preserved or contracted without information loss. Through rigorous mathematical derivations, we demonstrate that classification, segmentation, and detection are special cases of MTL, differing only in their dimensional configuration within a formally defined task space. We further prove that this task space is strictly larger than what matrix-based formulations can natively express, enabling principled task configurations such as spatiotemporal or cross modal predictions that require destructive flattening under conventional approaches. This work provides a mathematical foundation for understanding, comparing, and designing computer vision tasks through the lens of tensor algebra. --- ### Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction Authors: Chenhe Du, Xuanyu Tian, Qing Wu, Muyu Liu, Jingyi Yu, Hongjiang Wei, Yuyao Zhang Published: 2026-02-26 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2602.23214v2 Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generative models as modular priors. However, we identify a critical flaw in prevailing PnP solvers (e.g., based on HQS or Proximal Gradient): they function as memoryless operators, updating estimates solely based on instantaneous gradients. This lack of historical tracking inevitably leads to non-vanishing steady-state bias, where the reconstruction fails to strictly satisfy physical measurements under heavy corruption. To resolve this, we propose Dual-Coupled PnP Diffusion (DC-PnPDP), which restores the classical dual variable to provide integral feedback, progressively enforce agreement between the data-consistency and prior. However, this rigorous geometric coupling introduces a secondary challenge: the accumulated dual residuals exhibit spectrally colored, structured artifacts that violate the Additive White Gaussian Noise (AWGN) assumption of diffusion priors, causing severe hallucinations. To bridge this gap, we introduce Spectral Homogenization (SH), a frequency-domain adaptation mechanism that modulates these structured residuals into statistically compliant pseudo-AWGN inputs. This effectively aligns the solver's rigorous optimization trajectory with the denoiser's valid statistical manifold. Extensive experiments on CT and MRI reconstruction demonstrate that our approach resolves the bias-hallucination trade-off, achieving state-of-the-art fidelity with significantly accelerated convergence. The code is available at https://github.com/duchenhe/DC-PnPDP --- ### Through BrokenEyes: How Eye Disorders Impact Face Detection? Authors: Prottay Kumar Adhikary Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23212v1 Vision disorders significantly impact millions of lives, altering how visual information is processed and perceived. In this work, a computational framework was developed using the BrokenEyes system to simulate five common eye disorders: Age-related macular degeneration, cataract, glaucoma, refractive errors, and diabetic retinopathy and analyze their effects on neural-like feature representations in deep learning models. Leveraging a combination of human and non-human datasets, models trained under normal and disorder-specific conditions revealed critical disruptions in feature maps, particularly for cataract and glaucoma, which align with known neural processing challenges in these conditions. Evaluation metrics such as activation energy and cosine similarity quantified the severity of these distortions, providing insights into the interplay between degraded visual inputs and learned representations. --- ### EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents Authors: Wenjia Wang, Liang Pan, Huaijin Pi, Yuke Lou, Xuqian Ren, Yifan Wu, Zhouyingcheng Liao, Lei Yang, Rishabh Dabral, Christian Theobalt, Taku Komura Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23205v2 Human behaviors in the real world naturally encode rich, long-term contextual information that can be leveraged to train embodied agents for perception, understanding, and acting. However, existing capture systems typically rely on costly studio setups and wearable devices, limiting the large-scale collection of scene-conditioned human motion data in the wild. To address this, we propose EmbodMocap, a portable and affordable data collection pipeline using two moving iPhones. Our key idea is to jointly calibrate dual RGB-D sequences to reconstruct both humans and scenes within a unified metric world coordinate frame. The proposed method allows metric-scale and scene-consistent capture in everyday environments without static cameras or markers, bridging human motion and scene geometry seamlessly. Compared with optical capture ground truth, we demonstrate that the dual-view setting exhibits a remarkable ability to mitigate depth ambiguity, achieving superior alignment and reconstruction performance over single iphone or monocular models. Based on the collected data, we empower three embodied AI tasks: monocular human-scene-reconstruction, where we fine-tune on feedforward models that output metric-scale, world-space aligned humans and scenes; physics-based character animation, where we prove our data could be used to scale human-object interaction skills and scene-aware motion tracking; and robot motion control, where we train a humanoid robot via sim-to-real RL to replicate human motions depicted in videos. Experimental results validate the effectiveness of our pipeline and its contributions towards advancing embodied AI research. --- ### Motion-aware Event Suppression for Event Cameras Authors: Roberto Pellerito, Nico Messikommer, Giovanni Cioffi, Marco Cannici, Davide Scaramuzza Published: 2026-02-26 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.23204v4 Event cameras report asynchronously per-pixel brightness changes with microsecond latency, encoding dynamic visual information as a sparse stream of events. However, their extreme temporal resolution floods perception systems with entangled events from ego-motion and independently moving objects (IMOs), which existing solutions fail to efficiently decouple, relying instead on prohibitive dense 3D reconstructions or limited hand-tuned filters. In this work, we introduce the first framework for Motion-aware Event Suppression, which learns to filter events triggered by IMOs and ego-motion in real time. Our model jointly segments IMOs in the current event stream while predicting their future motion, enabling anticipatory suppression of dynamic events before they occur. Our lightweight architecture achieves 173 Hz inference on consumer-grade GPUs with less than 1 GB of memory usage, outperforming previous state-of-the-art methods on the challenging EVIMO benchmark by 67\% in segmentation accuracy while operating at a 53\% higher inference rate. Moreover, we demonstrate significant benefits for downstream applications: our method accelerates Vision Transformer inference by 83\% via token pruning and improves event-based visual odometry accuracy, reducing Absolute Trajectory Error (ATE) by 13\%. --- ### ColoDiff: Integrating Dynamic Consistency With Content Awareness for Colonoscopy Video Generation Authors: Junhu Fu, Shuyu Liang, Wutong Li, Chen Ma, Peng Huang, Kehao Wang, Ke Chen, Shengli Lin, Pinghong Zhou, Zeju Li, Yuanyuan Wang, Yi Guo Published: 2026-02-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.23203v1 Colonoscopy video generation delivers dynamic, information-rich data critical for diagnosing intestinal diseases, particularly in data-scarce scenarios. High-quality video generation demands temporal consistency and precise control over clinical attributes, but faces challenges from irregular intestinal structures, diverse disease representations, and various imaging modalities. To this end, we propose ColoDiff, a diffusion-based framework that generates dynamic-consistent and content-aware colonoscopy videos, aiming to alleviate data shortage and assist clinical analysis. At the inter-frame level, our TimeStream module decouples temporal dependency from video sequences through a cross-frame tokenization mechanism, enabling intricate dynamic modeling despite irregular intestinal structures. At the intra-frame level, our Content-Aware module incorporates noise-injected embeddings and learnable prototypes to realize precise control over clinical attributes, breaking through the coarse guidance of diffusion models. Additionally, ColoDiff employs a non-Markovian sampling strategy that cuts steps by over 90% for real-time generation. ColoDiff is evaluated across three public datasets and one hospital database, based on both generation metrics and downstream tasks including disease diagnosis, modality discrimination, bowel preparation scoring, and lesion segmentation. Extensive experiments show ColoDiff generates videos with smooth transitions and rich dynamics. ColoDiff presents an effort in controllable colonoscopy video generation, revealing the potential of synthetic videos in complementing authentic representation and mitigating data scarcity in clinical settings. --- ### Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language Authors: Max S. Bennett, Thomas P. Zollo, Richard Zemel Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.23201v2 Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural memory methods promise lightweight updates with minimal forgetting. However, existing neural memory models typically assume a single fixed objective and homogeneous information streams, leaving users with no control over what the model remembers or ignores over time. To address this challenge, we propose a generalized neural memory system that performs flexible updates based on learning instructions specified in natural language. Our approach enables adaptive agents to learn selectively from heterogeneous information sources, supporting settings, such as healthcare and customer service, where fixed-objective memory updates are insufficient. --- ### InnerQ: Hardware-Aware Tuning-Free Quantization of KV Cache for Large Language Models Authors: Sayed Mohammadreza Tayaranian Hosseini, Amir Ardakani, Warren J. Gross Published: 2026-02-26 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.23200v2 When transformer-based language models are deployed for text generation, most of the inference time is spent in the decoding stage, where output tokens are generated sequentially. Reducing the hardware cost of each decoding step is therefore critical for efficient long-context generation. A major bottleneck is the key-value (KV) cache, whose size grows with sequence length and often dominates the model's memory footprint. Prior work has proposed quantization methods to compress the KV cache while minimizing its loss of precision. We present InnerQ, a hardware-aware KV cache quantization scheme that reduces decode latency without compromising evaluation performance. InnerQ performs group-wise quantization by grouping cache matrices along their inner dimension. This grouping strategy aligns dequantization with vector-matrix multiplication and increases data reuse across GPU compute units. As a result, InnerQ reduces memory access and accelerates dequantization, achieving an average $1.3\times$ speedup over prior KV cache quantization methods and $2.7\times$ over the non-quantized baseline. To maintain fidelity under aggressive compression, InnerQ incorporates three techniques: (i) hybrid quantization, which chooses symmetric or asymmetric quantization for each group based on local statistics; (ii) high-precision windows for both recent tokens and attention sink tokens to mitigate outlier leakage; and (iii) per-channel normalization of the key cache, computed once during prefill and folded into the model parameters to eliminate runtime overhead. Beyond reducing latency, experiments on Llama and Mistral models show that InnerQ also improves few-shot evaluation scores relative to prior KV cache quantization methods. --- ### SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation Authors: Jiahao Zhao, Feng Jiang, Shaowei Qin, Zhonghui Zhang, Junhao Liu, Guibing Guo, Hamid Alinejad-Rokny, Min Yang Published: 2026-02-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.23199v1 Large language models (LLMs) are increasingly applied in scientific research, offering new capabilities for knowledge discovery and reasoning. In single-cell biology, however, evaluation practices for both general and specialized LLMs remain inadequate: existing benchmarks are fragmented across tasks, adopt formats such as multiple-choice classification that diverge from real-world usage, and rely on metrics lacking interpretability and biological grounding. We present SC-ARENA, a natural language evaluation framework tailored to single-cell foundation models. SC-ARENA formalizes a virtual cell abstraction that unifies evaluation targets by representing both intrinsic attributes and gene-level interactions. Within this paradigm, we define five natural language tasks (cell type annotation, captioning, generation, perturbation prediction, and scientific QA) that probe core reasoning capabilities in cellular biology. To overcome the limitations of brittle string-matching metrics, we introduce knowledge-augmented evaluation, which incorporates external ontologies, marker databases, and scientific literature to support biologically faithful and interpretable judgments. Experiments and analysis across both general-purpose and domain-specialized LLMs demonstrate that (i) under the Virtual Cell unified evaluation paradigm, current models achieve uneven performance on biologically complex tasks, particularly those demanding mechanistic or causal understanding; and (ii) our knowledge-augmented evaluation framework ensures biological correctness, provides interpretable, evidence-grounded rationales, and achieves high discriminative capacity, overcoming the brittleness and opacity of conventional metrics. SC-Arena thus provides a unified and interpretable framework for assessing LLMs in single-cell biology, pointing toward the development of biology-aligned, generalizable foundation models. --- ### Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models Authors: Chungpa Lee, Jy-yong Sohn, Kangwook Lee Published: 2026-02-26 Categories: cs.CL, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.23197v2 Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations. In practice, such models are often fine-tuned to improve zero-shot performance on downstream tasks, allowing them to solve tasks without examples and thereby reducing inference costs. However, fine-tuning can degrade in-context learning, limiting the performance of fine-tuned models on tasks not seen during fine-tuning. Using linear attention models, we provide a theoretical analysis that characterizes how fine-tuning objectives modify attention parameters and identifies conditions under which this leads to degraded few-shot performance. We show that fine-tuning all attention parameters can harm in-context learning, whereas restricting updates to the value matrix improves zero-shot performance while preserving in-context learning. We further show that incorporating an auxiliary few-shot loss enhances in-context learning primarily on the target task, at the expense of degraded in-context learning ability on tasks not seen during fine-tuning. We provide empirical evidence from synthetic and real-world datasets consistent with the qualitative predictions of our theory. --- ### ESAA: Event Sourcing for Autonomous Agents in LLM-Based Software Engineering Authors: Elzo Brito dos Santos Filho Published: 2026-02-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.23193v1 Autonomous agents based on Large Language Models (LLMs) have evolved from reactive assistants to systems capable of planning, executing actions via tools, and iterating over environment observations. However, they remain vulnerable to structural limitations: lack of native state, context degradation over long horizons, and the gap between probabilistic generation and deterministic execution requirements. This paper presents the ESAA (Event Sourcing for Autonomous Agents) architecture, which separates the agent's cognitive intention from the project's state mutation, inspired by the Event Sourcing pattern. In ESAA, agents emit only structured intentions in validated JSON (agent.result or issue.report); a deterministic orchestrator validates, persists events in an append-only log (activity.jsonl), applies file-writing effects, and projects a verifiable materialized view (roadmap.json). The proposal incorporates boundary contracts (AGENT_CONTRACT.yaml), metaprompting profiles (PARCER), and replay verification with hashing (esaa verify), ensuring the immutability of completed tasks and forensic traceability. Two case studies validate the architecture: (i) a landing page project (9 tasks, 49 events, single-agent composition) and (ii) a clinical dashboard system (50 tasks, 86 events, 4 concurrent agents across 8 phases), both concluding with run.status=success and verify_status=ok. The multi-agent case study demonstrates real concurrent orchestration with heterogeneous LLMs (Claude Sonnet 4.6, Codex GPT-5, Antigravity/Gemini 3 Pro, and Claude Opus 4.6), providing empirical evidence of the architecture's scalability beyond single-agent scenarios. --- ### FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification Authors: Thomas Woergaard, Raghavendra Selvan Published: 2026-02-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.23192v1 Compressing neural networks by quantizing model parameters offers useful trade-off between performance and efficiency. Methods like quantization-aware training and post-training quantization strive to maintain the downstream performance of compressed models compared to the full precision models. However, these techniques do not explicitly consider the impact on algorithmic fairness. In this work, we study fairness-aware mixed-precision quantization schemes for medical image classification under explicit bit budgets. We introduce FairQuant, a framework that combines group-aware importance analysis, budgeted mixed-precision allocation, and a learnable Bit-Aware Quantization (BAQ) mode that jointly optimizes weights and per-unit bit allocations under bitrate and fairness regularization. We evaluate the method on Fitzpatrick17k and ISIC2019 across ResNet18/50, DeiT-Tiny, and TinyViT. Results show that FairQuant configurations with average precision near 4-6 bits recover much of the Uniform 8-bit accuracy while improving worst-group performance relative to Uniform 4- and 8-bit baselines, with comparable fairness metrics under shared budgets. --- ### Uni-Animator: Towards Unified Visual Colorization Authors: Xinyuan Chen, Yao Xu, Shaowen Wang, Pengjie Song, Bowen Deng Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23191v2 We propose Uni-Animator, a novel Diffusion Transformer (DiT)-based framework for unified image and video sketch colorization. Existing sketch colorization methods struggle to unify image and video tasks, suffering from imprecise color transfer with single or multiple references, inadequate preservation of high-frequency physical details, and compromised temporal coherence with motion artifacts in large-motion scenes. To tackle imprecise color transfer, we introduce visual reference enhancement via instance patch embedding, enabling precise alignment and fusion of reference color information. To resolve insufficient physical detail preservation, we design physical detail reinforcement using physical features that effectively capture and retain high-frequency textures. To mitigate motion-induced temporal inconsistency, we propose sketch-based dynamic RoPE encoding that adaptively models motion-aware spatial-temporal dependencies. Extensive experimental results demonstrate that Uni-Animator achieves competitive performance on both image and video sketch colorization, matching that of task-specific methods while unlocking unified cross-domain capabilities with high detail fidelity and robust temporal consistency. --- ### Efficient Adaptation of ROMs for Unsteady Flows Using Data Assimilation Authors: Ismaël Zighed, Andrea Nóvoa, Luca Magri, Taraneh Sayadi Published: 2026-02-26 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2602.23188v3 We propose an efficient retraining strategy for a parameterized Reduced Order Model (ROM) that attains accuracy comparable to full retraining while requiring only a fraction of the computational time and relying solely on sparse observations of the full system. The architecture employs an encode-process-decode structure: a Variational Autoencoder (VAE) to perform dimensionality reduction, and a transformer network to evolve the latent states and model the dynamics. The ROM is parameterized by an external control variable, the Reynolds number in the Navier-Stokes setting, with the transformer exploiting attention mechanisms to capture both temporal dependencies and parameter effects. The probabilistic VAE enables stochastic sampling of trajectory ensembles, providing predictive means and uncertainty quantification through the first two moments. After initial training on a limited set of dynamical regimes, the model is adapted to out-of-sample parameter regions using only sparse data. Its probabilistic formulation naturally supports ensemble generation, which we employ within an ensemble Kalman filtering framework to assimilate data and reconstruct full-state trajectories from minimal observations. We further show that, for the dynamical system considered, the dominant source of error in out-of-sample forecasts stems from distortions of the latent manifold rather than changes in the latent dynamics. Consequently, retraining can be limited to the autoencoder, allowing for a lightweight, computationally efficient adaptation procedure with very sparse fine-tuning data. --- ### Efficient Real-Time Adaptation of ROMs for Unsteady Flows Using Data Assimilation Authors: Ismaël Zighed, Andrea Nóvoa, Luca Magri, Taraneh Sayadi Published: 2026-02-26 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2602.23188v1 We propose an efficient retraining strategy for a parameterized Reduced Order Model (ROM) that attains accuracy comparable to full retraining while requiring only a fraction of the computational time and relying solely on sparse observations of the full system. The architecture employs an encode-process-decode structure: a Variational Autoencoder (VAE) to perform dimensionality reduction, and a transformer network to evolve the latent states and model the dynamics. The ROM is parameterized by an external control variable, the Reynolds number in the Navier-Stokes setting, with the transformer exploiting attention mechanisms to capture both temporal dependencies and parameter effects. The probabilistic VAE enables stochastic sampling of trajectory ensembles, providing predictive means and uncertainty quantification through the first two moments. After initial training on a limited set of dynamical regimes, the model is adapted to out-of-sample parameter regions using only sparse data. Its probabilistic formulation naturally supports ensemble generation, which we employ within an ensemble Kalman filtering framework to assimilate data and reconstruct full-state trajectories from minimal observations. We further show that, for the dynamical system considered, the dominant source of error in out-of-sample forecasts stems from distortions of the latent manifold rather than changes in the latent dynamics. Consequently, retraining can be limited to the autoencoder, allowing for a lightweight, computationally efficient, real-time adaptation procedure with very sparse fine-tuning data. --- ### MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations Authors: Sara Rosenthal, Yannis Katsis, Vraj Shah, Lihong He, Lucian Popa, Marina Danilevsky Published: 2026-02-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.23184v1 We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augmented generation, a popular use of large language models. We release a benchmark of 666 tasks containing over 2,800 conversation turns across 6 domains with accompanying corpora. Our experiments show that retrieval and generation models continue to struggle on conversations with UNanswerable, UNderspecified, and NONstandalone questions and UNclear responses. Our benchmark is available at https://github.com/IBM/mt-rag-benchmark --- ### Closing the gap on tabular data with Fourier and Implicit Categorical Features Authors: Marius Dragoi, Florin Gogianu, Elena Burceanu Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.23182v1 While Deep Learning has demonstrated impressive results in applications on various data types, it continues to lag behind tree-based methods when applied to tabular data, often referred to as the last "unconquered castle" for neural networks. We hypothesize that a significant advantage of tree-based methods lies in their intrinsic capability to model and exploit non-linear interactions induced by features with categorical characteristics. In contrast, neural-based methods exhibit biases toward uniform numerical processing of features and smooth solutions, making it challenging for them to effectively leverage such patterns. We address this performance gap by using statistical-based feature processing techniques to identify features that are strongly correlated with the target once discretized. We further mitigate the bias of deep models for overly-smooth solutions, a bias that does not align with the inherent properties of the data, using Learned Fourier. We show that our proposed feature preprocessing significantly boosts the performance of deep learning models and enables them to achieve a performance that closely matches or surpasses XGBoost on a comprehensive tabular data benchmark. --- ### Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models Authors: Gal Pomerants, Yaniv Nikankin, Anja Reusch, Tomer Tsaban, Ora Schueler-Furman, Yonatan Belinkov Published: 2026-02-26 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2602.23179v5 Protein sequences are abundant in repeating segments, both as exact copies and as approximate segments with mutations. These repeats are important for protein structure and function, motivating decades of algorithmic work on repeat identification. Recent work has shown that protein language models (PLMs) identify repeats, by examining their behavior in masked-token prediction. To elucidate their internal mechanisms, we investigate how PLMs detect both exact and approximate repeats. We find that the mechanism for approximate repeats functionally subsumes that of exact repeats. We then characterize this mechanism, revealing two main stages: PLMs first build feature representations using both general positional attention heads and biologically specialized components, such as neurons that encode amino-acid similarity. Then, induction heads attend to aligned tokens across repeated segments, promoting the correct answer. Our results reveal how PLMs solve this biological task by combining language-based pattern matching with specialized biological knowledge, thereby establishing a basis for studying more complex evolutionary processes in PLMs. --- ### Phys-3D: Physics-Constrained Real-Time Crowd Tracking and Counting on Railway Platforms Authors: Bin Zeng, Johannes Künzel, Anna Hilsmann, Peter Eisert Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23177v1 Accurate, real-time crowd counting on railway platforms is essential for safety and capacity management. We propose to use a single camera mounted in a train, scanning the platform while arriving. While hardware constraints are simple, counting remains challenging due to dense occlusions, camera motion, and perspective distortions during train arrivals. Most existing tracking-by-detection approaches assume static cameras or ignore physical consistency in motion modeling, leading to unreliable counting under dynamic conditions. We propose a physics-constrained tracking framework that unifies detection, appearance, and 3D motion reasoning in a real-time pipeline. Our approach integrates a transfer-learned YOLOv11m detector with EfficientNet-B0 appearance encoding within DeepSORT, while introducing a physics-constrained Kalman model (Phys-3D) that enforces physically plausible 3D motion dynamics through pinhole geometry. To address counting brittleness under occlusions, we implement a virtual counting band with persistence. On our platform benchmark, MOT-RailwayPlatformCrowdHead Dataset(MOT-RPCH), our method reduces counting error to 2.97%, demonstrating robust performance despite motion and occlusions. Our results show that incorporating first-principles geometry and motion priors enables reliable crowd counting in safety-critical transportation scenarios, facilitating effective train scheduling and platform safety management. --- ### Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking Authors: Maximilian Luz, Rohit Mohan, Thomas Nürnberg, Yakov Miron, Daniele Cattaneo, Abhinav Valada Published: 2026-02-26 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2602.23172v2 Capturing 4D spatiotemporal scene structure is crucial for the safe and reliable operation of robots in dynamic environments. However, existing approaches typically address only part of the problem: they either provide coarse geometric tracking via bounding boxes or detailed 3D occupancy estimates that lack explicit temporal association and instance-level reasoning. In this work, we present Latent Gaussian Splatting (LaGS) for 4D Panoptic Occupancy Tracking (4D-POT). We revisit the underlying representation and model 3D features as a sparse set of feature-bearing Gaussians. These act as dynamic, volume-oriented keypoints that enable spatially continuous, distance-weighted aggregation of multi-view features before being splatted into a voxel grid for decoding. This point-centric formulation enables flexible, data-dependent receptive fields and long-range spatial interactions that are difficult to capture with local and dense voxel-based operators. A hierarchical Gaussian representation further enables multi-scale reasoning by combining global context from coarse super-points with fine-grained detail from higher-resolution streams. Extensive experiments on Occ3D nuScenes and Waymo demonstrate state-of-the-art performance for 4D-POT. We provide code and models at https://lags.cs.uni-freiburg.de/. --- ### Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration Authors: Xiaole Tang, Xiaoyi He, Jiayi Xu, Xiang Gu, Jian Sun Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23169v1 Despite substantial advances in all-in-one image restoration for addressing diverse degradations within a unified model, existing methods remain vulnerable to out-of-distribution degradations, thereby limiting their generalization in real-world scenarios. To tackle the challenge, this work is motivated by the intuition that multisource degraded feature distributions are induced by different degradation-specific shifts from an underlying degradation-agnostic distribution, and recovering such a shared distribution is thus crucial for achieving generalization across degradations. With this insight, we propose BaryIR, a representation learning framework that aligns multisource degraded features in the Wasserstein barycenter (WB) space, which models a degradation-agnostic distribution by minimizing the average of Wasserstein distances to multisource degraded distributions. We further introduce residual subspaces, whose embeddings are mutually contrasted while remaining orthogonal to the WB embeddings. Consequently, BaryIR explicitly decouples two orthogonal spaces: a WB space that encodes the degradation-agnostic invariant contents shared across degradations, and residual subspaces that adaptively preserve the degradation-specific knowledge. This disentanglement mitigates overfitting to in-distribution degradations and enables adaptive restoration grounded on the degradation-agnostic shared invariance. Extensive experiments demonstrate that BaryIR performs competitively against state-of-the-art all-in-one methods. Notably, BaryIR generalizes well to unseen degradations (\textit{e.g.,} types and levels) and shows remarkable robustness in learning generalized features, even when trained on limited degradation types and evaluated on real-world data with mixed degradations. --- ### SettleFL: Trustless and Scalable Reward Settlement Protocol for Federated Learning on Permissionless Blockchains (Extended version) Authors: Shuang Liang, Yang Hua, Linshan Jiang, Peishen Yan, Tao Song, Bin Yao, Haibing Guan Published: 2026-02-26 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.23167v1 In open Federated Learning (FL) environments where no central authority exists, ensuring collaboration fairness relies on decentralized reward settlement, yet the prohibitive cost of permissionless blockchains directly clashes with the high-frequency, iterative nature of model training. Existing solutions either compromise decentralization or suffer from scalability bottlenecks due to linear on-chain costs. To address this, we present SettleFL, a trustless and scalable reward settlement protocol designed to minimize total economic friction by offering a family of two interoperable protocols. Leveraging a shared domain-specific circuit architecture, SettleFL offers two interoperable strategies: (1) a Commit-and-Challenge variant that minimizes on-chain costs via optimistic execution and dispute-driven arbitration, and (2) a Commit-with-Proof variant that guarantees instant finality through per-round validity proofs. This design allows the protocol to flexibly adapt to varying latency and cost constraints while enforcing rational robustness without trusted coordination. We conduct extensive experiments combining real FL workloads and controlled simulations. Results show that SettleFL remains practical when scaling to 800 participants, achieving substantially lower gas cost. --- ### AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios Authors: Zhaochen Su, Jincheng Gao, Hangyu Guo, Zhenhua Liu, Lueyang Zhang, Xinyu Geng, Shijue Huang, Peng Xia, Guanyu Jiang, Cheng Wang, Yue Zhang, Yi R. Fung et al. Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23166v2 Real-world multimodal agents solve multi-step workflows grounded in visual evidence. For example, an agent can troubleshoot a device by linking a wiring photo to a schematic and validating the fix with online documentation, or plan a trip by interpreting a transit map and checking schedules under routing constraints. However, existing multimodal benchmarks mainly evaluate single-turn visual reasoning or specific tool skills, and they do not fully capture the realism, visual subtlety, and long-horizon tool use that practical agents require. We introduce AgentVista, a benchmark for generalist multimodal agents that spans 25 sub-domains across 7 categories, pairing realistic and detail-rich visual scenarios with natural hybrid tool use. Tasks require long-horizon tool interactions across modalities, including web search, image search, page navigation, and code-based operations for both image processing and general programming. Comprehensive evaluation of state-of-the-art models exposes significant gaps in their ability to carry out long-horizon multimodal tool use. Even the best model in our evaluation, Gemini-3-Pro with tools, achieves only 27.3% overall accuracy, and hard instances can require more than 25 tool-calling turns. We expect AgentVista to accelerate the development of more capable and reliable multimodal agents for realistic and ultra-challenging problem solving. --- ### DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation Authors: Yichen Peng, Jyun-Ting Song, Siyeol Jung, Ruofan Liu, Haiyang Liu, Xuangeng Chu, Ruicong Liu, Erwin Wu, Hideki Koike, Kris Kitani Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23165v2 Generating realistic conversational gestures are essential for achieving natural, socially engaging interactions with digital humans. However, existing methods typically map a single audio stream to a single speaker's motion, without considering social context or modeling the mutual dynamics between two people engaging in conversation. We present DyaDiT, a multi-modal diffusion transformer that generates contextually appropriate human motion from dyadic audio signals. Trained on Seamless Interaction Dataset, DyaDiT takes dyadic audio with optional social-context tokens to produce context-appropriate motion. It fuses information from both speakers to capture interaction dynamics, uses a motion dictionary to encode motion priors, and can optionally utilize the conversational partner's gestures to produce more responsive motion. We evaluate DyaDiT on standard motion generation metrics and conduct quantitative user studies, demonstrating that it not only surpasses existing methods on objective metrics but is also strongly preferred by users, highlighting its robustness and socially favorable motion generation. Code and models will be released upon acceptance. --- ### MetaOthello: A Controlled Study of Multiple World Models in Transformers Authors: Aviral Chawla, Galen Hall, Juniper Lovato Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.23164v2 Foundation models must handle multiple generative processes, yet mechanistic interpretability largely studies capabilities in isolation; it remains unclear how a single transformer organizes multiple, potentially conflicting "world models". Previous experiments on Othello playing neural-networks test world-model learning but focus on a single game with a single set of rules. We introduce MetaOthello, a controlled suite of Othello variants with shared syntax but different rules or tokenizations, and train small GPTs on mixed-variant data to study how multiple world models are organized in a shared representation space. We find that transformers trained on mixed-game data do not partition their capacity into isolated sub-models; instead, they converge on a mostly shared board-state representation that transfers causally across variants. Linear probes trained on one variant can intervene on another's internal state with effectiveness approaching that of matched probes. For isomorphic games with token remapping, representations are equivalent up to a single orthogonal rotation that generalizes across layers. When rules partially overlap, early layers maintain game-agnostic representations while a middle layer identifies game identity, and later layers specialize. MetaOthello offers a path toward understanding not just whether transformers learn world models, but how they organize many at once. --- ### A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring Authors: Usman Anwar, Julianna Piskorz, David D. Baek, David Africa, Jim Weatherall, Max Tegmark, Christian Schroeder de Witt, Mihaela van der Schaar, David Krueger Published: 2026-02-26 Categories: cs.AI, cs.CL, cs.CR, cs.IT, cs.MA arXiv: https://arxiv.org/abs/2602.23163v3 Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to detect and quantify such behaviours are lacking. Classical definitions of steganography, and detection methods based on them, require a known reference distribution of non-steganographic signals. For the case of steganographic reasoning in LLMs, knowing such a reference distribution is not feasible; this renders these approaches inapplicable. We propose an alternative, \textbf{decision-theoretic view of steganography}. Our central insight is that steganography creates an asymmetry in usable information between agents who can and cannot decode the hidden content (present within a steganographic signal), and this otherwise latent asymmetry can be inferred from the agents' observable actions. To formalise this perspective, we introduce generalised $\mathcal{V}$-information: a utilitarian framework for measuring the amount of usable information within some input. We use this to define the \textbf{steganographic gap} -- a measure that quantifies steganography by comparing the downstream utility of the steganographic signal to agents that can and cannot decode the hidden content. We empirically validate our formalism, and show that it can be used to detect, quantify, and mitigate steganographic reasoning in LLMs. --- ### PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering Authors: Junkai Lu, Peng Chen, Xingjian Wu, Yang Shu, Chenjuan Guo, Christian S. Jensen, Bin Yang Published: 2026-02-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.23161v4 Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitations: they often treat time series merely as text or images, failing to capture the patterns like trends and seasonalities needed to answer specific questions; and when trained on a mix of simple and complex tasks, simpler objectives often dominate the learning process, hindering the development of deep reasoning capabilities. To address these limitations, we propose the Pattern-Aware Alignment and Balanced Reasoning model (PATRA), introducing a pattern-aware mechanism that extracts trend and seasonality patterns from time series to achieve deep alignment. Furthermore, we design a task-aware balanced reward to harmonize learning across tasks of varying difficulty, incentivizing the generation of coherent Chains of Thought. Extensive experiments show that PATRA outperforms strong baselines across diverse Time Series Question Answering (TSQA) tasks, demonstrating superior cross-modal understanding and reasoning capability. --- ### Benchmarking Temporal Web3 Intelligence: Lessons from the FinSurvival 2025 Challenge Authors: Oshani Seneviratne, Fernando Spadea, Adrien Pavao, Aaron Micah Green, Kristin P. Bennett Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.23159v1 Temporal Web analytics increasingly relies on large-scale, longitudinal data to understand how users, content, and systems evolve over time. A rapidly growing frontier is the \emph{Temporal Web3}: decentralized platforms whose behavior is recorded as immutable, time-stamped event streams. Despite the richness of this data, the field lacks shared, reproducible benchmarks that capture real-world temporal dynamics, specifically censoring and non-stationarity, across extended horizons. This absence slows methodological progress and limits the transfer of techniques between Web3 and broader Web domains. In this paper, we present the \textit{FinSurvival Challenge 2025} as a case study in benchmarking \emph{temporal Web3 intelligence}. Using 21.8 million transaction records from the Aave v3 protocol, the challenge operationalized 16 survival prediction tasks to model user behavior transitions.We detail the benchmark design and the winning solutions, highlighting how domain-aware temporal feature construction significantly outperformed generic modeling approaches. Furthermore, we distill lessons for next-generation temporal benchmarks, arguing that Web3 systems provide a high-fidelity sandbox for studying temporal challenges, such as churn, risk, and evolution that are fundamental to the wider Web. --- ### Efficient Encoder-Free Fourier-based 3D Large Multimodal Model Authors: Guofeng Mei, Wei Lin, Luigi Riz, Yujiao Wu, Yiming Wang, Fabio Poiesi Published: 2026-02-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.23153v2 Large Multimodal Models (LMMs) that process 3D data typically rely on heavy, pre-trained visual encoders to extract geometric features. While recent 2D LMMs have begun to eliminate such encoders for efficiency and scalability, extending this paradigm to 3D remains challenging due to the unordered and large-scale nature of point clouds. This leaves a critical unanswered question: How can we design an LMM that tokenizes unordered 3D data effectively and efficiently without a cumbersome encoder? We propose Fase3D, the first efficient encoder-free Fourier-based 3D scene LMM. Fase3D tackles the challenges of scalability and permutation invariance with a novel tokenizer that combines point cloud serialization and the Fast Fourier Transform (FFT) to approximate self-attention. This design enables an effective and computationally minimal architecture, built upon three key innovations: First, we represent large scenes compactly via structured superpoints. Second, our space-filling curve serialization followed by an FFT enables efficient global context modeling and graph-based token merging. Lastly, our Fourier-augmented LoRA adapters inject global frequency-aware interactions into the LLMs at a negligible cost. Fase3D achieves performance comparable to encoder-based 3D LMMs while being significantly more efficient in computation and parameters. Project website: https://tev-fbk.github.io/Fase3D. --- ### The Trinity of Consistency as a Defining Principle for General World Models Authors: Jingxuan Wei, Siyuan Li, Yuhang Xu, Zheng Sun, Junjie Jiang, Hexuan Jin, Caijun Jia, Honghao He, Xinglong Xu, Xi bai, Chang Yu, Yumou Liu et al. Published: 2026-02-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.23152v1 The construction of World Models capable of learning, simulating, and reasoning about objective physical laws constitutes a foundational challenge in the pursuit of Artificial General Intelligence. Recent advancements represented by video generation models like Sora have demonstrated the potential of data-driven scaling laws to approximate physical dynamics, while the emerging Unified Multimodal Model (UMM) offers a promising architectural paradigm for integrating perception, language, and reasoning. Despite these advances, the field still lacks a principled theoretical framework that defines the essential properties requisite for a General World Model. In this paper, we propose that a World Model must be grounded in the Trinity of Consistency: Modal Consistency as the semantic interface, Spatial Consistency as the geometric basis, and Temporal Consistency as the causal engine. Through this tripartite lens, we systematically review the evolution of multimodal learning, revealing a trajectory from loosely coupled specialized modules toward unified architectures that enable the synergistic emergence of internal world simulators. To complement this conceptual framework, we introduce CoW-Bench, a benchmark centered on multi-frame reasoning and generation scenarios. CoW-Bench evaluates both video generation models and UMMs under a unified evaluation protocol. Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress. --- ### On Sample-Efficient Generalized Planning via Learned Transition Models Authors: Nitin Gupta, Vishal Pallagani, John A. Aydin, Biplav Srivastava Published: 2026-02-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.23148v3 Generalized planning studies the construction of solution strategies that generalize across families of planning problems sharing a common domain model, formally defined by a transition function $γ: S \times A \rightarrow S$. Classical approaches achieve such generalization through symbolic abstractions and explicit reasoning over $γ$. In contrast, recent Transformer-based planners, such as PlanGPT and Plansformer, largely cast generalized planning as direct action-sequence prediction, bypassing explicit transition modeling. While effective on in-distribution instances, these approaches typically require large datasets and model sizes, and often suffer from state drift in long-horizon settings due to the absence of explicit world-state evolution. In this work, we formulate generalized planning as a transition-model learning problem, in which a neural model explicitly approximates the successor-state function $\hatγ \approx γ$ and generates plans by rolling out symbolic state trajectories. Instead of predicting actions directly, the model autoregressively predicts intermediate world states, thereby learning the domain dynamics as an implicit world model. To study size-invariant generalization and sample efficiency, we systematically evaluate multiple state representations and neural architectures, including relational graph encodings. Our results show that learning explicit transition models yields higher out-of-distribution satisficing-plan success than direct action-sequence prediction in multiple domains, while achieving these gains with significantly fewer training instances and smaller models. This is an extended version of a short paper accepted at ICAPS 2026 under the same title. --- ### Partial recovery of meter-scale surface weather Authors: Jonathan Giezendanner, Qidong Yang, Ruizhe Huang, Eric Schmitt, Anirban Chandra, Yawen Zhang, Jeremy Vila, Detlef Hohl, Campbell Watson, Sherrie Wang Published: 2026-02-26 Categories: cs.LG, cs.CV, physics.ao-ph arXiv: https://arxiv.org/abs/2602.23146v2 Near-surface weather varies over tens to hundreds of meters, yet remains unresolved in analyses and forecasts. We test whether this variation can be inferred without resolving atmospheric dynamics. Combining sparse weather stations, high-resolution Earth observation, and coarse atmospheric dynamics, we infer temperature, dewpoint, and wind at 30-m resolution across the contiguous United States. Against measurements held out in space and time, estimates reduce error by 11-28\% relative to the strongest baseline. Within held-out $0.25^\circ$ grid cells, we recover more spatial variance than baselines, explaining nearly half of temperature variability in the median cell. The method captures time-varying differences between locations and produces coherent patterns associated with topography and land cover. Beyond weather, our findings illustrate how sparse observations of a dynamical system can be combined with dense observations of persistent environmental structure to recover otherwise unresolved spatial variability. --- ### Partial recovery of meter-scale surface weather Authors: Jonathan Giezendanner, Qidong Yang, Eric Schmitt, Anirban Chandra, Daniel Salles Civitarese, Johannes Jakubik, Jeremy Vila, Detlef Hohl, Campbell Watson, Sherrie Wang Published: 2026-02-26 Categories: cs.LG, cs.CV, physics.ao-ph arXiv: https://arxiv.org/abs/2602.23146v1 Near-surface atmospheric conditions can differ sharply over tens to hundreds of meters due to land cover and topography, yet this variability is absent from current weather analyses and forecasts. It is unclear whether such meter-scale variability reflects irreducibly chaotic dynamics or contains a component predictable from surface characteristics and large-scale atmospheric forcing. Here we show that a substantial, physically coherent component of meter-scale near-surface weather is statistically recoverable from existing observations. By conditioning coarse atmospheric state on sparse surface station measurements and high-resolution Earth observation data, we infer spatially continuous fields of near-surface wind, temperature, and humidity at 10 m resolution across the contiguous United States. Relative to ERA5, the inferred fields reduce wind error by 29% and temperature and dewpoint error by 6%, while explaining substantially more spatial variance at fixed time steps. They also exhibit physically interpretable structure, including urban heat islands, evapotranspiration-driven humidity contrasts, and wind speed differences across land cover types. Our findings expand the frontier of weather modeling by demonstrating a computationally feasible approach to continental-scale meter-resolution inference. More broadly, they illustrate how conditioning coarse dynamical models on static fine-scale features can reveal previously unresolved components of the Earth system. --- ### Prediction of Diffusion Coefficients in Mixtures with Tensor Completion Authors: Zeno Romero, Kerstin Münnemann, Hans Hasse, Fabian Jirasek Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.23142v1 Predicting diffusion coefficients in mixtures is crucial for many applications, as experimental data remain scarce, and machine learning (ML) offers promising alternatives to established semi-empirical models. Among ML models, matrix completion methods (MCMs) have proven effective in predicting thermophysical properties, including diffusion coefficients in binary mixtures. However, MCMs are restricted to single-temperature predictions, and their accuracy depends strongly on the availability of high-quality experimental data for each temperature of interest. In this work, we address this challenge by presenting a hybrid tensor completion method (TCM) for predicting temperature-dependent diffusion coefficients at infinite dilution in binary mixtures. The TCM employs a Tucker decomposition and is jointly trained on experimental data for diffusion coefficients at infinite dilution in binary systems at 298 K, 313 K, and 333 K. Predictions from the semi-empirical SEGWE model serve as prior knowledge within a Bayesian training framework. The TCM then extrapolates linearly to any temperature between 268 K and 378 K, achieving markedly improved prediction accuracy compared to established models across all studied temperatures. To further enhance predictive performance, the experimental database was expanded using active learning (AL) strategies for targeted acquisition of new diffusion data by pulsed-field gradient (PFG) NMR measurements. Diffusion coefficients at infinite dilution in 19 solute + solvent systems were measured at 298 K, 313 K, and 333 K. Incorporating these results yields a substantial improvement in the TCM's predictive accuracy. These findings highlight the potential of combining data-efficient ML methods with adaptive experimentation to advance predictive modeling of transport properties. --- ### No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors Authors: Tao Liu, Gang Wan, Kan Ren, Shibo Wen Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23141v1 We propose a new unsupervised framework for online video stabilization. Unlike methods based on deep learning that require paired stable and unstable datasets, our approach instantiates the classical stabilization pipeline with three stages and incorporates a multithreaded buffering mechanism. This design addresses three longstanding challenges in end-to-end learning: limited data, poor controllability, and inefficiency on hardware with constrained resources. Existing benchmarks focus mainly on handheld videos with a forward view in visible light, which restricts the applicability of stabilization to domains such as UAV nighttime remote sensing. To fill this gap, we introduce a new multimodal UAV aerial video dataset (UAV-Test). Experiments show that our method consistently outperforms state-of-the-art online stabilizers in both quantitative metrics and visual quality, while achieving performance comparable to offline methods. --- ### Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs Authors: Jayadev Billa Published: 2026-02-26 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.23136v2 Numerous studies have shown that multimodal LLMs process speech and images well but fail in non-intuitive ways rendering trivial tasks such as object counting unreliable. We investigate this behavior from an information-theoretic perspective by framing multimodal LLM inference as a mismatched decoder problem: a decoder trained primarily on text can only extract information along text-aligned directions (removing up to 98% of the variation in modality-specific (non-text) directions improves decoder loss) and the amount of accessible information is bounded by the Generalized Mutual Information (GMI). We show that information loss is bounded as the distributional mismatch between the source data and the text data increases, and as the sensitivity of the decoder increases. This bound is a function of the model's scoring rule not its architecture. We validate the predictions across five models spanning speech and vision. A controlled study (two Prismatic VLMs differing only in encoder text-alignment) shows that the bottleneck lies in the scoring rule of the decoder rather than the text-alignment of the encoder or the learned projection. A LoRA intervention demonstrates that simply training with an emotion-related objective improves emotion detection from 17.3% to 61.8% task accuracy without affecting other attributes, confirming that the training objective determines what becomes accessible. --- ### DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs Authors: Tyler Bonnet, Marek Rei Published: 2026-02-26 Categories: cs.LG, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2602.23135v2 Edge classification on directed dynamic graphs requires modeling interactions between source and destination nodes exhibiting asymmetrical behavioral patterns and temporal dynamics. However, existing dynamic graph architectures largely rely on shared parameters for processing source and destination nodes, with limited or no systematic role-aware modeling. We propose DyGnROLE (Dynamic Graph Node-Role-Oriented Latent Encoding), a Transformer-based architecture that disentangles source and destination representations. By using separate embedding tables and role-semantic positional encodings, the model captures the distinct structural and temporal contexts unique to each role. Critical in limited-label settings, which are common in edge classification, is a self-supervised pretraining objective we introduce: Directional Role Alignment (DRA). DRA learns distinct but aligned source and destination embedding spaces by training source representations to retrieve their corresponding destination representations while a historical positive masking strategy excludes previously observed interactions from future negative comparisons. The masks introduce a temporally directional training signal in which node pairs progress monotonically from unseen to observed, after which the relationship is eligible only for further alignment. A comprehensive evaluation on four edge classification tasks across eight datasets demonstrates that DyGnROLE consistently outperforms a wide range of state-of-the-art baselines, highlighting the importance of role-aware representation learning and asymmetric pretraining for modeling complex directed interactions when labeled data is limited. --- ### From Calibration to Refinement: Seeking Certainty via Probabilistic Evidence Propagation for Noisy-Label Person Re-Identification Authors: Xin Yuan, Zhiyong Zhang, Xin Xu, Zheng Wang, Chia-Wen Lin Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23133v1 With the increasing demand for robust person Re-ID in unconstrained environments, learning from datasets with noisy labels and sparse per-identity samples remains a critical challenge. Existing noise-robust person Re-ID methods primarily rely on loss-correction or sample-selection strategies using softmax outputs. However, these methods suffer from two key limitations: 1) Softmax exhibits translation invariance, leading to over-confident and unreliable predictions on corrupted labels. 2) Conventional sample selection based on small-loss criteria often discards valuable hard positives that are crucial for learning discriminative features. To overcome these issues, we propose the CAlibration-to-REfinement (CARE) method, a two-stage framework that seeks certainty through probabilistic evidence propagation from calibration to refinement. In the calibration stage, we propose the probabilistic evidence calibration (PEC) that dismantles softmax translation invariance by injecting adaptive learnable parameters into the similarity function, and employs an evidential calibration loss to mitigate overconfidence on mislabeled samples. In the refinement stage, we design the evidence propagation refinement (EPR) that can more accurately distinguish between clean and noisy samples. Specifically, the EPR contains two steps: Firstly, the composite angular margin (CAM) metric is proposed to precisely distinguish clean but hard-to-learn positive samples from mislabeled ones in a hyperspherical space; Secondly, the certainty-oriented sphere weighting (COSW) is developed to dynamically allocate the importance of samples according to CAM, ensuring clean instances drive model updates. Extensive experimental results on Market1501, DukeMTMC-ReID, and CUHK03 datasets under both random and patterned noises show that CARE achieves competitive performance. --- ### From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential Recommendation Authors: Ruochen Yang, Xiaodong Li, Jiawei Sheng, Jiangxia Cao, Xinkui Lin, Shen Wang, Shuang Yang, Zhaojie Liu, Tingwen Liu Published: 2026-02-26 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.23132v1 Multi-behavior sequential recommendation (MBSR) aims to learn the dynamic and heterogeneous interactions of users' multi-behavior sequences, so as to capture user preferences under target behavior for the next interacted item prediction. Unlike previous methods that adopt unidirectional modeling by mapping auxiliary behaviors to target behavior, recent concerns are shifting from behavior-fixed to behavior-specific recommendation. However, these methods still ignore the user's latent preference that underlying decision-making, leading to suboptimal solutions. Meanwhile, due to the asymmetric deterministic between items and behaviors, discriminative paradigm based on preference scoring is unsuitable to capture the uncertainty from low-entropy behaviors to high-entropy items, failing to provide efficient and diverse recommendation. To address these challenges, we propose \textbf{FatsMB}, a framework based diffusion model that guides preference generation \textit{\textbf{F}rom Behavior-\textbf{A}gnostic \textbf{T}o Behavior-\textbf{S}pecific} in latent spaces, enabling diverse and accurate \textit{\textbf{M}ulti-\textbf{B}ehavior Sequential Recommendation}. Specifically, we design a Multi-Behavior AutoEncoder (MBAE) to construct a unified user latent preference space, facilitating interaction and collaboration across Behaviors, within Behavior-aware RoPE (BaRoPE) employed for multiple information fusion. Subsequently, we conduct target behavior-specific preference transfer in the latent space, enriching with informative priors. A Multi-Condition Guided Layer Normalization (MCGLN) is introduced for the denoising. Extensive experiments on real-world datasets demonstrate the effectiveness of our model. --- ### Bound to Disagree: Generalization Bounds via Certifiable Surrogates Authors: Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.23128v2 Generalization bounds for deep learning models are typically vacuous, not computable or restricted to specific model classes. In this paper, we tackle these issues by providing new disagreement-based certificates for the gap between the true risk of any two predictors. We then bound the true risk of the predictor of interest via a surrogate model that enjoys tight generalization guarantees, and by evaluating our disagreement bound on an unlabeled dataset.We empirically demonstrate the tightness of the obtained certificates and showcase the versatility of the approach by training surrogate models leveraging three different frameworks: sample compression, model compression and PAC-Bayes theory. Importantly, such guarantees are achieved without modifying the target model, nor adapting the training procedure to the generalization framework. --- ### Multi-Agent Large Language Model Based Emotional Detoxification Through Personalized Intensity Control for Consumer Protection Authors: Keito Inoshita Published: 2026-02-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.23123v1 In the attention economy, sensational content exposes consumers to excessive emotional stimulation, hindering calm decision-making. This study proposes Multi-Agent LLM-based Emotional deToxification (MALLET), a multi-agent information sanitization system consisting of four agents: Emotion Analysis, Emotion Adjustment, Balance Monitoring, and Personal Guide. The Emotion Analysis Agent quantifies stimulus intensity using a 6-emotion BERT classifier, and the Emotion Adjustment Agent rewrites texts into two presentation modes, BALANCED (neutralized text) and COOL (neutralized text + supplementary text), using an LLM. The Balance Monitoring Agent aggregates weekly information consumption patterns and generates personalized advice, while the Personal Guide Agent recommends a presentation mode according to consumer sensitivity. Experiments on 800 AG News articles demonstrated significant stimulus score reduction (up to 19.3%) and improved emotion balance while maintaining semantic preservation. Near-zero correlation between stimulus reduction and semantic preservation confirmed that the two are independently controllable. Category-level analysis revealed substantial reduction (17.8-33.8%) in Sports, Business, and Sci/Tech, whereas the effect was limited in the World category, where facts themselves are inherently high-stimulus. The proposed system provides a framework for supporting calm information reception of consumers without restricting access to the original text. --- ### Automated Vulnerability Detection in Source Code Using Deep Representation Learning Authors: C. Seas, G. Fitzpatrick, J. A. Hamilton, M. C. Carlisle Published: 2026-02-26 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.23121v1 Each year, software vulnerabilities are discovered, which pose significant risks of exploitation and system compromise. We present a convolutional neural network model that can successfully identify bugs in C code. We trained our model using two complementary datasets: a machine-labeled dataset created by Draper Labs using three static analyzers and the NIST SATE Juliet human-labeled dataset designed for testing static analyzers. In contrast with the work of Russell et al. on these datasets, we focus on C programs, enabling us to specialize and optimize our detection techniques for this language. After removing duplicates from the dataset, we tokenize the input into 91 token categories. The category values are converted to a binary vector to save memory. Our first convolution layer is chosen so that the entire encoding of the token is presented to the filter. We use two convolution and pooling layers followed by two fully connected layers to classify programs into either a common weakness enumeration category or as ``clean.'' We obtain higher recall than prior work by Russell et al. on this dataset when requiring high precision. We also demonstrate on a custom Linux kernel dataset that we are able to find real vulnerabilities in complex code with a low false-positive rate. --- ### TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement Authors: Arian Sabaghi, José Oramas Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23120v1 Weakly supervised object localization (WSOL) aims to localize target objects in images using only image-level labels. Despite recent progress, many approaches still rely on multi-stage pipelines or full fine-tuning of large backbones, which increases training cost, while the broader WSOL community continues to face the challenge of partial object coverage. We present TriLite, a single-stage WSOL framework that leverages a frozen Vision Transformer with Dinov2 pre-training in a self-supervised manner, and introduces only a minimal number of trainable parameters (fewer than 800K on ImageNet-1K) for both classification and localization. At its core is the proposed TriHead module, which decomposes patch features into foreground, background, and ambiguous regions, thereby improving object coverage while suppressing spurious activations. By disentangling classification and localization objectives, TriLite effectively exploits the universal representations learned by self-supervised ViTs without requiring expensive end-to-end training. Extensive experiments on CUB-200-2011, ImageNet-1K, and OpenImages demonstrate that TriLite sets a new state of the art, while remaining significantly more parameter-efficient and easier to train than prior methods. The code will be released soon. --- ### Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation Authors: Xiaosen Wang, Zhijin Ge, Bohan Liu, Zheng Fang, Fengfan Zhou, Ruixuan Zhang, Shaokang Wang, Yuyang Luo Published: 2026-02-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.23117v1 Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an attack, thereby raising considerable security concerns in practical applications and attracting substantial research attention recently. In this work, we discern a lack of a standardized framework and criteria for evaluating transfer-based attacks, leading to potentially biased assessments of existing approaches. To rectify this gap, we have conducted an exhaustive review of hundreds of related works, organizing various transfer-based attacks into six distinct categories. Subsequently, we propose a comprehensive framework designed to serve as a benchmark for evaluating these attacks. In addition, we delineate common strategies that enhance adversarial transferability and highlight prevalent issues that could lead to unfair comparisons. Finally, we provide a brief review of transfer-based attacks beyond image classification. ---