# Research Papers — 2026-02 · bundle page 197 of 210

> Full-text markdown of papers #9801–9850 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/197
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/196.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/198.md)

### LoopViT: Scaling Visual ARC with Looped Transformers

Authors: Wen-Jie Shu, Xuerui Qiu, Rui-Jie Zhu, Harold Haodong Chen, Yexin Liu, Harry Yang
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02156v1

Recent advances in visual reasoning have leveraged vision transformers to tackle the ARC-AGI benchmark. However, we argue that the feed-forward architecture, where computational depth is strictly bound to parameter size, falls short of capturing the iterative, algorithmic nature of human induction. In this work, we propose a recursive architecture called Loop-ViT, which decouples reasoning depth from model capacity through weight-tied recurrence. Loop-ViT iterates a weight-tied Hybrid Block, combining local convolutions and global attention, to form a latent chain of thought. Crucially, we introduce a parameter-free Dynamic Exit mechanism based on predictive entropy: the model halts inference when its internal state ``crystallizes" into a low-uncertainty attractor. Empirical results on the ARC-AGI-1 benchmark validate this perspective: our 18M model achieves 65.8% accuracy, outperforming massive 73M-parameter ensembles. These findings demonstrate that adaptive iterative computation offers a far more efficient scaling axis for visual reasoning than simply increasing network width. The code is available at https://github.com/WenjieShu/LoopViT.

---

### Deep learning enables urban change profiling through alignment of historical maps

Authors: Sidi Wu, Yizi Chen, Maurizio Gribaudi, Konrad Schindler, Clément Mallet, Julien Perret, Lorenz Hurni
Published: 2026-02-02
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2602.02154v1

Prior to modern Earth observation technologies, historical maps provide a unique record of long-term urban transformation and offer a lens on the evolving identity of cities. However, extracting consistent and fine-grained change information from historical map series remains challenging due to spatial misalignment, cartographic variation, and degrading document quality, limiting most analyses to small-scale or qualitative approaches. We propose a fully automated, deep learning-based framework for fine-grained urban change analysis from large collections of historical maps, built on a modular design that integrates dense map alignment, multi-temporal object detection, and change profiling. This framework shifts the analysis of historical maps from ad hoc visual comparison toward systematic, quantitative characterization of urban change. Experiments demonstrate the robust performance of the proposed alignment and object detection methods. Applied to Paris between 1868 and 1937, the framework reveals the spatial and temporal heterogeneity in urban transformation, highlighting its relevance for research in the social sciences and humanities. The modular design of our framework further supports adaptation to diverse cartographic contexts and downstream applications.

---

### Learning Beyond the Gaussian Data: Learning Dynamics of Neural Networks on an Expressive and Cumulant-Controllable Data Model

Authors: Onat Ure, Samet Demir, Zafer Dogan
Published: 2026-02-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.02153v1

We study the effect of high-order statistics of data on the learning dynamics of neural networks (NNs) by using a moment-controllable non-Gaussian data model. Considering the expressivity of two-layer neural networks, we first construct the data model as a generative two-layer NN where the activation function is expanded by using Hermite polynomials. This allows us to achieve interpretable control over high-order cumulants such as skewness and kurtosis through the Hermite coefficients while keeping the data model realistic. Using samples generated from the data model, we perform controlled online learning experiments with a two-layer NN. Our results reveal a moment-wise progression in training: networks first capture low-order statistics such as mean and covariance, and progressively learn high-order cumulants. Finally, we pretrain the generative model on the Fashion-MNIST dataset and leverage the generated samples for further experiments. The results of these additional experiments confirm our conclusions and show the utility of the data model in a real-world scenario. Overall, our proposed approach bridges simplified data assumptions and practical data complexity, which offers a principled framework for investigating distributional effects in machine learning and signal processing.

---

### Revisiting Adaptive Rounding with Vectorized Reparameterization for LLM Quantization

Authors: Yuli Zhou, Qingxuan Chen, Luca Benini, Guolei Sun, Yawei Li
Published: 2026-02-02
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.02151v1

Adaptive Rounding has emerged as an alternative to round-to-nearest (RTN) for post-training quantization by enabling cross-element error cancellation. Yet, dense and element-wise rounding matrices are prohibitively expensive for billion-parameter large language models (LLMs). We revisit adaptive rounding from an efficiency perspective and propose VQRound, a parameter-efficient optimization framework that reparameterizes the rounding matrix into a compact codebook. Unlike low-rank alternatives, VQRound minimizes the element-wise worst-case error under $L_\infty$ norm, which is critical for handling heavy-tailed weight distributions in LLMs. Beyond reparameterization, we identify rounding initialization as a decisive factor and develop a lightweight end-to-end finetuning pipeline that optimizes codebooks across all layers using only 128 samples. Extensive experiments on OPT, LLaMA, LLaMA2, and Qwen3 models demonstrate that VQRound achieves better convergence than traditional adaptive rounding at the same number of steps while using as little as 0.2% of the trainable parameters. Our results show that adaptive rounding can be made both scalable and fast-fitting. The code is available at https://github.com/zhoustan/VQRound.

---

### ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning

Authors: Chu Zhao, Enneng Yang, Yuting Liu, Jianzhe Zhao, Guibing Guo
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02150v2

Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduce overhead and improve exploration, prior work introduces tree structured rollouts, which share reasoning prefixes and branch at key nodes to improve sampling efficiency. However, this paradigm still faces two challenges: (1) high entropy branching can trigger rollout collapse, where the branching budget concentrates on a few trajectories with consecutive high-entropy segments, rapidly reducing the number of effective branches; (2) early pseudo-labels are noisy and biased, which can induce self-reinforcing overfitting, causing the policy to sharpen prematurely and suppress exploration. To address these issues, we propose Entropy Confidence Hybrid Group Relative Policy Optimization (ECHO). During rollout, ECHO jointly leverages local entropy and group level confidence to adaptively control branch width, and further introduces online confidence-based pruning to terminate persistently low confidence branches, avoiding high entropy traps and mitigating collapse. During policy updates, ECHO employs confidence adaptive clipping and an entropy confidence hybrid advantage shaping approach to enhance training robustness and mitigate early stage bias. Experiments demonstrate that ECHO achieves consistent gains on multiple mathematical and visual reasoning benchmarks, and generalizes more effectively under a limited rollout budget.

---

### Back to the Future: Look-ahead Augmentation and Parallel Self-Refinement for Time Series Forecasting

Authors: Sunho Kim, Susik Yoon
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02146v1

Long-term time series forecasting (LTSF) remains challenging due to the trade-off between parallel efficiency and sequential modeling of temporal coherence. Direct multi-step forecasting (DMS) methods enable fast, parallel prediction of all future horizons but often lose temporal consistency across steps, while iterative multi-step forecasting (IMS) preserves temporal dependencies at the cost of error accumulation and slow inference. To bridge this gap, we propose Back to the Future (BTTF), a simple yet effective framework that enhances forecasting stability through look-ahead augmentation and self-corrective refinement. Rather than relying on complex model architectures, BTTF revisits the fundamental forecasting process and refines a base model by ensembling the second-stage models augmented with their initial predictions. Despite its simplicity, our approach consistently improves long-horizon accuracy and mitigates the instability of linear forecasting models, achieving accuracy gains of up to 58% and demonstrating stable improvements even when the first-stage model is trained under suboptimal conditions. These results suggest that leveraging model-generated forecasts as augmentation can be a simple yet powerful way to enhance long-term prediction, even without complex architectures.

---

### Learning Generative Selection for Best-of-N

Authors: Shubham Toshniwal, Aleksander Ficek, Siddhartha Jain, Wei Du, Vahid Noroozi, Sadegh Mahdavi, Somshubra Majumdar, Igor Gitman
Published: 2026-02-02
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.02143v1

Scaling test-time compute via parallel sampling can substantially improve LLM reasoning, but is often limited by Best-of-N selection quality. Generative selection methods, such as GenSelect, address this bottleneck, yet strong selection performance remains largely limited to large models. We show that small reasoning models can acquire strong GenSelect capabilities through targeted reinforcement learning. To this end, we synthesize selection tasks from large-scale math and code instruction datasets by filtering to instances with both correct and incorrect candidate solutions, and train 1.7B-parameter models with DAPO to reward correct selections. Across math (AIME24, AIME25, HMMT25) and code (LiveCodeBench) reasoning benchmarks, our models consistently outperform prompting and majority-voting baselines, often approaching or exceeding much larger models. Moreover, these gains generalize to selecting outputs from stronger models despite training only on outputs from weaker models. Overall, our results establish reinforcement learning as a scalable way to unlock strong generative selection in small models, enabling efficient test-time scaling.

---

### FD-VLA: Force-Distilled Vision-Language-Action Model for Contact-Rich Manipulation

Authors: Ruiteng Zhao, Wenshuo Wang, Yicheng Ma, Xiaocong Li, Francis E. H. Tay, Marcelo H. Ang, Haiyue Zhu
Published: 2026-02-02
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.02142v2

Force sensing is a crucial modality for Vision-Language-Action (VLA) frameworks, as it enables fine-grained perception and dexterous manipulation in contact-rich tasks. We present Force-Distilled VLA (FD-VLA), a novel framework that integrates force awareness into contact-rich manipulation without relying on physical force sensors. The core of our approach is a Force Distillation Module (FDM), which distills force by mapping a learnable query token, conditioned on visual observations and robot states, into a predicted force token aligned with the latent representation of actual force signals. During inference, this distilled force token is injected into the pretrained VLM, enabling force-aware reasoning while preserving the integrity of its vision-language semantics. This design provides two key benefits: first, it allows practical deployment across a wide range of robots that lack expensive or fragile force-torque sensors, thereby reducing hardware cost and complexity; second, the FDM introduces an additional force-vision-state fusion prior to the VLM, which improves cross-modal alignment and enhances perception-action robustness in contact-rich scenarios. Surprisingly, our physical experiments show that the distilled force token outperforms direct sensor force measurements as well as other baselines, which highlights the effectiveness of this force-distilled VLA approach.

---

### Quantifying the Gap between Understanding and Generation within Unified Multimodal Models

Authors: Chenlong Wang, Yuhang Chen, Zhihan Hu, Dongping Chen, Wenhu Chen, Sarah Wiegreffe, Tianyi Zhou
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02140v1

Recent advances in unified multimodal models (UMM) have demonstrated remarkable progress in both understanding and generation tasks. However, whether these two capabilities are genuinely aligned and integrated within a single model remains unclear. To investigate this question, we introduce GapEval, a bidirectional benchmark designed to quantify the gap between understanding and generation capabilities, and quantitatively measure the cognitive coherence of the two "unified" directions. Each question can be answered in both modalities (image and text), enabling a symmetric evaluation of a model's bidirectional inference capability and cross-modal consistency. Experiments reveal a persistent gap between the two directions across a wide range of UMMs with different architectures, suggesting that current models achieve only surface-level unification rather than deep cognitive convergence of the two. To further explore the underlying mechanism, we conduct an empirical study from the perspective of knowledge manipulation to illustrate the underlying limitations. Our findings indicate that knowledge within UMMs often remains disjoint. The capability emergence and knowledge across modalities are unsynchronized, paving the way for further exploration.

---

### EvoMU: Evolutionary Machine Unlearning

Authors: Pawel Batorski, Paul Swoboda
Published: 2026-02-02
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.02139v2

Machine unlearning aims to unlearn specified training data (e.g. sensitive or copyrighted material). A prominent approach is to fine-tune an existing model with an unlearning loss that retains overall utility. The space of suitable unlearning loss functions is vast, making the search for an optimal loss function daunting. Additionally, there might not even exist a universally optimal loss function: differences in the structure and overlap of the forget and retain data can cause a loss to work well in one setting but over-unlearn or under-unlearn in another. Our approach EvoMU tackles these two challenges simultaneously. An evolutionary search procedure automatically finds task-specific losses in the vast space of possible unlearning loss functions. This allows us to find dataset-specific losses that match or outperform existing losses from the literature, without the need for a human-in-the-loop. This work is therefore an instance of automatic scientific discovery, a.k.a. an AI co-scientist. In contrast to previous AI co-scientist works, we do so on a budget: We achieve SotA results using a small 4B parameter model (Qwen3-4B-Thinking), showing the potential of AI co-scientists with limited computational resources. Our experimental evaluation shows that we surpass previous loss-based unlearning formulations on TOFU-5%, TOFU-10%, MUSE and WMDP by synthesizing novel unlearning losses. Our code is available at https://github.com/Batorskq/EvoMU.

---

### CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems

Authors: Zongyi Lyu, Zhenlan Ji, Songqiang Chen, Liwen Wang, Yuheng Huang, Shuai Wang, Shing-Chi Cheung
Published: 2026-02-02
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.02138v3

Despite the remarkable success that Multi-Agent Code Generation Systems (MACGS) have achieved, the inherent complexity of multi-agent architectures produces substantial volumes of intermediate outputs. To date, the individual importance of these intermediate outputs to the system correctness remains opaque, which impedes targeted optimization of MACGS designs. To address this challenge, we propose CAM, the first \textbf{C}ausality-based \textbf{A}nalysis framework for \textbf{M}ACGS that systematically quantifies the contribution of different intermediate features for system correctness. By comprehensively categorizing intermediate outputs and systematically simulating realistic errors on intermediate features, we identify the important features for system correctness and aggregate their importance rankings. We conduct extensive empirical analysis on the identified importance rankings. Our analysis reveals intriguing findings: first, we uncover context-dependent features\textemdash features whose importance emerges mainly through interactions with other features, revealing that quality assurance for MACGS should incorporate cross-feature consistency checks; second, we reveal that hybrid backend MACGS with different backend LLMs assigned according to their relative strength achieves up to 7.3\% Pass@1 improvement, underscoring hybrid architectures as a promising direction for future MACGS design. We further demonstrate CAM's practical utility through two applications: (1) failure repair which achieves a 73.6\% success rate by optimizing top-3 importance-ranked features and (2) feature pruning that reduces up to 33.6\% intermediate token consumption while maintaining generation performance. Our work provides actionable insights for MACGS design and deployment, establishing causality analysis as a powerful approach for understanding and improving MACGS.

---

### DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations

Authors: Minghao Li, Ruihang Wang, Rui Tan, Yonggang Wen
Published: 2026-02-02
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2602.02137v3

Modern data centers (DCs) hosting artificial intelligence (AI)-dedicated devices operate at high power densities with rapidly varying workloads, making minute-level adaptation essential for safe and energy-efficient operation. However, manually designing piecewise deep reinforcement learning (DRL) agents cannot keep pace with frequent dynamics shifts and service-level agreement (SLA) changes of an evolving DC. This specification-to-policy lag causes a lack of timely, effective control policies, which may lead to service outages. To bridge the gap, we present DCoPilot, a hybrid framework for generative control policies in dynamic DC operation. DCoPilot synergizes two distinct generative paradigms, i.e., a large language model (LLM) that performs symbolic generation of structured reward forms, and a hypernetwork that conducts parametric generation of policy weights. DCoPilot operates through three coordinated phases: (i) simulation scale-up, which stress-tests reward candidates across diverse simulation-ready (SimReady) scenes; (ii) meta policy distillation, where a hypernetwork is trained to output policy weights conditioned on SLA and scene embeddings; and (iii) online adaptation, enabling zero-shot policy generation in response to updated specifications. Evaluated across five control task families spanning diverse DC components, DCoPilot achieves near-zero constraint violations and outperforms all baselines across specification variations. Ablation studies validate the effectiveness of LLM-based unified reward generation in enabling stable hypernetwork convergence.

---

### Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning Models

Authors: Yingsha Xie, Tiansheng Huang, Enneng Yang, Rui Min, Wenjie Lu, Xiaochun Cao, Naiqiang Tan, Li Shen
Published: 2026-02-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02136v1

Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety alignment for an LRM are usually constructed by distilling safety reasoning traces and answers from an external LRM or human labeler. However, such reasoning traces and answers exhibit a distributional gap with the target LRM that needs alignment, and we conjecture such distributional gap is the culprit leading to significant degradation of reasoning ability of the target LRM. Driven by this hypothesis, we propose a safety alignment dataset construction method, dubbed DGR. DGR transforms and refines an existing out-of-distributional safety reasoning dataset to be aligned with the target's LLM inner distribution. Experimental results demonstrate that i) DGR effectively mitigates the safety tax while maintaining safety performance across all baselines, i.e., achieving \textbf{+30.2\%} on DirectRefusal and \textbf{+21.2\%} on R1-ACT improvement in average reasoning accuracy compared to Vanilla SFT; ii) the degree of reasoning degradation correlates with the extent of distribution shift, suggesting that bridging this gap is central to preserving capabilities. Furthermore, we find that safety alignment in LRMs may primarily function as a mechanism to activate latent knowledge, as a mere \textbf{10} samples are sufficient for activating effective refusal behaviors. These findings not only emphasize the importance of distributional consistency but also provide insights into the activation mechanism of safety in reasoning models.

---

### A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse

Authors: Moongyu Jeon, Sangwoo Shin, BumJun Kim, Kyelim Lee, Albert No
Published: 2026-02-02
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.02133v2

Autoregressive language models (ARMs) suffer from the reversal curse: after learning ''$A$ is $B$,'' they often fail on the reverse query ''$B$ is $A$.'' Masked diffusion language models (MDMs) exhibit this failure in a much weaker form, but the underlying reason has remained unclear. A common explanation attributes this mitigation to their any-order masked training objective. However, observing ''$(\mathbf{M})$ is $B$'' during training teaches recovery of $A$ from $B$ in one positional configuration, and does not by itself explain why the learned evidence should transfer to the reverse prompt ''$B$ is $(\mathbf{M})$.'' We provide a theoretical analysis showing that this transfer arises from a parameter-level coupling between forward and reverse positional conditionals: shared Transformer parameters store token-pair evidence, while relative positional encodings route attention through queries and keys without changing the value-side evidence being retrieved. In a one-layer MDM, we prove that forward masked training strengthens evidence that is reusable in reverse queries, induces correlated forward--reverse attention routes, and yields a positively aligned shared-storage gradient component that decreases the reverse loss to first order. Controlled one-layer experiments and large-scale LLaDA/Dream experiments verify these signatures and show that they translate into improved reverse prediction.

---

### There Is More to Refusal in Large Language Models than a Single Direction

Authors: Faaiz Joad, Majd Hawasly, Sabri Boughorbel, Nadir Durrani, Husrev Taha Sencar
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02132v2

Prior work argues that refusal in large language models is mediated by a single direction, enabling steering and abliteration. We show that this account is incomplete: across diverse refusal and non-compliance categories, refusal behaviors correspond to geometrically distinct directions in activation space. Yet activation steering along any refusal-related direction produces nearly identical refusal--over-refusal trade-offs, acting as a shared one-dimensional control knob. Thus, different directions primarily affect not whether the model refuses, but how it refuses. Using sparse autoencoders, we uncover a structured internal representation of refusal: a reusable core of shared refusal latents supplemented by style- and domain-specific latents. Linear interventions collapse this structure into uniform behavioral control, flattening mechanistic differences across refusal types. Our results reconcile the apparent simplicity of refusal steering with the diversity of refusal behaviors, and clarify the limits of linear interpretability for aligned model behavior.

---

### There Is More to Refusal in Large Language Models than a Single Direction

Authors: Faaiz Joad, Majd Hawasly, Sabri Boughorbel, Nadir Durrani, Husrev Taha Sencar
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02132v1

Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and ablation. We show that this account is incomplete. Across eleven categories of refusal and non-compliance, including safety, incomplete or unsupported requests, anthropomorphization, and over-refusal, we find that these refusal behaviors correspond to geometrically distinct directions in activation space. Yet despite this diversity, linear steering along any refusal-related direction produces nearly identical refusal to over-refusal trade-offs, acting as a shared one-dimensional control knob. The primary effect of different directions is not whether the model refuses, but how it refuses.

---

### Eliminating Registration Bias in Synthetic CT Generation: A Physics-Based Simulation Framework

Authors: Lukas Zimmermann, Michael Rauter, Maximilian Schmid, Dietmar Georg, Barbara Knäusl
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02130v1

Supervised synthetic CT generation from CBCT requires registered training pairs, yet perfect registration between separately acquired scans remains unattainable. This registration bias propagates into trained models and corrupts standard evaluation metrics. This may suggest that superior benchmark performance indicates better reproduction of registration artifacts rather than anatomical fidelity. We propose physics-based CBCT simulation to provide geometrically aligned training pairs by construction, combined with evaluation using geometric alignment metrics against input CBCT rather than biased ground truth. On two independent pelvic datasets, models trained on synthetic data achieved superior geometric alignment (Normalized Mutual Information: 0.31 vs 0.22) despite lower conventional intensity scores. Intensity metrics showed inverted correlations with clinical assessment for deformably registered data, while Normalized Mutual Information consistently predicted observer preference across registration methodologies (rho = 0.31, p < 0.001). Clinical observers preferred synthetic-trained outputs in 87% of cases, demonstrating that geometric fidelity, not intensity agreement with biased ground truth, aligns with clinical requirements.

---

### Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics

Authors: Nima Shoghi, Yuxuan Liu, Yuning Shen, Rob Brekelmans, Pan Li, Quanquan Gu
Published: 2026-02-02
Categories: cs.LG, cs.AI, physics.bio-ph, q-bio.BM, q-bio.QM
arXiv: https://arxiv.org/abs/2602.02128v2

Molecular dynamics (MD) simulations remain the gold standard for studying protein dynamics, but their computational cost limits access to biologically relevant timescales. Recent generative models have shown promise in accelerating simulations, yet they struggle with long-horizon generation due to architectural constraints, error accumulation, and inadequate modeling of spatio-temporal dynamics. We present STAR-MD (Spatio-Temporal Autoregressive Rollout for Molecular Dynamics), a scalable SE(3)-equivariant diffusion model that generates physically plausible protein trajectories over microsecond timescales. Our key innovation is a causal diffusion transformer with joint spatio-temporal attention that efficiently captures complex space-time dependencies while avoiding the memory bottlenecks of existing methods. On the standard ATLAS benchmark, STAR-MD achieves state-of-the-art performance across all metrics--substantially improving conformational coverage, structural validity, and dynamic fidelity compared to previous methods. STAR-MD successfully extrapolates to generate stable microsecond-scale trajectories where baseline methods fail catastrophically, maintaining high structural quality throughout the extended rollout. Our comprehensive evaluation reveals severe limitations in current models for long-horizon generation, while demonstrating that STAR-MD's joint spatio-temporal modeling enables robust dynamics simulation at biologically relevant timescales, paving the way for accelerated exploration of protein function.

---

### Two-Stage Grid Optimization for Group-wise Quantization of LLMs

Authors: Junhan Kim, Gukryeol Lee, Seungwoo Son, Jeewook Kim, Yongkweon Jeon
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02126v1

Group-wise quantization is an effective strategy for mitigating accuracy degradation in low-bit quantization of large language models (LLMs). Among existing methods, GPTQ has been widely adopted due to its efficiency; however, it neglects input statistics and inter-group correlations when determining group scales, leading to a mismatch with its goal of minimizing layer-wise reconstruction loss. In this work, we propose a two-stage optimization framework for group scales that explicitly minimizes the layer-wise reconstruction loss. In the first stage, performed prior to GPTQ, we initialize each group scale to minimize the group-wise reconstruction loss, thereby incorporating input statistics. In the second stage, we freeze the integer weights obtained via GPTQ and refine the group scales to minimize the layer-wise reconstruction loss. To this end, we employ the coordinate descent algorithm and derive a closed-form update rule, which enables efficient refinement without costly numerical optimization. Notably, our derivation incorporates the quantization errors from preceding layers to prevent error accumulation. Experimental results demonstrate that our method consistently enhances group-wise quantization, achieving higher accuracy with negligible overhead.

---

### Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomalies

Authors: Olga Graf, Dhrupal Patel, Peter Groß, Charlotte Lempp, Matthias Hein, Fabian Heinemann
Published: 2026-02-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.02124v2

Drug-induced toxicity is a leading cause of preclinical and early-clinical failure, making early detection critical. Histopathology is the gold standard for toxicity assessment but relies on expert pathologists, creating a bottleneck for large-scale screening. We introduce an AI-based anomaly detection framework for whole-slide images (WSIs) of rodent liver that identifies healthy tissue and known pathologies (anomalies) and flags samples without training data as out-of-distribution (OOD). We evaluate OOD detection on two held-out categories: apoptosis (single-cell, near-OOD) and staining/processing artifacts (heterogeneous, far-OOD). We build a novel pixelwise-annotated dataset and fine-tune a pre-trained Vision Transformer (DINOv2) via Low-Rank Adaptation (LoRA) for segmentation, then use the Mahalanobis distance for OOD detection with class-specific thresholds. Optimizing the false positive rate subject to a predefined constraint on the false negative rate yields only 0.16% of pathological tissue classified as healthy and 0.35% of healthy tissue classified as pathological. Our false negative rate does not penalise cross-type errors, reflecting the safety-first objective of never overlooking a lesion; under the stricter correct-class criterion our method assigns 93.93% of ID and 89.38% of OOD findings to their own class. The study demonstrates technical feasibility of pixel-level anomaly detection for mouse liver histopathology, indicating possible applications in improving preclinical workflows and drug development efficiency.

---

### MLV-Edit: Towards Consistent and Highly Efficient Editing for Minute-Level Videos

Authors: Yangyi Cao, Yuanhang Li, Lan Chen, Qi Mao
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02123v2

We propose MLV-Edit, a training-free, flow-based framework that address the unique challenges of minute-level video editing. While existing techniques excel in short-form video manipulation, scaling them to long-duration videos remains challenging due to prohibitive computational overhead and the difficulty of maintaining global temporal consistency across thousands of frames. To address this, MLV-Edit employs a divide-and-conquer strategy for segment-wise editing, facilitated by two core modules: Velocity Blend rectifies motion inconsistencies at segment boundaries by aligning the flow fields of adjacent chunks, eliminating flickering and boundary artifacts commonly observed in fragmented video processing; and Attention Sink anchors local segment features to global reference frames, effectively suppressing cumulative structural drift. Extensive quantitative and qualitative experiments demonstrate that MLV-Edit consistently outperforms state-of-the-art methods in terms of temporal stability and semantic fidelity.

---

### The Maximum von Neumann Entropy Principle: Theory and Applications in Machine Learning

Authors: Youqi Wu, Farzan Farnia
Published: 2026-02-02
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2602.02117v1

Von Neumann entropy (VNE) is a fundamental quantity in quantum information theory and has recently been adopted in machine learning as a spectral measure of diversity for kernel matrices and kernel covariance operators. While maximizing VNE under constraints is well known in quantum settings, a principled analogue of the classical maximum entropy framework, particularly its decision theoretic and game theoretic interpretation, has not been explicitly developed for VNE in data driven contexts. In this paper, we extend the minimax formulation of the maximum entropy principle due to Grünwald and Dawid to the setting of von Neumann entropy, providing a game-theoretic justification for VNE maximization over density matrices and trace-normalized positive semidefinite operators. This perspective yields a robust interpretation of maximum VNE solutions under partial information and clarifies their role as least committed inferences in spectral domains. We then illustrate how the resulting Maximum VNE principle applies to modern machine learning problems by considering two representative applications, selecting a kernel representation from multiple normalized embeddings via kernel-based VNE maximization, and completing kernel matrices from partially observed entries. These examples demonstrate how the proposed framework offers a unifying information-theoretic foundation for VNE-based methods in kernel learning.

---

### Enhancing Diffusion-Based Quantitatively Controllable Image Generation via Matrix-Form EDM and Adaptive Vicinal Training

Authors: Xin Ding, Yun Chen, Sen Zhang, Kao Zhang, Nenglun Chen, Peibei Cao, Yongwei Wang, Fei Wu
Published: 2026-02-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.02114v1

Continuous Conditional Diffusion Model (CCDM) is a diffusion-based framework designed to generate high-quality images conditioned on continuous regression labels. Although CCDM has demonstrated clear advantages over prior approaches across a range of datasets, it still exhibits notable limitations and has recently been surpassed by a GAN-based method, namely CcGAN-AVAR. These limitations mainly arise from its reliance on an outdated diffusion framework and its low sampling efficiency due to long sampling trajectories. To address these issues, we propose an improved CCDM framework, termed iCCDM, which incorporates the more advanced \textit{Elucidated Diffusion Model} (EDM) framework with substantial modifications to improve both generation quality and sampling efficiency. Specifically, iCCDM introduces a novel matrix-form EDM formulation together with an adaptive vicinal training strategy. Extensive experiments on four benchmark datasets, spanning image resolutions from $64\times64$ to $256\times256$, demonstrate that iCCDM consistently outperforms existing methods, including state-of-the-art large-scale text-to-image diffusion models (e.g., Stable Diffusion 3, FLUX.1, and Qwen-Image), achieving higher generation quality while significantly reducing sampling cost.

---

### Training-free score-based diffusion for parameter-dependent stochastic dynamical systems

Authors: Minglei Yang, Sicheng He
Published: 2026-02-02
Categories: stat.ML, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2602.02113v1

Simulating parameter-dependent stochastic differential equations (SDEs) presents significant computational challenges, as separate high-fidelity simulations are typically required for each parameter value of interest. Despite the success of machine learning methods in learning SDE dynamics, existing approaches either require expensive neural network training for score function estimation or lack the ability to handle continuous parameter dependence. We present a training-free conditional diffusion model framework for learning stochastic flow maps of parameter-dependent SDEs, where both drift and diffusion coefficients depend on physical parameters. The key technical innovation is a joint kernel-weighted Monte Carlo estimator that approximates the conditional score function using trajectory data sampled at discrete parameter values, enabling interpolation across both state space and the continuous parameter domain. Once trained, the resulting generative model produces sample trajectories for any parameter value within the training range without retraining, significantly accelerating parameter studies, uncertainty quantification, and real-time filtering applications. The performance of the proposed approach is demonstrated via three numerical examples of increasing complexity, showing accurate approximation of conditional distributions across varying parameter values.

---

### Unifying Masked Diffusion Models with Various Generation Orders and Beyond

Authors: Chunsan Hong, Sanghyun Lee, Jong Chul Ye
Published: 2026-02-02
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.02112v2

Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality depends critically on the generation order. Prior work either hard-codes an ordering (e.g., blockwise left-to-right) or learns an ordering policy for a pretrained MDM, which incurs extra cost and can yield suboptimal solutions due to the two-stage optimization. Motivated by this, we propose order-expressive masked diffusion model (OeMDM) for a broad class of diffusion generative processes with various generation orders, enabling the interpretation of MDM, ARM, and block diffusion in a single framework. Furthermore, building on OeMDM, we introduce learnable-order masked diffusion model (LoMDM), which jointly learns the generation ordering and diffusion backbone through a single objective from scratch, enabling the diffusion model to generate text in context-dependent ordering. Empirically, we confirm that LoMDM outperforms various discrete diffusion models across multiple language modeling benchmarks.

---

### An Empirical Study of World Model Quantization

Authors: Zhongqian Fu, Tianyi Zhao, Kai Han, Hang Zhou, Xinghao Chen, Yunhe Wang
Published: 2026-02-02
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.02110v1

World models learn an internal representation of environment dynamics, enabling agents to simulate and reason about future states within a compact latent space for tasks such as planning, prediction, and inference. However, running world models rely on hevay computational cost and memory footprint, making model quantization essential for efficient deployment. To date, the effects of post-training quantization (PTQ) on world models remain largely unexamined. In this work, we present a systematic empirical study of world model quantization using DINO-WM as a representative case, evaluating diverse PTQ methods under both weight-only and joint weight-activation settings. We conduct extensive experiments on different visual planning tasks across a wide range of bit-widths, quantization granularities, and planning horizons up to 50 iterations. Our results show that quantization effects in world models extend beyond standard accuracy and bit-width trade-offs: group-wise weight quantization can stabilize low-bit rollouts, activation quantization granularity yields inconsistent benefits, and quantization sensitivity is highly asymmetric between encoder and predictor modules. Moreover, aggressive low-bit quantization significantly degrades the alignment between the planning objective and task success, leading to failures that cannot be remedied by additional optimization. These findings reveal distinct quantization-induced failure modes in world model-based planning and provide practical guidance for deploying quantized world models under strict computational constraints. The code will be available at https://github.com/huawei-noah/noah-research/tree/master/QuantWM.

---

### Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts

Authors: Wenhao Li, Daohai Yu, Gen Luo, Yuxin Zhang, Fei Chao, Rongrong Ji, Yifan Wu, Jiaxin Liu, Ziyang Gong, Zimu Liao
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02108v4

Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whose memory footprints scale linearly with sequence length. We introduce OOMB, a highly memory-efficient training system that directly confronts this barrier. Our approach employs a chunk-recurrent training framework with on-the-fly activation recomputation, which maintains a constant activation memory footprint (O(1)) and shifts the primary bottleneck to the growing KV cache. To manage the KV cache, OOMB integrates a suite of synergistic optimizations: a paged memory manager for both the KV cache and its gradients to eliminate fragmentation, asynchronous CPU offloading to hide data transfer latency, and page-level sparse attention to reduce both computational complexity and communication overhead. The synergy of these techniques yields exceptional efficiency. Our empirical results show that for every additional 10K tokens of context, the end-to-end training memory overhead increases by a mere 10MB for Qwen2.5-7B. This allows training Qwen2.5-7B with a 4M-token context on a single H200 GPU, a feat that would otherwise require a large cluster using context parallelism. This work represents a substantial advance in resource efficiency for long-context LLM training. The source code is available at https://github.com/wenhaoli-xmu/OOMB.

---

### Teacher-Guided Student Self-Knowledge Distillation Using Diffusion Model

Authors: Yu Wang, Chuanguang Yang, Zhulin An, Weilun Feng, Jiarui Zhao, Chengqing Yu, Libo Huang, Boyu Diao, Yongjun Xu
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02107v1

Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss functions. However, due to the difference in feature distributions between the teacher and student, the student model may learn incompatible information from the teacher. To address this problem, we propose teacher-guided student Diffusion Self-KD, dubbed as DSKD. Instead of the direct teacher-student alignment, we leverage the teacher classifier to guide the sampling process of denoising student features through a light-weight diffusion model. We then propose a novel locality-sensitive hashing (LSH)-guided feature distillation method between the original and denoised student features. The denoised student features encapsulate teacher knowledge and could be regarded as a teacher role. In this way, our DSKD method could eliminate discrepancies in mapping manners and feature distributions between the teacher and student, while learning meaningful knowledge from the teacher. Experiments on visual recognition tasks demonstrate that DSKD significantly outperforms existing KD methods across various models and datasets. Our code is attached in supplementary material.

---

### Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs

Authors: Shaltiel Shmidman, Avi Shmidman, Amir DN Cohen, Moshe Koppel
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02104v1

Open-weight LLMs have been released by frontier labs; however, sovereign Large Language Models (for languages other than English) remain low in supply yet high in demand. Training large language models (LLMs) for low-resource languages such as Hebrew poses unique challenges. In this paper, we introduce Dicta-LM 3.0: an open-weight collection of LLMs trained on substantially-sized corpora of Hebrew and English texts. The model is released in three sizes: 24B - adapted from the Mistral-Small-3.1 base model, 12B - adapted from the NVIDIA Nemotron Nano V2 model, and 1.7B - adapted from the Qwen3-1.7B base model. We are releasing multiple variants of each model, each with a native context length of 65k tokens; base model and chat model with tool-calling support. To rigorously evaluate our models, we introduce a new benchmark suite for evaluation of Hebrew chat-LLMs, covering a diverse set of tasks including Translation, Summarization, Winograd, Israeli Trivia, and Diacritization (nikud). Our work not only addresses the intricacies of training LLMs in low-resource languages but also proposes a framework that can be leveraged for adapting other LLMs to various non-English languages, contributing to the broader field of multilingual NLP.

---

### How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning

Authors: Liyan Xu, Mo Yu, Fandong Meng, Jie Zhou
Published: 2026-02-02
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.02103v2

Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent evidence presents a tension: hidden states appear to already encode future reasoning before CoT fully unfolds, while explicit steps still remain crucial for tasks requiring compositional computation. To deepen the understanding between LLM's internal states and its verbalized reasoning trajectories, we investigate the latent planning strength of LLMs, through our probing method, Tele-Lens, applying to hidden states across diverse task domains. Our empirical results indicate that LLMs exhibit a myopic horizon, primarily conducting incremental transitions without precise global planning. Leveraging this characteristic, we propose a hypothesis on enhancing uncertainty estimation of CoT, which we validate that a sparse set of pivot positions can effectively represent the uncertainty of the entire path. We further underscore the significance of exploiting CoT dynamics, and demonstrate that automatic recognition of CoT bypass can be achieved without performance degradation. Our code, data and models are released at https://github.com/lxucs/tele-lens.

---

### The Verification Crisis: Expert Perceptions of GenAI Disinformation and the Case for Reproducible Provenance

Authors: Alexander Loth, Martin Kappes, Marc-Oliver Pahl
Published: 2026-02-02
Categories: cs.CY, cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2602.02100v1

The growth of Generative Artificial Intelligence (GenAI) has shifted disinformation production from manual fabrication to automated, large-scale manipulation. This article presents findings from the first wave of a longitudinal expert perception survey (N=21) involving AI researchers, policymakers, and disinformation specialists. It examines the perceived severity of multimodal threats -- text, image, audio, and video -- and evaluates current mitigation strategies. Results indicate that while deepfake video presents immediate "shock" value, large-scale text generation poses a systemic risk of "epistemic fragmentation" and "synthetic consensus," particularly in the political domain. The survey reveals skepticism about technical detection tools, with experts favoring provenance standards and regulatory frameworks despite implementation barriers. GenAI disinformation research requires reproducible methods. The current challenge is measurement: without standardized benchmarks and reproducibility checklists, tracking or countering synthetic media remains difficult. We propose treating information integrity as an infrastructure with rigor in data provenance and methodological reproducibility.

---

### Think Dense, Not Long: Dynamic Decoupled Conditional Advantage for Efficient Reasoning

Authors: Keqin Peng, Yuanxin Ouyang, Xuebo Liu, Zhiliang Tian, Ruijian Han, Yancheng Yuan, Liang Ding
Published: 2026-02-02
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.02099v1

Reinforcement Learning with Verifiable Rewards (RLVR) can elicit strong multi-step reasoning, yet it often encourages overly verbose traces. Moreover, naive length penalties in group-relative optimization can severely hurt accuracy. We attribute this failure to two structural issues: (i) Dilution of Length Baseline, where incorrect responses (with zero length reward) depress the group baseline and over-penalize correct solutions; and (ii) Difficulty-Penalty Mismatch, where a static penalty cannot adapt to problem difficulty, suppressing necessary reasoning on hard instances while leaving redundancy on easy ones. We propose Dynamic Decoupled Conditional Advantage (DDCA) to decouple efficiency optimization from correctness. DDCA computes length advantages conditionally within the correct-response cluster to eliminate baseline dilution, and dynamically scales the penalty strength using the group pass rate as a proxy for difficulty. Experiments on GSM8K, MATH500, AMC23, and AIME25 show that DDCA consistently improves the efficiency--accuracy trade-off relative to adaptive baselines, reducing generated tokens by approximately 60% on simpler tasks (e.g., GSM8K) versus over 20% on harder benchmarks (e.g., AIME25), thereby maintaining or improving accuracy. Code is available at https://github.com/alphadl/DDCA.

---

### Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning

Authors: Yannik Schnitzer, Mathias Jackermeier, Alessandro Abate, David Parker
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02098v2

Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progress, existing approaches rarely provide formal performance guarantees, which are indispensable when deploying policies in safety-critical settings. We present an approach for computing high-confidence guarantees on the performance of a multi-task policy on tasks not seen during training. Concretely, we introduce a new generalisation bound that composes (i) per-task lower confidence bounds from finitely many rollouts with (ii) task-level generalisation from finitely many sampled tasks, yielding a high-confidence guarantee for new tasks drawn from the same arbitrary and unknown distribution. Across state-of-the-art multi-task RL methods, we show that the guarantees are theoretically sound and informative at realistic sample sizes.

---

### WADEPre: A Wavelet-based Decomposition Model for Extreme Precipitation Nowcasting with Multi-Scale Learning

Authors: Baitian Liu, Haiping Zhang, Huiling Yuan, Dongjing Wang, Ying Li, Feng Chen, Hao Wu
Published: 2026-02-02
Categories: physics.ao-ph, cs.AI
arXiv: https://arxiv.org/abs/2602.02096v1

The heavy-tailed nature of precipitation intensity impedes precise precipitation nowcasting. Standard models that optimize pixel-wise losses are prone to regression-to-the-mean bias, which blurs extreme values. Existing Fourier-based methods also lack the spatial localization needed to resolve transient convective cells. To overcome these intrinsic limitations, we propose WADEPre, a wavelet-based decomposition model for extreme precipitation that transitions the modeling into the wavelet domain. By leveraging the Discrete Wavelet Transform for explicit decomposition, WADEPre employs a dual-branch architecture: an Approximation Network to model stable, low-frequency advection, isolating deterministic trends from statistical bias, and a spatially localized Detail Network to capture high-frequency stochastic convection, resolving transient singularities and preserving sharp boundaries. A subsequent Refiner module then dynamically reconstructs these decoupled multi-scale components into the final high-fidelity forecast. To address optimization instability, we introduce a multi-scale curriculum learning strategy that progressively shifts supervision from coarse scales to fine-grained details. Extensive experiments on the SEVIR and Shanghai Radar datasets demonstrate that WADEPre achieves state-of-the-art performance, yielding significant improvements in capturing extreme thresholds and maintaining structural fidelity. Our code is available at https://github.com/sonderlau/WADEPre.

---

### FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space

Authors: FSVideo Team, Qingyu Chen, Zhiyuan Fang, Haibin Huang, Xinwei Huang, Tong Jin, Minxuan Lin, Bo Liu, Celong Liu, Chongyang Ma, Xing Mei, Xiaohui Shen et al.
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02092v1

We introduce FSVideo, a fast speed transformer-based image-to-video (I2V) diffusion framework. We build our framework on the following key components: 1.) a new video autoencoder with highly-compressed latent space ($64\times64\times4$ spatial-temporal downsampling ratio), achieving competitive reconstruction quality; 2.) a diffusion transformer (DIT) architecture with a new layer memory design to enhance inter-layer information flow and context reuse within DIT, and 3.) a multi-resolution generation strategy via a few-step DIT upsampler to increase video fidelity. Our final model, which contains a 14B DIT base model and a 14B DIT upsampler, achieves competitive performance against other popular open-source models, while being an order of magnitude faster. We discuss our model design as well as training strategies in this report.

---

### LEC-KG: An LLM-Embedding Collaborative Framework for Domain-Specific Knowledge Graph Construction -- A Case Study on SDGs

Authors: Yikai Zeng, Yingchao Piao, Changhua Pei, Jianhui Li
Published: 2026-02-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.02090v2

Constructing domain-specific knowledge graphs from unstructured text remains challenging due to heterogeneous entity mentions, long-tail relation distributions, and the absence of standardized schemas. We present LEC-KG, a bidirectional collaborative framework that integrates the semantic understanding of Large Language Models (LLMs) with the structural reasoning of Knowledge Graph Embeddings (KGE). Our approach features three key components: (1) hierarchical coarse-to-fine relation extraction that mitigates long-tail bias, (2) evidence-guided Chain-of-Thought feedback that grounds structural suggestions in source text, and (3) semantic initialization that enables structural validation for unseen entities. The two modules enhance each other iteratively-KGE provides structure-aware feedback to refine LLM extractions, while validated triples progressively improve KGE representations. We evaluate LEC-KG on Chinese Sustainable Development Goal (SDG) reports, demonstrating substantial improvements over LLM baselines, particularly on low-frequency relations. Through iterative refinement, our framework reliably transforms unstructured policy text into validated knowledge graph triples.

---

### UrbanGS: A Scalable and Efficient Architecture for Geometrically Accurate Large-Scene Reconstruction

Authors: Changbai Li, Haodong Zhu, Hanlin Chen, Xiuping Liang, Tongfei Chen, Shuwei Shao, Linlin Yang, Huobin Tan, Baochang Zhang
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02089v2

While 3D Gaussian Splatting (3DGS) enables high-quality, real-time rendering for bounded scenes, its extension to large-scale urban environments gives rise to critical challenges in terms of geometric consistency, memory efficiency, and computational scalability. To address these issues, we present UrbanGS, a scalable reconstruction framework that effectively tackles these challenges for city-scale applications. First, we propose a Depth-Consistent D-Normal Regularization module. Unlike existing approaches that rely solely on monocular normal estimators, which can effectively update rotation parameters yet struggle to update position parameters, our method integrates D-Normal constraints with external depth supervision. This allows for comprehensive updates of all geometric parameters. By further incorporating an adaptive confidence weighting mechanism based on gradient consistency and inverse depth deviation, our approach significantly enhances multi-view depth alignment and geometric coherence, which effectively resolves the issue of geometric accuracy in complex large-scale scenes. To improve scalability, we introduce a Spatially Adaptive Gaussian Pruning (SAGP) strategy, which dynamically adjusts Gaussian density based on local geometric complexity and visibility to reduce redundancy. Additionally, a unified partitioning and view assignment scheme is designed to eliminate boundary artifacts and optimize computational load. Extensive experiments on multiple urban datasets demonstrate that UrbanGS achieves superior performance in rendering quality, geometric accuracy, and memory efficiency, providing a systematic solution for high-fidelity large-scale scene reconstruction.

---

### Efficient Swap Regret Minimization in Combinatorial Bandits

Authors: Andreas Kontogiannis, Vasilis Pollatos, Panayotis Mertikopoulos, Ioannis Panageas
Published: 2026-02-02
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.02087v1

This paper addresses the problem of designing efficient no-swap regret algorithms for combinatorial bandits, where the number of actions $N$ is exponentially large in the dimensionality of the problem. In this setting, designing efficient no-swap regret translates to sublinear -- in horizon $T$ -- swap regret with polylogarithmic dependence on $N$. In contrast to the weaker notion of external regret minimization - a problem which is fairly well understood in the literature - achieving no-swap regret with a polylogarithmic dependence on $N$ has remained elusive in combinatorial bandits. Our paper resolves this challenge, by introducing a no-swap-regret learning algorithm with regret that scales polylogarithmically in $N$ and is tight for the class of combinatorial bandits. To ground our results, we also demonstrate how to implement the proposed algorithm efficiently -- that is, with a per-iteration complexity that also scales polylogarithmically in $N$ -- across a wide range of well-studied applications.

---

### Closing the Loop: Universal Repository Representation with RPG-Encoder

Authors: Jane Luo, Chengyu Yin, Xin Zhang, Qingtao Li, Steven Liu, Yiming Huang, Jie Wu, Hao Liu, Yangyu Huang, Yu Kang, Fangkai Yang, Ying Xin et al.
Published: 2026-02-02
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2602.02084v2

Current repository agents encounter a reasoning disconnect due to fragmented representations, as existing methods rely on isolated API documentation or dependency graphs that lack semantic depth. We consider repository comprehension and generation to be inverse processes within a unified cycle: generation expands intent into implementation, while comprehension compresses implementation back into intent. To address this, we propose RPG-Encoder, a framework that generalizes the Repository Planning Graph (RPG) from a static generative blueprint into a unified, high-fidelity representation. RPG-Encoder closes the reasoning loop through three mechanisms: (1) Encoding raw code into the RPG that combines lifted semantic features with code dependencies; (2) Evolving the topology incrementally to decouple maintenance costs from repository scale, reducing overhead by 95.7%; and (3) Operating as a unified interface for structure-aware navigation. In evaluations, RPG-Encoder establishes state-of-the-art localization performance on SWE-bench Verified with 93.7% Acc@5 and exceeds the best baseline by over 10% in localization accuracy on SWE-bench Live Lite. These results highlight our superior fine-grained precision in complex codebases. Furthermore, it achieves 98.5% reconstruction coverage on RepoCraft, confirming RPG's high-fidelity capacity to mirror the original codebase and closing the loop between intent and implementation.

---

### Handling Covariate Mismatch in Federated Linear Prediction

Authors: Alexis Ayme, Rémi Khellaf
Published: 2026-02-02
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.02083v1

Federated learning enables institutions to train predictive models collaboratively without sharing raw data, addressing privacy and regulatory constraints. In the standard horizontal setting, clients hold disjoint cohorts of individuals and collaborate to learn a shared predictor. Most existing methods, however, assume that all clients measure the same features. We study the more realistic setting of covariate mismatch, where each client observes a different subset of features, which typically arises in multicenter collaborations with no prior agreement on data collection. We formalize learning a linear prediction under client-wise MCAR patterns and develop two modular approaches tailored to the dimensional regime and communication budget. In the low-dimensional setting, we propose a plug-in estimator that approximates the oracle linear predictor by aggregating sufficient statistics to estimate the covariance and cross-moment terms. In higher dimensions, we study an impute-then-regress strategy: (i) impute missing covariates using any exchangeability-preserving imputation procedure, and (ii) fit a ridge-regularized linear model on the completed data. We provide asymptotic and finite-sample learning rates for our predictors, explicitly characterizing their behaviour with the global dimension, the client-specific feature partition, and the distribution of samples across sites.

---

### Active learning from positive and unlabeled examples

Authors: Farnam Mansouri, Sandra Zilles, Shai Ben-David
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02081v1

Learning from positive and unlabeled data (PU learning) is a weakly supervised variant of binary classification in which the learner receives labels only for (some) positively labeled instances, while all other examples remain unlabeled. Motivated by applications such as advertising and anomaly detection, we study an active PU learning setting where the learner can adaptively query instances from an unlabeled pool, but a queried label is revealed only when the instance is positive and an independent coin flip succeeds; otherwise the learner receives no information. In this paper, we provide the first theoretical analysis of the label complexity of active PU learning.

---

### Learning Half-Spaces from Perturbed Contrastive Examples

Authors: Aryan Alavi Razavi Ravari, Farnam Mansouri, Yuxin Chen, Valentio Iverson, Adish Singla, Sandra Zilles
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02080v1

We study learning under a two-step contrastive example oracle, as introduced by Mansouri et. al. (2025), where each queried (or sampled) labeled example is paired with an additional contrastive example of opposite label. While Mansouri et al. assume an idealized setting, where the contrastive example is at minimum distance of the originally queried/sampled point, we introduce and analyze a mechanism, parameterized by a non-decreasing noise function $f$, under which this ideal contrastive example is perturbed. The amount of perturbation is controlled by $f(d)$, where $d$ is the distance of the queried/sampled point to the decision boundary. Intuitively, this results in higher-quality contrastive examples for points closer to the decision boundary. We study this model in two settings: (i) when the maximum perturbation magnitude is fixed, and (ii) when it is stochastic. For one-dimensional thresholds and for half-spaces under the uniform distribution on a bounded domain, we characterize active and passive contrastive sample complexity in dependence on the function $f$. We show that, under certain conditions on $f$, the presence of contrastive examples speeds up learning in terms of asymptotic query complexity and asymptotic expected query complexity.

---

### AICD Bench: A Challenging Benchmark for AI-Generated Code Detection

Authors: Daniil Orel, Dilshod Azizov, Indraneil Paul, Yuxia Wang, Iryna Gurevych, Preslav Nakov
Published: 2026-02-02
Categories: cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2602.02079v1

Large language models (LLMs) are increasingly capable of generating functional source code, raising concerns about authorship, accountability, and security. While detecting AI-generated code is critical, existing datasets and benchmarks are narrow, typically limited to binary human-machine classification under in-distribution settings. To bridge this gap, we introduce $\emph{AICD Bench}$, the most comprehensive benchmark for AI-generated code detection. It spans $\emph{2M examples}$, $\emph{77 models}$ across $\emph{11 families}$, and $\emph{9 programming languages}$, including recent reasoning models. Beyond scale, AICD Bench introduces three realistic detection tasks: ($\emph{i}$)~$\emph{Robust Binary Classification}$ under distribution shifts in language and domain, ($\emph{ii}$)~$\emph{Model Family Attribution}$, grouping generators by architectural lineage, and ($\emph{iii}$)~$\emph{Fine-Grained Human-Machine Classification}$ across human, machine, hybrid, and adversarial code. Extensive evaluation on neural and classical detectors shows that performance remains far below practical usability, particularly under distribution shift and for hybrid or adversarial code. We release AICD Bench as a $\emph{unified, challenging evaluation suite}$ to drive the next generation of robust approaches for AI-generated code detection. The data and the code are available at https://huggingface.co/AICD-bench}.

---

### Calibrating Adaptive Smoothing Methods for Freeway Traffic Reconstruction

Authors: Junyi Ji, Derek Gloudemans, Gergely Zachár, Matthew Nice, William Barbour, Daniel B. Work
Published: 2026-02-02
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2602.02072v1

The adaptive smoothing method (ASM) is a widely used approach for traffic state reconstruction. This article presents a Python implementation of ASM, featuring end-to-end calibration using real-world ground truth data. The calibration is formulated as a parameterized kernel optimization problem. The model is calibrated using data from a full-state observation testbed, with input from a sparse radar sensor network. The implementation is developed in PyTorch, enabling integration with various deep learning methods. We evaluate the results in terms of speed distribution, spatio-temporal error distribution, and spatial error to provide benchmark metrics for the traffic reconstruction problem. We further demonstrate the usability of the calibrated method across multiple freeways. Finally, we discuss the challenges of reproducibility in general traffic model calibration and the limitations of ASM. This article is reproducible and can serve as a benchmark for various freeway operation tasks.

---

### BAPS: A Fine-Grained Low-Precision Scheme for Softmax in Attention via Block-Aware Precision reScaling

Authors: Zisheng Ye, Xiaoyu He, Maoyuan Song, Guoliang Qiu, Chao Liao, Chen Wu, Yonggang Sun, Zhichun Li, Xiaoru Xie, Yuanyong Luo, Hu Liu, Pinyan Lu et al.
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02071v1

As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck stems from two hardware limitations: (1) limited data bandwidth between matrix and vector compute cores, and (2) the significant area cost of high-precision (FP32/16) exponentiation units (EXP2). To address these issues, we introduce a novel low-precision workflow that employs a specific 8-bit floating-point format (HiF8) and block-aware precision rescaling for softmax. Crucially, our algorithmic innovations make low-precision softmax feasible without the significant model accuracy loss that hampers direct low-precision approaches. Specifically, our design (i) halves the required data movement bandwidth by enabling matrix multiplication outputs constrained to 8-bit, and (ii) substantially reduces the EXP2 unit area by computing exponentiations in low (8-bit) precision. Extensive evaluation on language models and multi-modal models confirms the validity of our method. By alleviating the vector computation bottleneck, our work paves the way for doubling end-to-end inference throughput without increasing chip area, and offers a concrete co-design path for future low-precision hardware and software.

---

### Multi-View Stenosis Classification Leveraging Transformer-Based Multiple-Instance Learning Using Real-World Clinical Data

Authors: Nikola Cenikj, Özgün Turgut, Alexander Müller, Alexander Steger, Jan Kehrer, Marcus Brugger, Daniel Rueckert, Eimo Martens, Philip Müller
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.02067v1

Coronary artery stenosis is a leading cause of cardiovascular disease, diagnosed by analyzing the coronary arteries from multiple angiography views. Although numerous deep-learning models have been proposed for stenosis detection from a single angiography view, their performance heavily relies on expensive view-level annotations, which are often not readily available in hospital systems. Moreover, these models fail to capture the temporal dynamics and dependencies among multiple views, which are crucial for clinical diagnosis. To address this, we propose SegmentMIL, a transformer-based multi-view multiple-instance learning framework for patient-level stenosis classification. Trained on a real-world clinical dataset, using patient-level supervision and without any view-level annotations, SegmentMIL jointly predicts the presence of stenosis and localizes the affected anatomical region, distinguishing between the right and left coronary arteries and their respective segments. SegmentMIL obtains high performance on internal and external evaluations and outperforms both view-level models and classical MIL baselines, underscoring its potential as a clinically viable and scalable solution for coronary stenosis diagnosis. Our code is available at https://github.com/NikolaCenic/mil-stenosis.

---

### See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers

Authors: Ding Xia, Xinyue Gui, Mark Colley, Fan Gao, Zhongyi Zhou, Dongyuan Li, Renhe Jiang, Takeo Igarashi
Published: 2026-02-02
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2602.02063v2

Automated vehicles lack natural communication channels with other road users, making external Human-Machine Interfaces (eHMIs) essential for conveying intent and maintaining trust in shared environments. However, most eHMI studies rely on developer-crafted message-action pairs, which are difficult to adapt to diverse and dynamic traffic contexts. A promising alternative is to use Large Language Models (LLMs) as action designers that generate context-conditioned eHMI actions, yet such designers lack perceptual verification and typically depend on fixed prompts or costly human-annotated feedback for improvement. We present See2Refine, a human-free, closed-loop framework that uses vision-language model (VLM) perceptual evaluation as automated visual feedback to improve an LLM-based eHMI action designer. Given a driving context and a candidate eHMI action, the VLM evaluates the perceived appropriateness of the action, and this feedback is used to iteratively revise the designer's outputs, enabling systematic refinement without human supervision. We evaluate our framework across three eHMI modalities (lightbar, eyes, and arm) and multiple LLM model sizes. Across settings, our framework consistently outperforms prompt-only LLM designers and manually specified baselines in both VLM-based metrics and human-subject evaluations. Results further indicate that the improvements generalize across modalities and that VLM evaluations are well aligned with human preferences, supporting the robustness and effectiveness of See2Refine for scalable action design.

---

### Learning to Route and Schedule LLMs from User Retrials via Contextual Queueing Bandits

Authors: Seoungbin Bae, Junyoung Son, Dabeen Lee
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02061v2

Explosive demands for LLMs often cause user queries to accumulate in server queues, requiring efficient routing (query-LLM matching) and scheduling (query prioritization) mechanisms. Several online algorithms are being deployed, but they overlook the following two key challenges inherent to conversational LLM services: (1) unsatisfied users may retry queries, increasing the server backlog, and (2) requests for ``explicit" feedback, such as ratings, degrade user experiences. In this paper, we develop a joint routing and scheduling algorithm that leverages ``implicit" feedback inferred from user retrial behaviors. The key idea is to propose and study the framework of contextual queueing bandits with multinomial logit feedback (CQB-MNL). CQB-MNL models query retrials, as well as context-based learning for user preferences over LLMs. Our algorithm, anytime CQB (ACQB), achieves efficient learning while maintaining queue stability by combining Thompson sampling with forced exploration at a decaying rate. We show that ACQB simultaneously achieves a cumulative regret of $\widetilde{\mathcal{O}}(\sqrt{t})$ for routing and a queue length regret of $\widetilde{\mathcal{O}}(t^{-1/4})$ for any large $t$. For experiments, we refine query embeddings via contrastive learning while adopting a disjoint parameter model to learn LLM-specific parameters. Experiments on synthetic data, offline routing datasets (SPROUT, EmbedLLM, and RouterBench), and real user conversation logs (WildChat-1M) confirm that our methods improve routing, scheduling, and queue stability against strong online and offline-trained baselines.

---

### FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance

Authors: Hyunsuk Chung, Soyeon Caren Han, Seungyeon Ji, Jinwoo Kim, Eun-Jung Holden, Kyungreem Han
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02060v2

Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains unclear whether their predictions can be controlled by explicitly modulating reliance on different internal feature pathways. Existing approaches to shortcut and spurious behavior primarily rely on post hoc analysis or data-level interventions, offering limited ability to directly intervene on how models use information. We introduce FiLoRA (Focus-and-Ignore LoRA), an instruction-conditioned, parameter-efficient adaptation framework that enables controllable modulation of feature reliance while keeping the task and predictive objective fixed. FiLoRA decomposes adaptation into feature-aligned low-rank modules and applies instruction-conditioned gating, allowing natural language instructions to act as computation-level control signals over internal representations. We evaluate FiLoRA across both controlled classification settings and generative multimodal tasks, and under a range of instruction types, including natural and compositional instructions. Results show that FiLoRA induces consistent and interpretable shifts in feature reliance, selectively amplifying or suppressing different feature groups in accordance with the instruction, without altering task semantics. Our findings suggest that instruction-conditioned parameter adaptation can serve as a practical mechanism for intervening on internal model behavior, providing a new perspective on controllability and analysis of multimodal systems beyond output-level prompting or post hoc interpretation.

---

### FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance

Authors: Hyunsuk Chung, Caren Han, Yerin Choi, Seungyeon Ji, Jinwoo Kim, Eun-Jung Holden, Kyungreem Han
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02060v1

Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains poorly understood how their predictions depend on specific internal feature groups and whether such reliance can be deliberately controlled. Existing studies of shortcut and spurious behavior largely rely on post hoc analyses or feature removal, offering limited insight into whether reliance can be modulated without altering task semantics. We introduce FiLoRA (Focus-and-Ignore LoRA), an instruction-conditioned, parameter-efficient adaptation framework that enables explicit control over internal feature reliance while keeping the predictive objective fixed. FiLoRA decomposes adaptation into feature group-aligned LoRA modules and applies instruction-conditioned gating, allowing natural language instructions to act as computation-level control signals rather than task redefinitions. Across text--image and audio--visual benchmarks, we show that instruction-conditioned gating induces consistent and causal shifts in internal computation, selectively amplifying or suppressing core and spurious feature groups without modifying the label space or training objective. Further analyses demonstrate that FiLoRA yields improved robustness under spurious feature interventions, revealing a principled mechanism to regulate reliance beyond correlation-driven learning.

---