# Research Papers — 2026-02 · bundle page 61 of 210 > Full-text markdown of papers #3001–3050 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/61 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/60.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/62.md) ### VQPP: Video Query Performance Prediction Benchmark Authors: Adrian Catalin Lutu, Eduard Poesina, Radu Tudor Ionescu Published: 2026-02-19 Categories: cs.CV, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.17814v1 Query performance prediction (QPP) is an important and actively studied information retrieval task, having various applications, such as query reformulation, query expansion, and retrieval system selection, among many others. The task has been primarily studied in the context of text and image retrieval, whereas QPP for content-based video retrieval (CBVR) remains largely underexplored. To this end, we propose the first benchmark for video query performance prediction (VQPP), comprising two text-to-video retrieval datasets and two CBVR systems, respectively. VQPP contains a total of 56K text queries and 51K videos, and comes with official training, validation and test splits, fostering direct comparisons and reproducible results. We explore multiple pre-retrieval and post-retrieval performance predictors, creating a representative benchmark for future exploration of QPP in the video domain. Our results show that pre-retrieval predictors obtain competitive performance, enabling applications before performing the retrieval step. We also demonstrate the applicability of VQPP by employing the best performing pre-retrieval predictor as reward model for training a large language model (LLM) on the query reformulation task via direct preference optimization (DPO). We release our benchmark and code at https://github.com/AdrianLutu/VQPP. --- ### Promptable segmentation with region exploration enables minimal-effort expert-level prostate cancer delineation Authors: Junqing Yang, Natasha Thorley, Ahmed Nadeem Abbasi, Shonit Punwani, Zion Tse, Yipeng Hu, Shaheer U. Saeed Published: 2026-02-19 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.17813v1 Purpose: Accurate segmentation of prostate cancer on magnetic resonance (MR) images is crucial for planning image-guided interventions such as targeted biopsies, cryoablation, and radiotherapy. However, subtle and variable tumour appearances, differences in imaging protocols, and limited expert availability make consistent interpretation difficult. While automated methods aim to address this, they rely on large expertly-annotated datasets that are often inconsistent, whereas manual delineation remains labour-intensive. This work aims to bridge the gap between automated and manual segmentation through a framework driven by user-provided point prompts, enabling accurate segmentation with minimal annotation effort. Methods: The framework combines reinforcement learning (RL) with a region-growing segmentation process guided by user prompts. Starting from an initial point prompt, region-growing generates a preliminary segmentation, which is iteratively refined through RL. At each step, the RL agent observes the image and current segmentation to predict a new point, from which region growing updates the mask. A reward, balancing segmentation accuracy and voxel-wise uncertainty, encourages exploration of ambiguous regions, allowing the agent to escape local optima and perform sample-specific optimisation. Despite requiring fully supervised training, the framework bridges manual and fully automated segmentation at inference by substantially reducing user effort while outperforming current fully automated methods. Results: The framework was evaluated on two public prostate MR datasets (PROMIS and PICAI, with 566 and 1090 cases). It outperformed the previous best automated methods by 9.9% and 8.9%, respectively, with performance comparable to manual radiologist segmentation, reducing annotation time tenfold. --- ### Calibrated Adaptation: Bayesian Stiefel Manifold Priors for Reliable Parameter-Efficient Fine-Tuning Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17809v1 Parameter-efficient fine-tuning methods such as LoRA enable practical adaptation of large language models but provide no principled uncertainty estimates, leading to poorly calibrated predictions and unreliable behavior under domain shift. We introduce Stiefel-Bayes Adapters (SBA), a Bayesian PEFT framework that places a Matrix Langevin prior over orthonormal adapter factors on the Stiefel manifold $\St$ and performs approximate posterior inference via tangent space Laplace approximation with geodesic retraction. Unlike Gaussian priors in flat space projected onto orthogonality constraints, our prior on the manifold naturally encodes the inductive bias that adapter subspaces should be well conditioned and orthogonal, while the posterior provides calibrated predictive uncertainty without recalibration. We prove formally that the tangent space approximation strictly avoids the structural variance inflation inherent in projecting from ambient space, establishing a rigorous theoretical advantage for intrinsic manifold inference. Across GLUE and SuperGLUE benchmarks on RoBERTa-large, LLaMA-2-7B, LLaMA-2-13B, Mistral-7B, and Qwen2.5-7B, domain shift evaluations, selective prediction protocols, and an abstractive summarization task, SBA achieves task performance comparable to LoRA and DoRA while reducing Expected Calibration Error by 18 to 34\% over deterministic baselines, improving selective prediction AUROC by 12 to 25\% under domain shift, and outperforming deep ensembles of five LoRA models on OOD detection at a fraction of the parameter cost. Our results demonstrate that where you place uncertainty, on the right geometric structure, matters more than simply adding any Bayesian treatment to adapters. --- ### VidEoMT: Your ViT is Secretly Also a Video Segmentation Model Authors: Narges Norouzi, Idil Esen Zulfikar, Niccolò Cavagnero, Tommie Kerssies, Bastian Leibe, Gijs Dubbelman, Daan de Geus Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17807v3 Existing online video segmentation models typically combine a per-frame segmenter with complex specialized tracking modules. While effective, these modules introduce significant architectural complexity and computational overhead. Recent studies suggest that plain Vision Transformer (ViT) encoders, when scaled with sufficient capacity and large-scale pre-training, can conduct accurate image segmentation without requiring specialized modules. Motivated by this observation, we propose the Video Encoder-only Mask Transformer (VidEoMT), a simple encoder-only video segmentation model that eliminates the need for dedicated tracking modules. To enable temporal modeling in an encoder-only ViT, VidEoMT introduces a lightweight query propagation mechanism that carries information across frames by reusing queries from the previous frame. To balance this with adaptability to new content, it employs a query fusion strategy that combines the propagated queries with a set of temporally-agnostic learned queries. As a result, VidEoMT attains the benefits of a tracker without added complexity, achieving competitive accuracy while being 5x-10x faster, running at up to 160 FPS with a ViT-L backbone. Code: https://www.tue-mps.org/videomt/ --- ### Enabling Training-Free Text-Based Remote Sensing Segmentation Authors: Jose Sosa, Danila Rukhovich, Anis Kacem, Djamila Aouada Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17799v1 Recent advances in Vision Language Models (VLMs) and Vision Foundation Models (VFMs) have opened new opportunities for zero-shot text-guided segmentation of remote sensing imagery. However, most existing approaches still rely on additional trainable components, limiting their generalisation and practical applicability. In this work, we investigate to what extent text-based remote sensing segmentation can be achieved without additional training, by relying solely on existing foundation models. We propose a simple yet effective approach that integrates contrastive and generative VLMs with the Segment Anything Model (SAM), enabling a fully training-free or lightweight LoRA-tuned pipeline. Our contrastive approach employs CLIP as mask selector for SAM's grid-based proposals, achieving state-of-the-art open-vocabulary semantic segmentation (OVSS) in a completely zero-shot setting. In parallel, our generative approach enables reasoning and referring segmentation by generating click prompts for SAM using GPT-5 in a zero-shot setting and a LoRA-tuned Qwen-VL model, with the latter yielding the best results. Extensive experiments across 19 remote sensing benchmarks, including open-vocabulary, referring, and reasoning-based tasks, demonstrate the strong capabilities of our approach. Code will be released at https://github.com/josesosajs/trainfree-rs-segmentation. --- ### Grassmannian Mixture-of-Experts: Concentration-Controlled Routing on Subspace Manifolds Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17798v1 Mixture-of-Experts models rely on learned routers to assign tokens to experts, yet standard softmax gating provides no principled mechanism to control the tradeoff between sparsity and utilization. We propose Grassmannian MoE (GrMoE), a routing framework that operates on the Grassmannian manifold of subspaces, where gating weights arise from the concentration parameters of Matrix Bingham distributions. This construction yields a single, interpretable knob -- the concentration matrix $Λ$ -- that continuously controls routing entropy, replacing discrete top-$k$ selection with a smooth, geometrically principled sparsity mechanism. We further develop an amortized variational inference procedure for posterior routing distributions, enabling uncertainty-aware expert assignment that naturally resists expert collapse. We formally prove tight bounds relating the Bingham concentration spectrum to routing entropy, expected top-$k$ mass, and an exponential bound on expert collapse, establishing the first formal theory of concentration-controlled sparsity. On synthetic routing tasks, a 350M-parameter MoE language model with 8 experts, a 1.3B-parameter model with 16 experts, and a 2.7B-parameter model with 32 experts, GrMoE achieves 0\% routing collapse across all seeds, comparable or better perplexity with 15--30\% improved load balance, and a smooth monotonic relationship between concentration and effective sparsity that enables post-hoc sparsity tuning without retraining. Token-level analysis reveals that experts learn heterogeneous concentration values that correlate with linguistic specialization, providing interpretable routing behavior. --- ### Deep Learning for Dermatology: An Innovative Framework for Approaching Precise Skin Cancer Detection Authors: Mohammad Tahmid Noor, B. M. Shahria Alam, Tasmiah Rahman Orpa, Shaila Afroz Anika, Mahjabin Tasnim Samiha, Fahad Ahammed Published: 2026-02-19 Categories: eess.IV, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.17797v1 Skin cancer can be life-threatening if not diagnosed early, a prevalent yet preventable disease. Globally, skin cancer is perceived among the finest prevailing cancers and millions of people are diagnosed each year. For the allotment of benign and malignant skin spots, an area of critical importance in dermatological diagnostics, the application of two prominent deep learning models, VGG16 and DenseNet201 are investigated by this paper. We evaluate these CNN architectures for their efficacy in differentiating benign from malignant skin lesions leveraging enhancements in deep learning enforced to skin cancer spotting. Our objective is to assess model accuracy and computational efficiency, offering insights into how these models could assist in early detection, diagnosis, and streamlined workflows in dermatology. We used two deep learning methods DenseNet201 and VGG16 model on a binary class dataset containing 3297 images. The best result with an accuracy of 93.79% achieved by DenseNet201. All images were resized to 224x224 by rescaling. Although both models provide excellent accuracy, there is still some room for improvement. In future using new datasets, we tend to improve our work by achieving great accuracy. --- ### LGD-Net: Latent-Guided Dual-Stream Network for HER2 Scoring with Task-Specific Domain Knowledge Authors: Peide Zhu, Linbin Lu, Zhiqin Chen, Xiong Chen Published: 2026-02-19 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2602.17793v1 It is a critical task to evalaute HER2 expression level accurately for breast cancer evaluation and targeted treatment therapy selection. However, the standard multi-step Immunohistochemistry (IHC) staining is resource-intensive, expensive, and time-consuming, which is also often unavailable in many areas. Consequently, predicting HER2 levels directly from H&E slides has emerged as a potential alternative solution. It has been shown to be effective to use virtual IHC images from H&E images for automatic HER2 scoring. However, the pixel-level virtual staining methods are computationally expensive and prone to reconstruction artifacts that can propagate diagnostic errors. To address these limitations, we propose the Latent-Guided Dual-Stream Network (LGD-Net), a novel framework that employes cross-modal feature hallucination instead of explicit pixel-level image generation. LGD-Net learns to map morphological H&E features directly to the molecular latent space, guided by a teacher IHC encoder during training. To ensure the hallucinated features capture clinically relevant phenotypes, we explicitly regularize the model training with task-specific domain knowledge, specifically nuclei distribution and membrane staining intensity, via lightweight auxiliary regularization tasks. Extensive experiments on the public BCI dataset demonstrate that LGD-Net achieves state-of-the-art performance, significantly outperforming baseline methods while enabling efficient inference using single-modality H&E inputs. --- ### Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry Authors: Xiukun Wei, Min Shi, Xueru Zhang Published: 2026-02-19 Categories: cs.GT, cs.LG arXiv: https://arxiv.org/abs/2602.17787v1 Generative model ecosystems increasingly operate as competitive multi-platform markets, where platforms strategically select models from a shared pool and users with heterogeneous preferences choose among them. Understanding how platforms interact, when market equilibria exist, how outcomes are shaped by model-providers, platforms, and user behavior, and how social welfare is affected is critical for fostering a beneficial market environment. In this paper, we formalize a three-layer model-platform-user market game and identify conditions for the existence of pure Nash equilibrium. Our analysis shows that market structure, whether platforms converge on similar models or differentiate by selecting distinct ones, depends not only on models' global average performance but also on their localized attraction to user groups. We further examine welfare outcomes and show that expanding the model pool does not necessarily increase user welfare or market diversity. Finally, we design novel best-response training schemes that allow model providers to strategically introduce new models into competitive markets. --- ### Multi-Modal Monocular Endoscopic Depth and Pose Estimation with Edge-Guided Self-Supervision Authors: Xinwei Ju, Rema Daher, Danail Stoyanov, Sophia Bano, Francisco Vasconcelos Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17785v1 Monocular depth and pose estimation play an important role in the development of colonoscopy-assisted navigation, as they enable improved screening by reducing blind spots, minimizing the risk of missed or recurrent lesions, and lowering the likelihood of incomplete examinations. However, this task remains challenging due to the presence of texture-less surfaces, complex illumination patterns, deformation, and a lack of in-vivo datasets with reliable ground truth. In this paper, we propose **PRISM** (Pose-Refinement with Intrinsic Shading and edge Maps), a self-supervised learning framework that leverages anatomical and illumination priors to guide geometric learning. Our approach uniquely incorporates edge detection and luminance decoupling for structural guidance. Specifically, edge maps are derived using a learning-based edge detector (e.g., DexiNed or HED) trained to capture thin and high-frequency boundaries, while luminance decoupling is obtained through an intrinsic decomposition module that separates shading and reflectance, enabling the model to exploit shading cues for depth estimation. Experimental results on multiple real and synthetic datasets demonstrate state-of-the-art performance. We further conduct a thorough ablation study on training data selection to establish best practices for pose and depth estimation in colonoscopy. This analysis yields two practical insights: (1) self-supervised training on real-world data outperforms supervised training on realistic phantom data, underscoring the superiority of domain realism over ground truth availability; and (2) video frame rate is an extremely important factor for model performance, where dataset-specific video frame sampling is necessary for generating high quality training data. --- ### QueryPlot: Generating Geological Evidence Layers using Natural Language Queries for Mineral Exploration Authors: Meng Ye, Xiao Lin, Georgina Lukoczki, Graham W. Lederer, Yi Yao Published: 2026-02-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.17784v2 Mineral prospectivity mapping requires synthesizing heterogeneous geological knowledge, including textual deposit models and geospatial datasets, to identify regions likely to host specific mineral deposit types. This process is traditionally manual and knowledge-intensive. We present QueryPlot, a semantic retrieval and mapping framework that integrates large-scale geological text corpora with geologic map data using modern Natural Language Processing techniques. We curate descriptive deposit models for over 120 deposit types and transform the State Geologic Map Compilation (SGMC) polygons into structured textual representations. Given a user-defined natural language query, the system encodes both queries and region descriptions using a pretrained embedding model and computes semantic similarity scores to rank and spatially visualize regions as continuous evidence layers. QueryPlot supports compositional querying over deposit characteristics, enabling aggregation of multiple similarity-derived layers for multi-criteria prospectivity analysis. In a case study on tungsten skarn deposits, we demonstrate that embedding-based retrieval achieves high recall of known occurrences and produces prospective regions that closely align with expert-defined permissive tracts. Furthermore, similarity scores can be incorporated as additional features in supervised learning pipelines, yielding measurable improvements in classification performance. QueryPlot is implemented as a web-based system supporting interactive querying, visualization, and export of GIS-compatible prospectivity layers.To support future research, we have made the source code and datasets used in this study publicly available. --- ### Multi-material Multi-physics Topology Optimization with Physics-informed Gaussian Process Priors Authors: Xiangyu Sun, Shirin Hosseinmardi, Amin Yousefpour, Ramin Bostanabad Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17783v1 Machine learning (ML) has been increasingly used for topology optimization (TO). However, most existing ML-based approaches focus on simplified benchmark problems due to their high computational cost, spectral bias, and difficulty in handling complex physics. These limitations become more pronounced in multi-material, multi-physics problems whose objective or constraint functions are not self-adjoint. To address these challenges, we propose a framework based on physics-informed Gaussian processes (PIGPs). In our approach, the primary, adjoint, and design variables are represented by independent GP priors whose mean functions are parametrized via neural networks whose architectures are particularly beneficial for surrogate modeling of PDE solutions. We estimate all parameters of our model simultaneously by minimizing a loss that is based on the objective function, multi-physics potential energy functionals, and design-constraints. We demonstrate the capability of the proposed framework on benchmark TO problems such as compliance minimization, heat conduction optimization, and compliant mechanism design under single- and multi-material settings. Additionally, we leverage thermo-mechanical TO with single- and multi-material options as a representative multi-physics problem. We also introduce differentiation and integration schemes that dramatically accelerate the training process. Our results demonstrate that the proposed PIGP framework can effectively solve coupled multi-physics and design problems simultaneously -- generating super-resolution topologies with sharp interfaces and physically interpretable material distributions. We validate these results using open-source codes and the commercial software package COMSOL. --- ### Topological Exploration of High-Dimensional Empirical Risk Landscapes: general approach, and applications to phase retrieval Authors: Antoine Maillard, Tony Bonnaire, Giulio Biroli Published: 2026-02-19 Categories: stat.ML, cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2602.17779v1 We consider the landscape of empirical risk minimization for high-dimensional Gaussian single-index models (generalized linear models). The objective is to recover an unknown signal $\boldsymbolθ^\star \in \mathbb{R}^d$ (where $d \gg 1$) from a loss function $\hat{R}(\boldsymbolθ)$ that depends on pairs of labels $(\mathbf{x}_i \cdot \boldsymbolθ, \mathbf{x}_i \cdot \boldsymbolθ^\star)_{i=1}^n$, with $\mathbf{x}_i \sim \mathcal{N}(0, I_d)$, in the proportional asymptotic regime $n \asymp d$. Using the Kac-Rice formula, we analyze different complexities of the landscape -- defined as the expected number of critical points -- corresponding to various types of critical points, including local minima. We first show that some variational formulas previously established in the literature for these complexities can be drastically simplified, reducing to explicit variational problems over a finite number of scalar parameters that we can efficiently solve numerically. Our framework also provides detailed predictions for properties of the critical points, including the spectral properties of the Hessian and the joint distribution of labels. We apply our analysis to the real phase retrieval problem for which we derive complete topological phase diagrams of the loss landscape, characterizing notably BBP-type transitions where the Hessian at local minima (as predicted by the Kac-Rice formula) becomes unstable in the direction of the signal. We test the predictive power of our analysis to characterize gradient flow dynamics, finding excellent agreement with finite-size simulations of local optimization algorithms, and capturing fine-grained details such as the empirical distribution of labels. Overall, our results open new avenues for the asymptotic study of loss landscapes and topological trivialization phenomena in high-dimensional statistical models. --- ### Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs Authors: Zachary Coalson, Bo Fang, Sanghyun Hong Published: 2026-02-19 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2602.17778v1 Multi-turn interaction length is a dominant factor in the operational costs of conversational LLMs. In this work, we present a new failure mode in conversational LLMs: turn amplification, in which a model consistently prolongs multi-turn interactions without completing the underlying task. We show that an adversary can systematically exploit clarification-seeking behavior$-$commonly encouraged in multi-turn conversation settings$-$to scalably prolong interactions. Moving beyond prompt-level behaviors, we take a mechanistic perspective and identify a query-independent, universal activation subspace associated with clarification-seeking responses. Unlike prior cost-amplification attacks that rely on per-turn prompt optimization, our attack arises from conversational dynamics and persists across prompts and tasks. We show that this mechanism provides a scalable pathway to induce turn amplification: both supply-chain attacks via fine-tuning and runtime attacks through low-level parameter corruptions consistently shift models toward abstract, clarification-seeking behavior across prompts. Across multiple instruction-tuned LLMs and benchmarks, our attack substantially increases turn count while remaining compliant. We also show that existing defenses offer limited protection against this emerging class of failures. --- ### Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method Authors: Yuhe Wang, Min Wang Published: 2026-02-19 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2602.17776v2 Physics-governed models are increasingly paired with machine learning for accelerated predictions, yet most "physics--informed" formulations treat the governing equations as a penalty loss whose scale and meaning are set by heuristic balancing. This blurs operator structure, thereby confounding solution approximation error with governing-equation enforcement error and making the solving and learning progress hard to interpret and control. Here we introduce the Neural Basis Method, a projection-based formulation that couples a predefined, physics-conforming neural basis space with an operator-induced residual metric to obtain a well-conditioned deterministic minimization. Stability and reliability then hinge on this metric: the residual is not merely an optimization objective but a computable certificate tied to approximation and enforcement, remaining stable under basis enrichment and yielding reduced coordinates that are learnable across parametric instances. We use advective multiscale Darcian dynamics as a concrete demonstration of this broader point. Our method produce accurate and robust solutions in single solves and enable fast and effective parametric inference with operator learning. --- ### Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds Authors: Noah Trupin, Rahul Ghosh, Aadi Jangid Published: 2026-02-19 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2602.17773v1 We present a generative modeling framework for synthesizing physically feasible two-dimensional incompressible flows under arbitrary obstacle geometries and boundary conditions. Whereas existing diffusion-based flow generators either ignore physical constraints, impose soft penalties that do not guarantee feasibility, or specialize to fixed geometries, our approach integrates three complementary components: (1) a boundary-conditioned diffusion model operating on velocity fields; (2) a physics-informed training objective incorporating a divergence penalty; and (3) a projection-constrained reverse diffusion process that enforces exact incompressibility through a geometry-aware Helmholtz-Hodge operator. We derive the method as a discrete approximation to constrained Langevin sampling on the manifold of divergence-free vector fields, providing a connection between modern diffusion models and geometric constraint enforcement in incompressible flow spaces. Experiments on analytic Navier-Stokes data and obstacle-bounded flow configurations demonstrate significantly improved divergence, spectral accuracy, vorticity statistics, and boundary consistency relative to unconstrained, projection-only, and penalty-only baselines. Our formulation unifies soft and hard physical structure within diffusion models and provides a foundation for generative modeling of incompressible fields in robotics, graphics, and scientific computing. --- ### Sparse Bayesian Modeling of EEG Channel Interactions Improves P300 Brain-Computer Interface Performance Authors: Guoxuan Ma, Yuan Zhong, Moyan Li, Yuxiao Nie, Jian Kang Published: 2026-02-19 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2602.17772v3 Electroencephalography (EEG)-based P300 brain-computer interfaces (BCIs) enable communication without physical movement by detecting stimulus-evoked neural responses. Accurate and efficient decoding remains challenging due to high dimensionality, temporal dependence, and complex interactions across EEG channels. Existing approaches often treat channels independently or rely on black-box models, limiting interpretability and personalization. We propose a sparse Bayesian time-varying regression framework that explicitly models pairwise EEG channel interactions while performing temporal feature selection, where a relaxed-thresholded Gaussian process prior induces structured sparsity in both channel-specific and interaction effects, enabling interpretable identification of task-relevant channels and channel pairs. Applied to a public P300 speller dataset of 55 participants, our method achieves a 96.4% median character-level accuracy using all sequence repetitions and attains the best overall decoding performance among competing statistical and deep learning approaches. Incorporating channel interactions yields subgroup-specific gains in character-level accuracy, particularly among participants abstained from alcohol (median 7%, up to 14%). Importantly, our approach improves median BCI-Utility by more than 10% at its optimal operating point, achieving peak throughput after only six sequence repetitions. These results demonstrate that explicitly modeling structured EEG channel interactions within a principled Bayesian framework enhances accuracy and user-centric throughput, and supports personalization in P300 BCI systems. --- ### Sparse Bayesian Modeling of EEG Channel Interactions Improves P300 Brain-Computer Interface Performance Authors: Guoxuan Ma, Yuan Zhong, Moyan Li, Yuxiao Nie, Jian Kang Published: 2026-02-19 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2602.17772v2 Electroencephalography (EEG)-based P300 brain-computer interfaces (BCIs) enable communication without physical movement by detecting stimulus-evoked neural responses. Accurate and efficient decoding remains challenging due to high dimensionality, temporal dependence, and complex interactions across EEG channels. Most existing approaches treat channels independently or rely on black-box machine learning models, limiting interpretability and personalization. We propose a sparse Bayesian time-varying regression framework that explicitly models pairwise EEG channel interactions while performing automatic temporal feature selection. The model employs a relaxed-thresholded Gaussian process prior to induce structured sparsity in both channel-specific and interaction effects, enabling interpretable identification of task-relevant channels and channel pairs. Applied to a publicly available P300 speller dataset of 55 participants, the proposed method achieves a median character-level accuracy of 100\% using all stimulus sequences and attains the highest overall decoding performance among competing statistical and deep learning approaches. Incorporating channel interactions yields subgroup-specific gains of up to 7\% in character-level accuracy, particularly among participants who abstained from alcohol (up to 18\% improvement). Importantly, the proposed method improves median BCI-Utility by approximately 10\% at its optimal operating point, achieving peak throughput after only seven stimulus sequences. These results demonstrate that explicitly modeling structured EEG channel interactions within a principled Bayesian framework enhances predictive accuracy, improves user-centric throughput, and supports personalization in P300 BCI systems. --- ### CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild Authors: Balamurugan Thambiraja, Omid Taheri, Radek Danecek, Giorgio Becherini, Gerard Pons-Moll, Justus Thies Published: 2026-02-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.17770v1 Hands play a central role in daily life, yet modeling natural hand motions remains underexplored. Existing methods that tackle text-to-hand-motion generation or hand animation captioning rely on studio-captured datasets with limited actions and contexts, making them costly to scale to "in-the-wild" settings. Further, contemporary models and their training schemes struggle to capture animation fidelity with text-motion alignment. To address this, we (1) introduce '3D Hands in the Wild' (3D-HIW), a dataset of 32K 3D hand-motion sequences and aligned text, and (2) propose CLUTCH, an LLM-based hand animation system with two critical innovations: (a) SHIFT, a novel VQ-VAE architecture to tokenize hand motion, and (b) a geometric refinement stage to finetune the LLM. To build 3D-HIW, we propose a data annotation pipeline that combines vision-language models (VLMs) and state-of-the-art 3D hand trackers, and apply it to a large corpus of egocentric action videos covering a wide range of scenarios. To fully capture motion in-the-wild, CLUTCH employs SHIFT, a part-modality decomposed VQ-VAE, which improves generalization and reconstruction fidelity. Finally, to improve animation quality, we introduce a geometric refinement stage, where CLUTCH is co-supervised with a reconstruction loss applied directly to decoded hand motion parameters. Experiments demonstrate state-of-the-art performance on text-to-motion and motion-to-text tasks, establishing the first benchmark for scalable in-the-wild hand motion modelling. Code, data and models will be released. --- ### KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding Authors: Boda Lin, Yongjie Zhu, Xiaocheng Gong, Wenyu Qin, Meng Wang Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17768v1 Despite recent advancements, video captioning models still face significant limitations in accurately describing fine-grained motion details and suffer from severe hallucination issues. These challenges become particularly prominent when generating captions for motion-centric videos, where precise depiction of intricate movements and limb dynamics is crucial yet often neglected. To alleviate this gap, we introduce an automated annotation pipeline that integrates kinematic-based motion computation with linguistic parsing, enabling detailed decomposition and description of complex human motions. Based on this pipeline, we construct and release the Kinematic Parsing Motion Benchmark (KPM-Bench), a novel open-source dataset designed to facilitate fine-grained motion understanding. KPM-Bench consists of (i) fine-grained video-caption pairs that comprehensively illustrate limb-level dynamics in complex actions, (ii) diverse and challenging question-answer pairs focusing specifically on motion understanding, and (iii) a meticulously curated evaluation set specifically designed to assess hallucination phenomena associated with motion descriptions. Furthermore, to address hallucination issues systematically, we propose the linguistically grounded Motion Parsing and Extraction (MoPE) algorithm, capable of accurately extracting motion-specific attributes directly from textual captions. Leveraging MoPE, we introduce a precise hallucination evaluation metric that functions independently of large-scale vision-language or language-only models. By integrating MoPE into the GRPO post-training framework, we effectively mitigate hallucination problems, significantly improving the reliability of motion-centric video captioning models. --- ### The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems Authors: Leon Staufer, Kevin Feng, Kevin Wei, Luke Bailey, Yawen Duan, Mick Yang, A. Pinar Ozisik, Stephen Casper, Noam Kolt Published: 2026-02-19 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.17753v2 Agentic AI systems are increasingly capable of performing professional and personal tasks with limited human involvement. However, tracking these developments is difficult because the AI agent ecosystem is complex, rapidly evolving, and inconsistently documented, posing obstacles to both researchers and policymakers. To address these challenges, this paper presents the 2025 AI Agent Index. The Index documents information regarding the origins, design, capabilities, ecosystem, and safety features of 30 state-of-the-art AI agents based on publicly available information and email correspondence with developers. In addition to documenting information about individual agents, the Index illuminates broader trends in the development of agents, their capabilities, and the level of transparency of developers. Notably, we find different transparency levels among agent developers and observe that most developers share little information about safety, evaluations, and societal impacts. The 2025 AI Agent Index is available online at https://aiagentindex.mit.edu --- ### Investigating Target Class Influence on Neural Network Compressibility for Energy-Autonomous Avian Monitoring Authors: Nina Brolich, Simon Geis, Maximilian Kasper, Alexander Barnhill, Axel Plinge, Dominik Seuß Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17751v2 Biodiversity loss poses a significant threat to humanity, making wildlife monitoring essential for assessing ecosystem health. Avian species are ideal subjects for this due to their popularity and the ease of identifying them through their distinctive songs. Traditionalavian monitoring methods require manual counting and are therefore costly and inefficient. In passive acoustic monitoring, soundscapes are recorded over long periods of time. The recordings are analyzed to identify bird species afterwards. Machine learning methods have greatly expedited this process in a wide range of species and environments, however, existing solutions require complex models and substantial computational resources. Instead, we propose running machine learning models on inexpensive microcontroller units (MCUs) directly in the field. Due to the resulting hardware and energy constraints, efficient artificial intelligence (AI) architecture is required. In this paper, we present our method for avian monitoring on MCUs. We trained and compressed models for various numbers of target classes to assess the detection of multiple bird species on edge devices and evaluate the influence of the number of species on the compressibility of neural networks. Our results demonstrate significant compression rates with minimal performance loss. We also provide benchmarking results for different hardware platforms and evaluate the feasibility of deploying energy-autonomous devices. --- ### Investigating Target Class Influence on Neural Network Compressibility for Energy-Autonomous Avian Monitoring Authors: Nina Brolich, Simon Geis, Maximilian Kasper, Alexander Barnhill, Axel Plinge, Dominik Seuß Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17751v1 Biodiversity loss poses a significant threat to humanity, making wildlife monitoring essential for assessing ecosystem health. Avian species are ideal subjects for this due to their popularity and the ease of identifying them through their distinctive songs. Traditionalavian monitoring methods require manual counting and are therefore costly and inefficient. In passive acoustic monitoring, soundscapes are recorded over long periods of time. The recordings are analyzed to identify bird species afterwards. Machine learning methods have greatly expedited this process in a wide range of species and environments, however, existing solutions require complex models and substantial computational resources. Instead, we propose running machine learning models on inexpensive microcontroller units (MCUs) directly in the field. Due to the resulting hardware and energy constraints, efficient artificial intelligence (AI) architecture is required. In this paper, we present our method for avian monitoring on MCUs. We trained and compressed models for various numbers of target classes to assess the detection of multiple bird species on edge devices and evaluate the influence of the number of species on the compressibility of neural networks. Our results demonstrate significant compression rates with minimal performance loss. We also provide benchmarking results for different hardware platforms and evaluate the feasibility of deploying energy-autonomous devices. --- ### Inelastic Constitutive Kolmogorov-Arnold Networks: A generalized framework for automated discovery of interpretable inelastic material models Authors: Chenyi Ji, Kian P. Abdolazizi, Hagen Holthusen, Christian J. Cyron, Kevin Linka Published: 2026-02-19 Categories: cond-mat.mtrl-sci, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2602.17750v3 A key problem of solid mechanics is the identification of the constitutive law of a material, that is, the relation between strain history and stress. Machine learning has lead to considerable advances in this field lately. Here we introduce inelastic Constitutive Kolmogorov-Arnold Networks (iCKANs). This novel artificial neural network architecture can discover in an automated manner symbolic constitutive laws describing both the elastic and inelastic behavior of materials. That is, it can translate data from material testing into corresponding elastic and inelastic potential functions in closed mathematical form. We demonstrate the advantages of iCKANs using both synthetic data and experimental data of the viscoelastic polymer materials VHB 4910 and VHB 4905. The results demonstrate that iCKANs accurately capture complex viscoelastic behavior while preserving physical interpretability. It is a particular strength of iCKANs that they can process not only mechanical data but also arbitrary additional information available about a material (e.g., about temperature-dependent behavior). This makes iCKANs a powerful tool to discover in the future also how specific processing or service conditions affect the properties of materials. --- ### Detection and Classification of Cetacean Echolocation Clicks using Image-based Object Detection Methods applied to Advanced Wavelet-based Transformations Authors: Christopher Hauer Published: 2026-02-19 Categories: eess.AS, cs.AI, cs.CV, cs.SD arXiv: https://arxiv.org/abs/2602.17749v1 A challenge in marine bioacoustic analysis is the detection of animal signals, like calls, whistles and clicks, for behavioral studies. Manual labeling is too time-consuming to process sufficient data to get reasonable results. Thus, an automatic solution to overcome the time-consuming data analysis is necessary. Basic mathematical models can detect events in simple environments, but they struggle with complex scenarios, like differentiating signals with a low signal-to-noise ratio or distinguishing clicks from echoes. Deep Learning Neural Networks, such as ANIMAL-SPOT, are better suited for such tasks. DNNs process audio signals as image representations, often using spectrograms created by Short-Time Fourier Transform. However, spectrograms have limitations due to the uncertainty principle, which creates a tradeoff between time and frequency resolution. Alternatives like the wavelet, which provides better time resolution for high frequencies and improved frequency resolution for low frequencies, may offer advantages for feature extraction in complex bioacoustic environments. This thesis shows the efficacy of CLICK-SPOT on Norwegian Killer whale underwater recordings provided by the cetacean biologist Dr. Vester. Keywords: Bioacoustics, Deep Learning, Wavelet Transformation --- ### AgriVariant: Variant Effect Prediction using DeepChem-Variant for Precision Breeding in Rice Authors: Ankita Vaishnobi Bisoi, Bharath Ramsundar Published: 2026-02-19 Categories: q-bio.GN, cs.LG arXiv: https://arxiv.org/abs/2602.17747v1 Predicting functional consequences of genetic variants in crop genes remains a critical bottleneck for precision breeding programs. We present AgriVariant, an end-to-end pipeline for variant-effect prediction in rice (Oryza sativa) that addresses the lack of crop-specific variant-interpretation tools and can be extended to any crop species with available reference genomes and gene annotations. Our approach integrates deep learning-based variant calling (DeepChem-Variant) with custom plant genomics annotation using RAP-DB gene models and database-independent deleteriousness scoring that combines the Grantham distance and the BLOSUM62 substitution matrix. We validate the pipeline through targeted mutations in stress-response genes (OsDREB2a, OsDREB1F, SKC1), demonstrating correct classification of stop-gained, missense, and synonymous variants with appropriate HIGH / MODERATE / LOW impact assignments. An exhaustive mutagenesis study of OsMT-3a analyzed all 1,509 possible single-nucleotide variants in 10 days, identifying 353 high-impact, 447 medium-impact, and 709 low-impact variants - an analysis that would have required 2-4 years using traditional wet-lab approaches. This computational framework enables breeders to prioritize variants for experimental validation across diverse crop species, reducing screening costs and accelerating development of climate-resilient crop varieties. --- ### Bayesian Optimality of In-Context Learning with Selective State Spaces Authors: Di Zhang, Jiaqi Xing Published: 2026-02-19 Categories: cs.LG, cs.CL, math.ST, stat.ML arXiv: https://arxiv.org/abs/2602.17744v1 We propose Bayesian optimal sequential prediction as a new principle for understanding in-context learning (ICL). Unlike interpretations framing Transformers as performing implicit gradient descent, we formalize ICL as meta-learning over latent sequence tasks. For tasks governed by Linear Gaussian State Space Models (LG-SSMs), we prove a meta-trained selective SSM asymptotically implements the Bayes-optimal predictor, converging to the posterior predictive mean. We further establish a statistical separation from gradient descent, constructing tasks with temporally correlated noise where the optimal Bayesian predictor strictly outperforms any empirical risk minimization (ERM) estimator. Since Transformers can be seen as performing implicit ERM, this demonstrates selective SSMs achieve lower asymptotic risk due to superior statistical efficiency. Experiments on synthetic LG-SSM tasks and a character-level Markov benchmark confirm selective SSMs converge faster to Bayes-optimal risk, show superior sample efficiency with longer contexts in structured-noise settings, and track latent states more robustly than linear Transformers. This reframes ICL from "implicit optimization" to "optimal inference," explaining the efficiency of selective SSMs and offering a principled basis for architecture design. --- ### Bigger Is Safer: Provable Robustness in In-Context Learning Scales with Capacity Authors: Di Zhang, Ningxu Zhang, Zimeng Liu Published: 2026-02-19 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.17743v2 In-context learning (ICL) allows large language models to adapt to new tasks from a few examples without updating their parameters. Existing theories explain ICL by assuming the test task distribution matches pretraining -- an assumption that breaks down under adversarial distribution shifts. We introduce a distributionally robust meta-learning framework that provides worst-case guarantees for ICL under Wasserstein-based distribution shifts. Focusing on linear self-attention Transformers, we derive a non-asymptotic bound connecting adversarial perturbation strength ($ρ$), model capacity ($m$), and the number of in-context examples ($N$). The analysis reveals that the maximum safe perturbation radius scales as $ρ_{\max} \propto \sqrt{m}$, while maintaining performance under adversarial shift requires additional in-context examples with $N_ρ- N_0 \propto ρ^2$. Experiments on synthetic tasks confirm these scaling laws, and experiments on 21 real pretrained models (0.1B--7B parameters, 5 families) provide qualitative evidence consistent with the theory's predictions, while revealing that ICL capability is a prerequisite for robustness. These findings advance the theoretical understanding of ICL under adversarial conditions and formalize the sense in which larger models are safer under distributional shift. --- ### GeneZip: Region-Aware Compression for Long Context DNA Modeling Authors: Jianan Zhao, Xixian Liu, Zhihao Zhan, Xinyu Yuan, Hongyu Guo, Jian Tang Published: 2026-02-19 Categories: q-bio.GN, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.17739v3 Long-context DNA models are limited by token-mixing cost and by how compression allocates representational budget across the genome. Existing approaches operate close to base-pair resolution, apply fixed downsampling, or learn content-dependent chunks without an explicit genomic budget, making long-context pretraining expensive and difficult to control. We introduce GeneZip, a region-aware DNA compression framework that combines H-Net-style dynamic routing with a Region-Aware Ratio (RAR) objective and bounded routing. GeneZip uses static gene-structure annotations during compression training to specify region-wise base-pairs-per-token (BPT) targets; at inference time, it compresses raw unseen DNA without annotations. GeneZip provides three main benefits. First, it is effective: GeneZip variants achieve the best validation PPL among encoder-based compressors, with GeneZip-70M operating at 137.6 BPT, and across four reproducible DNALongBench tasks--contact map prediction, eQTL prediction, enhancer-target gene prediction, and transcription-initiation signal prediction--GeneZip obtains the best average rank among compared sequence models. Second, it is redundancy-aware: a post-hoc RepeatMasker/TRF analysis shows that, without repeat supervision, GeneZip assigns higher local BPT to TE-derived interspersed repeats and tandem repeats, two major classes of repetitive DNA sequence redundancy. Third, it is efficient: by reducing the effective token-mixing length, GeneZip enables longer-context and larger-capacity pretraining, including 128K-context and 636M-parameter variants on a single A100 80GB GPU, and fine-tunes the eQTL task 50.4x faster than JanusDNA (50 vs. 2520 minutes). These results establish GeneZip as an effective, redundancy-aware, and efficient compression interface for long-context DNA modeling. --- ### OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents Authors: Akashah Shabbir, Muhammad Umer Sheikh, Muhammad Akhtar Munir, Hiyam Debary, Mustansar Fiaz, Muhammad Zaigham Zaheer, Paolo Fraccaro, Fahad Shahbaz Khan, Muhammad Haris Khan, Xiao Xiang Zhu, Salman Khan Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17665v4 Recent progress in multimodal reasoning has enabled agents that interpret imagery, connect it with language, and execute structured analytical tasks. Extending these capabilities to remote sensing remains challenging, as models must reason over spatial scale, geographic structures, and multispectral indices while maintaining coherent multi-step logic. To address this gap, we introduce \textit{OpenEarthAgent}, a unified framework for tool-augmented geospatial reasoning trained on satellite imagery, natural-language queries, and structured reasoning traces. Beyond serving as a benchmark, OpenEarthAgent establishes a cohesive agentic architecture built around a unified executable tool registry and trajectory-based policy learning. The framework standardizes heterogeneous visual, spectral, GIS, and georeferenced raster operations under a consistent callable schema, enabling modular orchestration and deterministic execution. Training is performed via supervised fine-tuning on structured reasoning trajectories with deterministic replay validation to ensure executability and spatial correctness. The accompanying corpus comprises 14,538 training and 1,169 evaluation instances with over 107K reasoning steps, spanning urban, environmental, disaster, and infrastructure domains and incorporating GIS operations alongside index analyses such as NDVI, NBR, and NDBI. Grounded in explicit reasoning traces, the learned agent demonstrates structured reasoning, stable spatial understanding, and interpretable tool-driven behaviour across diverse EO scenarios. We report consistent improvements over a strong baseline and competitive performance against recent open and closed-source models. Our code, data and trained models are publicly available: https://github.com/mbzuai-oryx/OpenEarthAgent --- ### Sink-Aware Pruning for Diffusion Language Models Authors: Aidar Myrzakhan, Tianyi Li, Bowei Guo, Shengkun Tang, Zhiqiang Shen Published: 2026-02-19 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.17664v1 Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics largely inherited from autoregressive (AR) LLMs, typically preserve attention sink tokens because AR sinks serve as stable global anchors. We show that this assumption does not hold for DLMs: the attention-sink position exhibits substantially higher variance over the full generation trajectory (measured by how the dominant sink locations shift across timesteps), indicating that sinks are often transient and less structurally essential than in AR models. Based on this observation, we propose ${\bf \texttt{Sink-Aware Pruning}}$, which automatically identifies and prunes unstable sinks in DLMs (prior studies usually keep sinks for AR LLMs). Without retraining, our method achieves a better quality-efficiency trade-off and outperforms strong prior pruning baselines under matched compute. Our code is available at https://github.com/VILA-Lab/Sink-Aware-Pruning. --- ### CLEF HIPE-2026: Evaluating Accurate and Efficient Person-Place Relation Extraction from Multilingual Historical Texts Authors: Juri Opitz, Corina Raclé, Emanuela Boros, Andrianos Michail, Matteo Romanello, Maud Ehrmann, Simon Clematide Published: 2026-02-19 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.17663v3 HIPE-2026 is a CLEF evaluation lab dedicated to person-place relation extraction from noisy, multilingual historical texts. Building on the HIPE-2020 and HIPE-2022 campaigns, it extends the series toward semantic relation extraction by targeting the task of identifying person-place associations in multiple languages and time periods. Systems are asked to classify relations of two types -- $at$ ("Has the person ever been at this place?") and $isAt$ ("Is the person located at this place around publication time?") -- requiring reasoning over temporal and geographical cues. The lab introduces a three-fold evaluation profile that jointly assesses accuracy, computational efficiency, and domain generalization. By linking relation extraction to large-scale historical data processing, HIPE-2026 aims to support downstream applications in knowledge-graph construction, historical biography reconstruction, and spatial analysis in digital humanities. --- ### When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs Authors: Yu Fang, Yuchun Feng, Dong Jing, Jiaqi Liu, Yue Yang, Zhenyu Wei, Daniel Szafir, Mingyu Ding Published: 2026-02-19 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.17659v2 Vision-Language-Action models (VLAs) promise to ground language instructions in robot control, yet in practice often fail to faithfully follow language. When presented with instructions that lack strong scene-specific supervision, VLAs suffer from counterfactual failures: they act based on vision shortcuts induced by dataset biases, repeatedly executing well-learned behaviors and selecting objects frequently seen during training regardless of language intent. To systematically study it, we introduce LIBERO-CF, the first counterfactual benchmark for VLAs that evaluates language following capability by assigning alternative instructions under visually plausible LIBERO layouts. Our evaluation reveals that counterfactual failures are prevalent yet underexplored across state-of-the-art VLAs. We propose Counterfactual Action Guidance (CAG), a simple yet effective dual-branch inference scheme that explicitly regularizes language conditioning in VLAs. CAG combines a standard VLA policy with a language-unconditioned Vision-Action (VA) module, enabling counterfactual comparison during action selection. This design reduces reliance on visual shortcuts, improves robustness on under-observed tasks, and requires neither additional demonstrations nor modifications to existing architectures or pretrained models. Extensive experiments demonstrate its plug-and-play integration across diverse VLAs and consistent improvements. For example, on LIBERO-CF, CAG improves $π_{0.5}$ by 9.7% in language following accuracy and 3.6% in task success on under-observed tasks using a training-free strategy, with further gains of 15.5% and 8.5%, respectively, when paired with a VA model. In real-world evaluations, CAG reduces counterfactual failures of 9.4% and improves task success by 17.2% on average. --- ### MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling Authors: Payel Bhattacharjee, Osvaldo Simeone, Ravi Tandon Published: 2026-02-19 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2602.17658v4 Reward modeling is central to RLHF, RLAIF, and PPO-based alignment, but its reliability is often limited by scarce and heterogeneous human preference data. In this paper, we introduce MARS (Margin and Semantic-Aware Data Augmentation for Reward Modeling), an adaptive augmentation framework for controlled low-resource reward modeling. MARS allocates more augmentation to low-margin preference pairs and uses semantic-distance-based refinement to improve chosen-rejected contrast before generating synthetic preference samples. Across three preference datasets, two reward-model backbones, and downstream alignment evaluations, MARS improves average RewardBench performance and alignment win rates over uniform augmentation, WoN, and AdaBoost-style baselines. Ablations and independent-judge evaluations suggest that the gains are not solely explained by semantic refinement alone or GPT-4.1 judge coupling. --- ### What Language is This? Ask Your Tokenizer Authors: Clara Meister, Ahmetcan Yavuz, Pietro Lesci, Tiago Pimentel Published: 2026-02-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.17655v3 Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite near-perfect performance on high-resource languages, existing systems remain brittle in low-resource and closely related language settings. We introduce UniLID, a simple and efficient LID method based on the UnigramLM tokenization algorithm. In short, to predict a string's language label, we simply ask: under which language's unigram distribution is this string most likely? Our formulation is data- and compute-efficient, supports incremental addition of new languages without retraining existing models, and can naturally be integrated into existing language model tokenization pipelines. Empirical evaluations against widely used baselines, including fasttext, GlotLID-M, and CLD3, show that UniLID achieves competitive performance on standard benchmarks, reaches 69% accuracy with five labeled samples per language and 89% with 25, and delivers large gains on fine-grained dialect identification. --- ### What Language is This? Ask Your Tokenizer Authors: Clara Meister, Ahmetcan Yavuz, Pietro Lesci, Tiago Pimentel Published: 2026-02-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.17655v2 Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite near-perfect performance on high-resource languages, existing systems remain brittle in low-resource and closely related language settings. We introduce UniLID, a simple and efficient LID method based on the UnigramLM tokenization algorithm, leveraging its probabilistic framing, parameter estimation technique and inference strategy. In short, to predict a string's language label, we simply ask: under which language's unigram distribution is this string most likely? Our formulation is data- and compute-efficient, supports incremental addition of new languages without retraining existing models, and can naturally be integrated into existing language model tokenization pipelines. Empirical evaluations against widely used baselines, including fastText, GlotLID and CLD3, show that UniLID achieves competitive performance on standard benchmarks, substantially improves sample efficiency in low-resource settings -- reaching ~70% accuracy with as few as five labeled samples per language -- and delivers large gains on fine-grained dialect identification. --- ### Mine and Refine: Optimizing Graded Relevance in E-commerce Semantic Search Retrieval Authors: Jiaqi Xi, Raghav Saboo, Luming Chen, Johny Rufus, Aditya Dodda, Ved Sampath, Kenny Chi, Elyse Winer, Akshad Viswanathan, Martin Wang, Sudeep Das Published: 2026-02-19 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.17654v2 Embedding-based retrieval (EBR) for large-scale e-commerce search faces three intertwined challenges: graded (non-binary) relevance where engagement signals are noisy and intent-varying while business relevance guidelines admit acceptable-but-not-exact matches, false negatives in hard sample mining, and unstable similarity score separability across relevance levels, the last of which complicates hybrid search score fusion and downstream ranking. We propose Mine and Refine, a two-stage contrastive training framework that addresses all three. A lightweight LLM, fine-tuned with engagement-driven audit, serves as a guideline-aligned scalable labeler throughout training. Stage 1 establishes a robust global embedding space via label-aware supervised contrastive learning; Stage 2 mines hard samples, re-annotates them with the LLM labeler to mitigate spurious negatives, and refines the model through a multi-level extension of circle loss that enforces margin-controlled separation across relevance levels. Deployed in production e-commerce search across multiple product verticals, the approach delivers statistically significant lifts in user engagement and gross order value, and substantially improves retrieval and end-to-end relevance metrics. --- ### Mine and Refine: Optimizing Graded Relevance in E-commerce Search Retrieval Authors: Jiaqi Xi, Raghav Saboo, Luming Chen, Martin Wang, Sudeep Das Published: 2026-02-19 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.17654v1 We propose a two-stage "Mine and Refine" contrastive training framework for semantic text embeddings to enhance multi-category e-commerce search retrieval. Large scale e-commerce search demands embeddings that generalize to long tail, noisy queries while adhering to scalable supervision compatible with product and policy constraints. A practical challenge is that relevance is often graded: users accept substitutes or complements beyond exact matches, and production systems benefit from clear separation of similarity scores across these relevance strata for stable hybrid blending and thresholding. To obtain scalable policy consistent supervision, we fine-tune a lightweight LLM on human annotations under a three-level relevance guideline and further reduce residual noise via engagement driven auditing. In Stage 1, we train a multilingual Siamese two-tower retriever with a label aware supervised contrastive objective that shapes a robust global semantic space. In Stage 2, we mine hard samples via ANN and re-annotate them with the policy aligned LLM, and introduce a multi-class extension of circle loss that explicitly sharpens similarity boundaries between relevance levels, to further refine and enrich the embedding space. Robustness is additionally improved through additive spelling augmentation and synthetic query generation. Extensive offline evaluations and production A/B tests show that our framework improves retrieval relevance and delivers statistically significant gains in engagement and business impact. --- ### Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking Authors: Iskar Deng, Nathalia Xu, Shane Steinert-Threlkeld Published: 2026-02-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.17653v2 Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities in human languages, particularly for syntactic phenomena such as word order. In this paper, we extend this paradigm to differential argument marking (DAM), a semantic licensing system in which morphological marking depends on semantic prominence. Using a controlled synthetic learning method, we train GPT-2 models on 18 corpora implementing distinct DAM systems and evaluate their generalization using minimal pairs. Our results reveal a dissociation between two typological dimensions of DAM. Models reliably exhibit human-like preferences for natural markedness direction, favoring systems in which overt marking targets semantically atypical arguments. In contrast, models do not reproduce the strong object preference in human languages, in which overt marking in DAM more often targets objects rather than subjects. These findings suggest that different typological tendencies may arise from distinct underlying sources. --- ### Human-level 3D shape perception emerges from multi-view learning Authors: Tyler Bonnen, Jitendra Malik, Angjoo Kanazawa Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17650v2 Humans can infer the three-dimensional structure of objects from two-dimensional visual inputs. Modeling this ability has been a longstanding goal for the science and engineering of visual intelligence, yet decades of computational methods have fallen short of human performance. Here we develop a modeling framework that predicts human 3D shape inferences for arbitrary objects, directly from experimental stimuli. We achieve this with a novel class of neural networks trained using a visual-spatial objective over naturalistic sensory data; given a set of images taken from different locations within a natural scene, these models learn to predict spatial information related to these images, such as camera location and visual depth, without relying on any object-related inductive biases. Notably, these visual-spatial signals are analogous to sensory cues readily available to humans. We design a zero-shot evaluation approach to determine the performance of these 'multi-view' models on a well established 3D perception task, then compare model and human behavior. Our modeling framework is the first to match human accuracy on 3D shape inferences, even without task-specific training or fine-tuning. Remarkably, independent readouts of model responses predict fine-grained measures of human behavior, including error patterns and reaction times, revealing a natural correspondence between model dynamics and human perception. Taken together, our findings indicate that human-level 3D perception can emerge from a simple, scalable learning objective over naturalistic visual-spatial data. Code, images, and human data needed to reproduce all analyses can be found at https://tzler.github.io/human_multiview/ --- ### Multi-Round Human-AI Collaboration with User-Specified Requirements Authors: Sima Noorani, Shayan Kiyani, Hamed Hassani, George Pappas Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17646v2 As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human centric view governed by two principles: counterfactual harm, ensuring the AI does not undermine human strengths, and complementarity, ensuring it adds value where the human is prone to err. We formalize these concepts via user defined rules, allowing users to specify exactly what harm and complementarity mean for their specific task. We then introduce an online, distribution free algorithm with finite sample guarantees that enforces the user-specified constraints over the collaboration dynamics. We evaluate our framework across two interactive settings: LLM simulated collaboration on a medical diagnostic task and a human crowdsourcing study on a pictorial reasoning task. We show that our online procedure maintains prescribed counterfactual harm and complementarity violation rates even under nonstationary interaction dynamics. Moreover, tightening or loosening these constraints produces predictable shifts in downstream human accuracy, confirming that the two principles serve as practical levers for steering multi-round collaboration toward better decision quality without the need to model or constrain human behavior. --- ### Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting Authors: Xiaohan Zhao, Zhaoyi Li, Yaxin Luo, Jiacheng Cui, Zhiqiang Shen Published: 2026-02-19 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2602.17645v1 Black-box adversarial attacks on Large Vision-Language Models (LVLMs) are challenging due to missing gradients and complex multimodal boundaries. While prior state-of-the-art transfer-based approaches like M-Attack perform well using local crop-level matching between source and target images, we find this induces high-variance, nearly orthogonal gradients across iterations, violating coherent local alignment and destabilizing optimization. We attribute this to (i) ViT translation sensitivity that yields spike-like gradients and (ii) structural asymmetry between source and target crops. We reformulate local matching as an asymmetric expectation over source transformations and target semantics, and build a gradient-denoising upgrade to M-Attack. On the source side, Multi-Crop Alignment (MCA) averages gradients from multiple independently sampled local views per iteration to reduce variance. On the target side, Auxiliary Target Alignment (ATA) replaces aggressive target augmentation with a small auxiliary set from a semantically correlated distribution, producing a smoother, lower-variance target manifold. We further reinterpret momentum as Patch Momentum, replaying historical crop gradients; combined with a refined patch-size ensemble (PE+), this strengthens transferable directions. Together these modules form M-Attack-V2, a simple, modular enhancement over M-Attack that substantially improves transfer-based black-box attacks on frontier LVLMs: boosting success rates on Claude-4.0 from 8% to 30%, Gemini-2.5-Pro from 83% to 97%, and GPT-5 from 98% to 100%, outperforming prior black-box LVLM attacks. Code and data are publicly available at: https://github.com/vila-lab/M-Attack-V2. --- ### A.R.I.S.: Automated Recycling Identification System for E-Waste Classification Using Deep Learning Authors: Dhruv Talwar, Harsh Desai, Wendong Yin, Goutam Mohanty, Rafael Reveles Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17642v1 Traditional electronic recycling processes suffer from significant resource loss due to inadequate material separation and identification capabilities, limiting material recovery. We present A.R.I.S. (Automated Recycling Identification System), a low-cost, portable sorter for shredded e-waste that addresses this efficiency gap. The system employs a YOLOx model to classify metals, plastics, and circuit boards in real time, achieving low inference latency with high detection accuracy. Experimental evaluation yielded 90% overall precision, 82.2% mean average precision (mAP), and 84% sortation purity. By integrating deep learning with established sorting methods, A.R.I.S. enhances material recovery efficiency and lowers barriers to advanced recycling adoption. This work complements broader initiatives in extending product life cycles, supporting trade-in and recycling programs, and reducing environmental impact across the supply chain. --- ### FAMOSE: A ReAct Approach to Automated Feature Discovery Authors: Keith Burghardt, Jienan Liu, Sadman Sakib, Yuning Hao, Bo Li Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17641v1 Feature engineering remains a critical yet challenging bottleneck in machine learning, particularly for tabular data, as identifying optimal features from an exponentially large feature space traditionally demands substantial domain expertise. To address this challenge, we introduce FAMOSE (Feature AugMentation and Optimal Selection agEnt), a novel framework that leverages the ReAct paradigm to autonomously explore, generate, and refine features while integrating feature selection and evaluation tools within an agent architecture. To our knowledge, FAMOSE represents the first application of an agentic ReAct framework to automated feature engineering, especially for both regression and classification tasks. Extensive experiments demonstrate that FAMOSE is at or near the state-of-the-art on classification tasks (especially tasks with more than 10K instances, where ROC-AUC increases 0.23% on average), and achieves the state-of-the-art for regression tasks by reducing RMSE by 2.0% on average, while remaining more robust to errors than other algorithms. We hypothesize that FAMOSE's strong performance is because ReAct allows the LLM context window to record (via iterative feature discovery and evaluation steps) what features did or did not work. This is similar to a few-shot prompt and guides the LLM to invent better, more innovative features. Our work offers evidence that AI agents are remarkably effective in solving problems that require highly inventive solutions, such as feature engineering. --- ### IntRec: Intent-based Retrieval with Contrastive Refinement Authors: Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Yue Lu Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17639v1 Retrieving user-specified objects from complex scenes remains a challenging task, especially when queries are ambiguous or involve multiple similar objects. Existing open-vocabulary detectors operate in a one-shot manner, lacking the ability to refine predictions based on user feedback. To address this, we propose IntRec, an interactive object retrieval framework that refines predictions based on user feedback. At its core is an Intent State (IS) that maintains dual memory sets for positive anchors (confirmed cues) and negative constraints (rejected hypotheses). A contrastive alignment function ranks candidate objects by maximizing similarity to positive cues while penalizing rejected ones, enabling fine-grained disambiguation in cluttered scenes. Our interactive framework provides substantial improvements in retrieval accuracy without additional supervision. On LVIS, IntRec achieves 35.4 AP, outperforming OVMR, CoDet, and CAKE by +2.3, +3.7, and +0.5, respectively. On the challenging LVIS-Ambiguous benchmark, it improves performance by +7.9 AP over its one-shot baseline after a single corrective feedback, with less than 30 ms of added latency per interaction. --- ### CORAL: Correspondence Alignment for Improved Virtual Try-On Authors: Jiyoung Kim, Youngjin Shin, Siyoon Jin, Dahyun Chung, Jisu Nam, Tongmin Kim, Jongjae Park, Hyeonwoo Kang, Seungryong Kim Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17636v1 Existing methods for Virtual Try-On (VTON) often struggle to preserve fine garment details, especially in unpaired settings where accurate person-garment correspondence is required. These methods do not explicitly enforce person-garment alignment and fail to explain how correspondence emerges within Diffusion Transformers (DiTs). In this paper, we first analyze full 3D attention in DiT-based architecture and reveal that the person-garment correspondence critically depends on precise person-garment query-key matching within the full 3D attention. Building on this insight, we then introduce CORrespondence ALignment (CORAL), a DiT-based framework that explicitly aligns query-key matching with robust external correspondences. CORAL integrates two complementary components: a correspondence distillation loss that aligns reliable matches with person-garment attention, and an entropy minimization loss that sharpens the attention distribution. We further propose a VLM-based evaluation protocol to better reflect human preference. CORAL consistently improves over the baseline, enhancing both global shape transfer and local detail preservation. Extensive ablations validate our design choices. --- ### Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting Authors: Xinghong Fu, Yanhong Li, Georgios Papaioannou, Yoon Kim Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17634v2 Learning time series foundation models has been shown to be a promising approach for zero-shot time series forecasting across diverse time series domains. Insofar as scaling has been a critical driver of performance of foundation models in other modalities such as language and vision, much recent work on time series foundation modeling has focused on scaling. This has resulted in time series foundation models with hundreds of millions of parameters that are, while performant, inefficient and expensive to use in practice. This paper describes a simple recipe for learning efficient foundation models for zero-shot time series forecasting that are orders of magnitude smaller. We show that large-scale transformers are not necessary: small hybrid models that interleave long convolution and linear RNN layers (in particular DeltaNet layers) can match the performance of larger transformer-based models while being more than a hundred times smaller. We also describe several data augmentation and inference strategies that further improve performance. This recipe results in Reverso, a family of efficient time series foundation models for zero-shot forecasting that significantly push the performance-efficiency Pareto frontier. --- ### When to Trust the Cheap Check: Weak and Strong Verification for Reasoning Authors: Shayan Kiyani, Sima Noorani, George Pappas, Hamed Hassani Published: 2026-02-19 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.17633v1 Reasoning with LLMs increasingly unfolds inside a broader verification loop. Internally, systems use cheap checks, such as self-consistency or proxy rewards, which we call weak verification. Externally, users inspect outputs and steer the model through feedback until results are trustworthy, which we call strong verification. These signals differ sharply in cost and reliability: strong verification can establish trust but is resource-intensive, while weak verification is fast and scalable but noisy and imperfect. We formalize this tension through weak--strong verification policies, which decide when to accept or reject based on weak verification and when to defer to strong verification. We introduce metrics capturing incorrect acceptance, incorrect rejection, and strong-verification frequency. Over population, we show that optimal policies admit a two-threshold structure and that calibration and sharpness govern the value of weak verifiers. Building on this, we develop an online algorithm that provably controls acceptance and rejection errors without assumptions on the query stream, the language model, or the weak verifier. --- ### SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer Authors: Nathan Samuel de Lara, Florian Shkurti Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17632v3 Modern offline Reinforcement Learning (RL) methods find performant actor-critics, however, fine-tuning these actor-critics online with value-based RL algorithms typically causes immediate drops in performance. We provide evidence consistent with the hypothesis that, in the loss landscape, offline maxima for prior algorithms and online maxima are separated by low-performance valleys that gradient-based fine-tuning traverses. Following this, we present Score Matched Actor-Critic (SMAC), an offline RL method designed to learn actor-critics that transition to online value-based RL algorithms with no drop in performance. SMAC avoids valleys between offline and online maxima by regularizing the Q-function during the offline phase to respect a first-order derivative equality between the score of the policy and action-gradient of the Q-function. We experimentally demonstrate that SMAC converges to offline maxima that are connected to better online maxima via paths with monotonically increasing reward found by first-order optimization. SMAC achieves smooth transfer to Soft Actor-Critic and TD3 in 6/6 D4RL tasks. In 4/6 environments, it reduces regret by 34-58% over the best baseline. --- ### SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer Authors: Nathan Samuel de Lara, Florian Shkurti Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17632v2 Modern offline Reinforcement Learning (RL) methods find performant actor-critics, however, fine-tuning these actor-critics online with value-based RL algorithms typically causes immediate drops in performance. We provide evidence consistent with the hypothesis that, in the loss landscape, offline maxima for prior algorithms and online maxima are separated by low-performance valleys that gradient-based fine-tuning traverses. Following this, we present Score Matched Actor-Critic (SMAC), an offline RL method designed to learn actor-critics that transition to online value-based RL algorithms with no drop in performance. SMAC avoids valleys between offline and online maxima by regularizing the Q-function during the offline phase to respect a first-order derivative equality between the score of the policy and action-gradient of the Q-function. We experimentally demonstrate that SMAC converges to offline maxima that are connected to better online maxima via paths with monotonically increasing reward found by first-order optimization. SMAC achieves smooth transfer to Soft Actor-Critic and TD3 in 6/6 D4RL tasks. In 4/6 environments, it reduces regret by 34-58% over the best baseline. ---