# Research Papers — 2026-02 · bundle page 142 of 210 > Full-text markdown of papers #7051–7100 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/142 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/141.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/143.md) ### AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering Authors: Yuzhu Cai, Zexi Liu, Xinyu Zhu, Cheng Wang, Yanfeng Wang, Siheng Chen Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07906v5 Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation due to frozen parameters. Although Reinforcement Learning (RL) offers a remedy, applying it to MLE is hindered by prohibitive execution latency and inefficient data selection. Recognizing these challenges, we propose AceGRPO with two core components: (1) Evolving Data Buffer that continuously repurposes execution traces into reusable training tasks, and (2) Adaptive Sampling guided by a Learnability Potential function, which dynamically prioritizes tasks at the agent's learning frontier to maximize learning efficiency. Leveraging AceGRPO, our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines (e.g., DeepSeek-V3.2), demonstrating robust capability for sustained iterative optimization. Code is available at https://github.com/yuzhu-cai/AceGRPO. --- ### MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation Authors: Yu Zhao, Hao Guan, Yongcheng Jing, Ying Zhang, Dacheng Tao Published: 2026-02-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07905v2 Large Language Models (LLMs) have shown strong potential in complex medical reasoning yet face diminishing gains under inference scaling laws. While existing studies augment LLMs with various knowledge types, it remains unclear how effectively the additional costs translate into accuracy. In this paper, we explore how meta-cognition of LLMs, i.e., their self-assessment of their own cognitive states, can regulate the reasoning process. Specifically, we propose MedCoG, a Medical Meta-Cognition Agent with Knowledge Graph, where the meta-cognitive assessments of task complexity, familiarity, and knowledge density dynamically regulate utilization of procedural, episodic, and factual knowledge. The LLM-centric on-demand reasoning aims to mitigate the diminishing returns under scaling law by (1) reducing costs via avoiding indiscriminate scaling, (2) improving accuracy via filtering out distractive knowledge. To validate this, we empirically characterize the scaling curve and introduce inference density to quantify inference efficiency. Experiments demonstrate the effectiveness and efficiency of MedCoG on five hard sets of medical benchmarks, yielding 6.2x inference density. Furthermore, the Oracle study highlights the significant potential of meta-cognitive regulation. --- ### Adaptive Acquisition Selection for Bayesian Optimization with Large Language Models Authors: Giang Ngo, Dat Phan Trong, Dang Nguyen, Sunil Gupta, Svetha Venkatesh Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07904v1 Bayesian Optimization critically depends on the choice of acquisition function, but no single strategy is universally optimal; the best choice is non-stationary and problem-dependent. Existing adaptive portfolio methods often base their decisions on past function values while ignoring richer information like remaining budget or surrogate model characteristics. To address this, we introduce LMABO, a novel framework that casts a pre-trained Large Language Model (LLM) as a zero-shot, online strategist for the BO process. At each iteration, LMABO uses a structured state representation to prompt the LLM to select the most suitable acquisition function from a diverse portfolio. In an evaluation across 50 benchmark problems, LMABO demonstrates a significant performance improvement over strong static, adaptive portfolio, and other LLM-based baselines. We show that the LLM's behavior is a comprehensive strategy that adapts to real-time progress, proving its advantage stems from its ability to process and synthesize the complete optimization state into an effective, adaptive policy. --- ### GCN-MPPR: Enhancing the Propagation of Message Passing Neural Networks via Motif-Based Personalized PageRank Authors: Mingcan Wang, Junchang Xin, Zhongming Yao, Kaifu Long, Zhiqiong Wang Published: 2026-02-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07903v1 The algorithms based on message passing neural networks (MPNNs) on graphs have recently achieved great success for various graph applications. However, studies find that these methods always propagate the information to very limited neighborhoods with shallow depth, particularly due to over-smoothing. That means most of the existing MPNNs fail to be so `deep'. Although some previous work tended to handle this challenge via optimization- or structure-level remedies, the overall performance of GCNs still suffers from limited accuracy, poor stability, and unaffordable computational cost. Moreover, neglect of higher-order relationships during the propagation of MPNNs has further limited the performance of them. To overcome these challenges, a novel variant of PageRank named motif-based personalized PageRank (MPPR) is proposed to measure the influence of one node to another on the basis of considering higher-order motif relationships. Secondly, the MPPR is utilized to the message passing process of GCNs, thereby guiding the message passing process at a relatively `high' level. The experimental results show that the proposed method outperforms almost all of the baselines on accuracy, stability, and time consumption. Additionally, the proposed method can be considered as a component that can underpin almost all GCN tasks, with DGCRL being demonstrated in the experiment. The anonymous code repository is available at: https://anonymous.4open.science/r/GCN-MPPR-AFD6/. --- ### Incremental Mapping with Measurement Synchronization & Compression Authors: Mark Griguletskii, Danil Belov, Pavel Osinenko Published: 2026-02-08 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.07901v1 Modern autonomous vehicles and robots utilize versatile sensors for localization and mapping. The fidelity of these maps is paramount, as an accurate environmental representation is a prerequisite for stable and precise localization. Factor graphs provide a powerful approach for sensor fusion, enabling the estimation of the maximum a posteriori solution. However, the discrete nature of graph-based representations, combined with asynchronous sensor measurements, complicates consistent state estimation. The design of an optimal factor graph topology remains an open challenge, especially in multi-sensor systems with asynchronous data. Conventional approaches rely on a rigid graph structure, which becomes inefficient with sensors of disparate rates. Although preintegration techniques can mitigate this for high-rate sensors, their applicability is limited. To address this problem, this work introduces a novel approach that incrementally constructs connected factor graphs, ensuring the incorporation of all available sensor data by choosing the optimal graph topology based on the external evaluation criteria. The proposed methodology facilitates graph compression, reducing the number of nodes (optimized variables) by ~30% on average while maintaining map quality at a level comparable to conventional approaches. --- ### Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents Authors: Zhi Chen, Zhensu Sun, Yuling Shi, Chao Peng, Xiaodong Gu, David Lo, Lingxiao Jiang Published: 2026-02-08 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.07900v2 Large Language Model (LLM) code agents increasingly resolve repository-level issues by iteratively editing code, invoking tools, and validating candidate patches. In these workflows, agents often write tests on the fly, but the value of this behavior remains unclear. For example, GPT-5.2 writes almost no new tests yet achieves performance comparable to top-ranking agents.This raises a central question: do such tests meaningfully improve issue resolution, or do they mainly mimic a familiar software-development practice while consuming interaction budget? To better understand the role of agent-written tests, we analyze trajectories produced by six strong LLMs on SWE-bench Verified. Our results show that test writing is common, but resolved and unresolved tasks within the same model exhibit similar test-writing frequencies. When tests are written, they mainly serve as observational feedback channels, with value-revealing print statements appearing much more often than assertion-based checks. Based on these insights, we perform a prompt-intervention study by revising the prompts used with four models to either increase or reduce test writing. The results suggest that prompt-induced changes in the volume of agent-written tests do not significantly change final outcomes in this setting. Taken together, these results suggest that current agent-written testing practices reshape process and cost more than final task outcomes. --- ### Rethinking Practical and Efficient Quantization Calibration for Vision-Language Models Authors: Zhenhao Shang, Haizhao Jing, Guoting Wei, Haokui Zhang, Rong Xiao, Jianqing Gao, Peng Wang Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07899v1 Post-training quantization (PTQ) is a primary approach for deploying large language models without fine-tuning, and the quantized performance is often strongly affected by the calibration in PTQ. By contrast, in vision-language models (VLMs), substantial differences between visual and text tokens in their activation distributions and sensitivities to quantization error pose significant challenges for effective calibration during PTQ. In this work, we rethink what PTQ calibration should align with in VLMs and propose the Token-level Importance-aware Layer-wise Quantization framework (TLQ). Guided by gradient information, we design a token-level importance integration mechanism for quantization error, and use it to construct a token-level calibration set, enabling a more fine-grained calibration strategy. Furthermore, TLQ introduces a multi-GPU, quantization-exposed layer-wise calibration scheme. This scheme keeps the layer-wise calibration procedure consistent with the true quantized inference path and distributes the complex layer-wise calibration workload across multiple RTX3090 GPUs, thereby reducing reliance on the large memory of A100 GPUs. TLQ is evaluated across two models, three model scales, and two quantization settings, consistently achieving performance improvements across all settings, indicating its strong quantization stability. The code will be released publicly. --- ### Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection Authors: Guanglong Sun, Siyuan Zhang, Liyuan Wang, Jun Zhu, Hang Su, Yi Zhong Published: 2026-02-08 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.07892v2 Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the \emph{alignment tax}. We study this trade-off through the lens of continual learning: sequential alignment stages expose the model to shifted data distributions and objectives, and their gradients may interfere with directions that support previously acquired general capabilities. This view does not claim that all alignment degradation has a single cause; rather, it provides a useful first-order mechanism for mitigating one important source of capability regression. We propose \textbf{O}rthogonal \textbf{G}radient \textbf{P}rojection for \textbf{S}afety \textbf{A}lignment (\textbf{OGPSA}), a lightweight update rule that estimates a low-rank reference subspace from gradients on a small set of general-capability data and removes from each safety gradient the component lying in this subspace. The resulting update is the steepest local safety-descent direction subject to first-order preservation constraints on the reference objectives. OGPSA is compatible with standard post-training pipelines and avoids large-scale replay, although it introduces periodic reference-gradient computation. Across Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and sequential SFT$\rightarrow$DPO settings, OGPSA improves the observed safety--utility trade-off over standard baselines. Under the sequential SFT$\rightarrow$DPO pipeline, the average performance gain increases from 33.98\% to 42.74\% on Qwen2.5-7B-Instruct and from 19.74\% to 32.98\% on Llama3.1-8B-Instruct. We have open sourced our code at https://github.com/SunGL001/OGPSA. --- ### Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video Authors: Zihui Gao, Ke Liu, Donny Y. Chen, Duochao Shi, Guosheng Lin, Hao Chen, Chunhua Shen Published: 2026-02-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.07891v1 Geometric foundation models show promise in 3D reconstruction, yet their progress is severely constrained by the scarcity of diverse, large-scale 3D annotations. While Internet videos offer virtually unlimited raw data, utilizing them as a scaling source for geometric learning is challenging due to the absence of ground-truth geometry and the presence of observational noise. To address this, we propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams. SAGE leverages a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervision: (1) Informative training trajectory selection; (2) Sparse Geometric Anchoring via SfM point clouds for global structural guidance; and (3) Dense Differentiable Consistency via 3D Gaussian rendering for multi-view constraints. To prevent catastrophic forgetting, we introduce a regularization strategy using anchor data. Extensive experiments show that SAGE significantly enhances zero-shot generalization, reducing Chamfer Distance by 20-42% on unseen benchmarks (7Scenes, TUM-RGBD, Matterport3D) compared to state-of-the-art baselines. To our knowledge, SAGE pioneers the adaptation of geometric foundation models via Internet video, establishing a scalable paradigm for general-purpose 3D learning. --- ### Efficient Anti-exploration via VQVAE and Fuzzy Clustering in Offline Reinforcement Learning Authors: Long Chen, Yinkui Liu, Shen Li, Bo Tang, Xuemin Hu Published: 2026-02-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07889v1 Pseudo-count is an effective anti-exploration method in offline reinforcement learning (RL) by counting state-action pairs and imposing a large penalty on rare or unseen state-action pair data. Existing anti-exploration methods count continuous state-action pairs by discretizing these data, but often suffer from the issues of dimension disaster and information loss in the discretization process, leading to efficiency and performance reduction, and even failure of policy learning. In this paper, a novel anti-exploration method based on Vector Quantized Variational Autoencoder (VQVAE) and fuzzy clustering in offline RL is proposed. We first propose an efficient pseudo-count method based on the multi-codebook VQVAE to discretize state-action pairs, and design an offline RL anti-exploitation method based on the proposed pseudo-count method to handle the dimension disaster issue and improve the learning efficiency. In addition, a codebook update mechanism based on fuzzy C-means (FCM) clustering is developed to improve the use rate of vectors in codebooks, addressing the information loss issue in the discretization process. The proposed method is evaluated on the benchmark of Datasets for Deep Data-Driven Reinforcement Learning (D4RL), and experimental results show that the proposed method performs better and requires less computing cost in multiple complex tasks compared to state-of-the-art (SOTA) methods. --- ### Research on a Camera Position Measurement Method based on a Parallel Perspective Error Transfer Model Authors: Ning Hu, Shuai Li, Jindong Tan Published: 2026-02-08 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.07888v1 Camera pose estimation from sparse correspondences is a fundamental problem in geometric computer vision and remains particularly challenging in near-field scenarios, where strong perspective effects and heterogeneous measurement noise can significantly degrade the stability of analytic PnP solutions. In this paper, we present a geometric error propagation framework for camera pose estimation based on a parallel perspective approximation. By explicitly modeling how image measurement errors propagate through perspective geometry, we derive an error transfer model that characterizes the relationship between feature point distribution, camera depth, and pose estimation uncertainty. Building on this analysis, we develop a pose estimation method that leverages parallel perspective initialization and error-aware weighting within a Gauss-Newton optimization scheme, leading to improved robustness in proximity operations. Extensive experiments on both synthetic data and real-world images, covering diverse conditions such as strong illumination, surgical lighting, and underwater low-light environments, demonstrate that the proposed approach achieves accuracy and robustness comparable to state-of-the-art analytic and iterative PnP methods, while maintaining high computational efficiency. These results highlight the importance of explicit geometric error modeling for reliable camera pose estimation in challenging near-field settings. --- ### Rich-ARQ: From 1-bit Acknowledgment to Rich Neural Coded Feedback Authors: Enhao Chen, Yulin Shao Published: 2026-02-08 Categories: cs.IT, cs.AI arXiv: https://arxiv.org/abs/2602.07886v1 This paper reimagines the foundational feedback mechanism in wireless communication, transforming the prevailing 1-bit binary ACK/NACK with a high-dimensional, information-rich vector to transform passive acknowledgment into an active collaboration. We present Rich-ARQ, a paradigm that introduces neural-coded feedback for collaborative physical-layer channel coding between transmitter and receiver. To realize this vision in practice, we develop a novel asynchronous feedback code that eliminates stalling from feedback delays, adapts dynamically to channel fluctuations, and features a lightweight encoder suitable for on-device deployment. We materialize this concept into the first full-stack, standard-compliant software-defined radio prototype, which decouples AI inference from strict radio timing. Comprehensive over-the-air experiments demonstrate that Rich-ARQ achieves significant SNR gains over conventional 1-bit hybrid ARQ and remarkable latency reduction over prior learning-based feedback codes, moving the promise of intelligent feedback from theory to a practical, high-performance reality for next-generation networks. --- ### MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory Authors: Zhenyuan Zhang, Xianzhang Jia, Zhiqin Yang, Zhenbo Song, Wei Xue, Sirui Han, Yike Guo Published: 2026-02-08 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.07885v3 Memory systems enable LLM agents to consolidate and retrieve relevant evidence from the factual knowledge accumulated through growing interaction histories for downstream reasoning. Existing approaches have explored diverse strategies for organizing and compressing these histories. However, balancing compression with retrieval effectiveness remains challenging: retaining too much content can cause relevant evidence to be obscured by redundant entries, while discarding too aggressively may remove content that later proves relevant. This amounts to a tradeoff between compressing redundancy and preserving enough structure to retrieve target evidence, as formalized by the information bottleneck. To this end, we propose MemCoRe, which organizes memory as a compression hierarchy where each level compresses redundancy further while retaining the structure needed for retrieval at that level. In this hierarchy, evidence is progressively compressed from detailed records through extracted keywords to topic groups. This enables retrieval to locate target evidence by searching across levels of the hierarchy. Comprehensive experiments demonstrate that MemCoRe outperforms existing state-of-the-art baselines. --- ### MemFly: On-the-Fly Memory Optimization via Information Bottleneck Authors: Zhenyuan Zhang, Xianzhang Jia, Zhiqin Yang, Zhenbo Song, Wei Xue, Sirui Han, Yike Guo Published: 2026-02-08 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.07885v2 Long-term memory enables large language model agents to tackle complex tasks through historical interactions. However, existing frameworks encounter a fundamental dilemma between compressing redundant information efficiently and maintaining precise retrieval for downstream tasks. To bridge this gap, we propose MemFly, a framework grounded in information bottleneck principles that facilitates on-the-fly memory evolution for LLMs. Our approach minimizes compression entropy while maximizing relevance entropy via a gradient-free optimizer, constructing a stratified memory structure for efficient storage. To fully leverage MemFly, we develop a hybrid retrieval mechanism that seamlessly integrates semantic, symbolic, and topological pathways, incorporating iterative refinement to handle complex multi-hop queries. Comprehensive experiments demonstrate that MemFly substantially outperforms state-of-the-art baselines in memory coherence, response fidelity, and accuracy. --- ### GRAFT: Decoupling Ranking and Calibration for Survival Analysis Authors: Mohammad Ashhad, Robert Hoehndorf, Ricardo Henao Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07884v2 Survival analysis is complicated by censored data, high-dimensional features, and non-linear interactions. Classical models offer interpretability and superior calibration but are restricted to linear or predefined functional forms, while deep learning models are flexible and achieve strong discriminative performance, but tend to produce poorly calibrated survival estimates. To address this trade-off, we propose GRAFT (Gated Residual Accelerated Failure Time), a novel AFT model that decouples prognostic ranking from survival calibration. GRAFT's hybrid architecture combines a linear AFT model with a non-linear residual neural network, and it also integrates stochastic gates for automatic feature selection. The model is trained by optimizing a differentiable, C-index-aligned ranking loss using stochastic conditional imputation from local Kaplan-Meier estimators, while calibrated survival estimates are obtained through simple post-training calibration. In public benchmarks, GRAFT outperforms baselines in discrimination and calibration, while remaining robust and sparse in high-noise settings. --- ### ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation Authors: Jingqi Zhou, Sheng Wang, Dezhao Deng, Junwen Lu, Junwei Su, Qintong Li, Jiahui Gao, Hao Wu, Jiyue Jiang, Lingpeng Kong, Dunhong Jin, Chuan Wu Published: 2026-02-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07883v4 LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidity forces a trade-off between domain-specific performance and cross-task generalization: strong priors and compact tool spaces aid specialization but weaken transfer, while task-agnostic workflows and broad action spaces expand coverage but dilute guidance. Existing pre-execution optimization, planner-worker orchestration, and configuration patching fall short of resolving this tension, as they decouple adaptation from execution, causing information loss, fragmented optimization, and ambiguous credit assignment. We propose ToolSelf, a tool-driven runtime self-reconfiguration paradigm that abstracts configuration updates as a standardized tool interface and unifies execution and adaptation within one policy's action space. The execution agent can dynamically update sub-goals, strategies, toolboxes, context, and context-management modes based on task progress and feedback. We further introduce Configuration-Aware Two-stage Training (CAT), which combines rejection sampling fine-tuning with trajectory-level KTO reinforcement learning to internalize self-reconfiguration. Across diverse benchmarks, zero-shot ToolSelf rivals task-specialized agents; after CAT training, ToolSelf gains 28.8 points over the static-configuration baseline on average, illuminating a path toward emergent adaptivity that obviates manually injected guidance. The code is available at https://github.com/lian-tian-mo-zun/ToolSelf. --- ### Deep Variable-Length Feedback Codes Authors: Yu Ding, Yulin Shao Published: 2026-02-08 Categories: cs.IT, cs.AI arXiv: https://arxiv.org/abs/2602.07881v1 Deep learning has enabled significant advances in feedback-based channel coding, yet existing learned schemes remain fundamentally limited: they employ fixed block lengths, suffer degraded performance at high rates, and cannot fully exploit the adaptive potential of feedback. This paper introduces Deep Variable-Length Feedback (DeepVLF) coding, a flexible coding framework that dynamically adjusts transmission length via learned feedback. We propose two complementary architectures: DeepVLF-R, where termination is receiver-driven, and DeepVLF-T, where the transmitter controls termination. Both architectures leverage bit-group partitioning and transformer-based encoder-decoder networks to enable fine-grained rate adaptation in response to feedback. Evaluations over AWGN and 5G-NR fading channels demonstrate that DeepVLF substantially outperforms state-of-the-art learned feedback codes. It achieves the same block error rate with 20%-55% fewer channel uses and lowers error floors by orders of magnitude, particularly in high-rate regimes. Encoding dynamics analysis further reveals that the models autonomously learn a two-phase strategy analogous to classical Schalkwijk-Kailath coding: an initial information-carrying phase followed by a noise-cancellation refinement phase. This emergent behavior underscores the interpretability and information-theoretic alignment of the learned codes. --- ### Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model Authors: Tianyi Wang, Huawei Fan, Yuanchao Shu, Peng Cheng, Cong Wang Published: 2026-02-08 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.07878v1 Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks. Recently, a growing body of research has focused on algorithmic complexity attacks by crafting inputs to trigger worst-case output lengths. However, we report a counter-intuitive finding that these algorithmic latency attacks are largely ineffective against modern LLM serving systems. We reveal that system-level optimization such as continuous batching provides a logical isolation to mitigate contagious latency impact on co-located users. To this end, in this paper, we shift the focus from the algorithm to the system layer, and introduce a new Fill and Squeeze attack strategy targeting the state transition of the scheduler. "Fill" first exhausts the global KV cache to induce Head-of-Line blocking, while "Squeeze" forces the system into repetitive preemption. By manipulating output lengths using methods from simple plain-text prompts to more complex prompt engineering, and leveraging side-channel probing of memory status, we demonstrate that the attack can be orchestrated in a black-box setting with much less cost. Extensive evaluations indicate by up to 20-280x average slowdown on Time to First Token and 1.5-4x average slowdown on Time Per Output Token compared to existing attacks with 30-40% lower attack cost. --- ### Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion Authors: Aditya Shankar, Yuandou Wang, Rihan Hai, Lydia Y. Chen Published: 2026-02-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07875v3 Generating tabular data under conditions is critical to applications requiring precise control over the generative process. Existing methods rely on training-time strategies that do not generalise to unseen constraints during inference, and struggle to handle conditional tasks beyond tabular imputation. While manifold theory offers a principled way to guide generation, current formulations are tied to specific inference-time objectives and are limited to continuous domains. We extend manifold theory to tabular data and expand its scope to handle diverse inference-time objectives. On this foundation, we introduce HARPOON, a tabular diffusion method that guides unconstrained samples along the manifold geometry to satisfy diverse tabular conditions at inference. We validate our theoretical contributions empirically on tasks such as imputation and enforcing inequality constraints, demonstrating HARPOON'S strong performance across diverse datasets and the practical benefits of manifold-aware guidance for tabular data. Code URL: https://github.com/adis98/Harpoon --- ### Direct Soft-Policy Sampling via Langevin Dynamics Authors: Donghyeon Ki, Hee-Jun Ahn, Kyungyoon Kim, Byung-Jun Lee Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07873v1 Soft policies in reinforcement learning define policies as Boltzmann distributions over state-action value functions, providing a principled mechanism for balancing exploration and exploitation. However, realizing such soft policies in practice remains challenging. Existing approaches either depend on parametric policies with limited expressivity or employ diffusion-based policies whose intractable likelihoods hinder reliable entropy estimation in soft policy objectives. We address this challenge by directly realizing soft-policy sampling via Langevin dynamics driven by the action gradient of the Q-function. This perspective leads to Langevin Q-Learning (LQL), which samples actions from the target Boltzmann distribution without explicitly parameterizing the policy. However, directly applying Langevin dynamics suffers from slow mixing in high-dimensional and non-convex Q-landscapes, limiting its practical effectiveness. To overcome this, we propose Noise-Conditioned Langevin Q-Learning (NC-LQL), which integrates multi-scale noise perturbations into the value function. NC-LQL learns a noise-conditioned Q-function that induces a sequence of progressively smoothed value landscapes, enabling sampling to transition from global exploration to precise mode refinement. On OpenAI Gym MuJoCo benchmarks, NC-LQL achieves competitive performance compared to state-of-the-art diffusion-based methods, providing a simple yet powerful solution for online RL. --- ### WristMIR: Coarse-to-Fine Region-Aware Retrieval of Pediatric Wrist Radiographs with Radiology Report-Driven Learning Authors: Mert Sonmezer, Serge Vasylechko, Duygu Atasoy, Seyda Ertekin, Sila Kurugol Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07872v3 Retrieving wrist radiographs with analogous fracture patterns is challenging because clinically important cues are subtle, highly localized and often obscured by overlapping anatomy or variable imaging views. Progress is further limited by the scarcity of large, well-annotated datasets for case-based medical image retrieval. We introduce WristMIR, a region-aware pediatric wrist radiograph retrieval framework that leverages dense radiology reports and bone-specific localization to learn fine-grained, clinically meaningful image representations without any manual image-level annotations. Using MedGemma-based structured report mining to generate both global and region-level captions, together with pre-processed wrist images and bone-specific crops of the distal radius, distal ulna, and ulnar styloid, WristMIR jointly trains global and local contrastive encoders and performs a two-stage retrieval process: (1) coarse global matching to identify candidate exams, followed by (2) region-conditioned reranking aligned to a predefined anatomical bone region. WristMIR improves retrieval performance over strong vision-language baselines, raising image-to-text Recall@5 from 0.82% to 9.35%. Its embeddings also yield stronger fracture classification (AUROC 0.949, AUPRC 0.953). In region-aware evaluation, the two-stage design markedly improves retrieval-based fracture diagnosis, increasing mean $F_1$ from 0.568 to 0.753, and radiologists rate its retrieved cases as more clinically relevant, with mean scores rising from 3.36 to 4.35. These findings highlight the potential of anatomically guided retrieval to enhance diagnostic reasoning and support clinical decision-making in pediatric musculoskeletal imaging. The source code is publicly available at https://github.com/quin-med-harvard-edu/WristMIR. --- ### Orchestrating Attention: Bringing Harmony to the 'Chaos' of Neurodivergent Learning States Authors: Satyam Kumar Navneet, Joydeep Chandra, Yong Zhang Published: 2026-02-08 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.07865v1 Adaptive learning systems optimize content delivery based on performance metrics but ignore the dynamic attention fluctuations that characterize neurodivergent learners. We present AttentionGuard, a framework that detects engagement-attention states from privacy-preserving behavioral signals and adapts interface elements accordingly. Our approach models four attention states derived from ADHD phenomenology and implements five novel UI adaptation patterns including bi-directional scaffolding that responds to both understimulation and overstimulation. We validate our detection model on the OULAD dataset, achieving 87.3% classification accuracy, and demonstrate correlation with clinical ADHD profiles through cross-validation on the HYPERAKTIV dataset. A Wizard-of-Oz study with 11 adults showing ADHD characteristics found significantly reduced cognitive load in the adaptive condition (NASA-TLX: 47.2 vs 62.8, Cohen's d=1.21, p=0.008) and improved comprehension (78.4% vs 61.2%, p=0.009). Concordance analysis showed 84% agreement between wizard decisions and automated classifier predictions, supporting deployment feasibility. The system is presented as an interactive demo where observers can inspect detected attention states, observe real-time UI adaptations, and compare automated decisions with human-in-the-loop overrides. We contribute empirically validated UI patterns for attention-adaptive interfaces and evidence that behavioral attention detection can meaningfully support neurodivergent learning experiences. --- ### Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spaces Authors: Chen Yang, Guanxin Lin, Youquan He, Peiyao Chen, Guanghe Liu, Yufan Mo, Zhouyuan Xu, Linhao Wang, Guohui Zhang, Zihang Zhang, Shenxiang Zeng, Chen Wang et al. Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07864v2 Spatial intelligence is crucial for vision--language models (VLMs), yet many scene-centric benchmarks evaluate unconstrained environments where a single image may admit multiple plausible 3D interpretations. We introduce SSI-Bench, a VQA benchmark for Structure-Centric Spatial Reasoning (SCSR) in constraint-governed spaces. Built from complex real-world 3D structures, it uses structural constraints from geometry, topology, and physical feasibility to make component relations more determinate from visual evidence. The benchmark contains 1,000 ranking questions spanning geometric and topological reasoning, where correct ordering requires resolving all candidate-wise 3D relations, imposing stronger demands on spatial understanding. It is created through a fully human-centered pipeline with over 400 researcher-hours of image curation, component annotation, and question design. Evaluating 31 VLMs reveals a large gap to humans: the best open-source model achieves 22.2% accuracy and the strongest closed-source model reaches 33.6%, while humans score 91.6%. Further results show that chain-of-thought reasoning brings only marginal gains, and error analysis reveals fundamental limitations in current models' spatial understanding within constraint-governed spaces. Project page: https://ssi-bench.github.io. --- ### Recovering 3D Shapes from Ultra-Fast Motion-Blurred Images Authors: Fei Yu, Shudan Guo, Shiqing Xin, Beibei Wang, Haisen Zhao, Wenzheng Chen Published: 2026-02-08 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.07860v1 We consider the problem of 3D shape recovery from ultra-fast motion-blurred images. While 3D reconstruction from static images has been extensively studied, recovering geometry from extreme motion-blurred images remains challenging. Such scenarios frequently occur in both natural and industrial settings, such as fast-moving objects in sports (e.g., balls) or rotating machinery, where rapid motion distorts object appearance and makes traditional 3D reconstruction techniques like Multi-View Stereo (MVS) ineffective. In this paper, we propose a novel inverse rendering approach for shape recovery from ultra-fast motion-blurred images. While conventional rendering techniques typically synthesize blur by averaging across multiple frames, we identify a major computational bottleneck in the repeated computation of barycentric weights. To address this, we propose a fast barycentric coordinate solver, which significantly reduces computational overhead and achieves a speedup of up to 4.57x, enabling efficient and photorealistic simulation of high-speed motion. Crucially, our method is fully differentiable, allowing gradients to propagate from rendered images to the underlying 3D shape, thereby facilitating shape recovery through inverse rendering. We validate our approach on two representative motion types: rapid translation and rotation. Experimental results demonstrate that our method enables efficient and realistic modeling of ultra-fast moving objects in the forward simulation. Moreover, it successfully recovers 3D shapes from 2D imagery of objects undergoing extreme translational and rotational motion, advancing the boundaries of vision-based 3D reconstruction. Project page: https://maxmilite.github.io/rec-from-ultrafast-blur/ --- ### Dynamic Load Model for Data Centers with Pattern-Consistent Calibration Authors: Siyu Lu, Chenhan Xiao, Yang Weng Published: 2026-02-08 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2602.07859v1 The rapid growth of data centers has made large electronic load (LEL) modeling increasingly important for power system analysis. Such loads are characterized by fast workload-driven variability and protection-driven disconnection and reconnection behavior that are not captured by conventional load models. Existing data center load modeling includes physics-based approaches, which provide interpretable structure for grid simulation, and data-driven approaches, which capture empirical workload variability from data. However, physics-based models are typically uncalibrated to facility-level operation, while trajectory alignment in data-driven methods often leads to overfitting and unrealistic dynamic behavior. To resolve these limitations, we design the framework to leverage both physics-based structure and data-driven adaptability. The physics-based structure is parameterized to enable data-driven pattern-consistent calibration from real operational data, supporting facility-level grid planning. We further show that trajectory-level alignment is limited for inherently stochastic data center loads. Therefore, we design the calibration to align temporal and statistical patterns using temporal contrastive learning (TCL). This calibration is performed locally at the facility, and only calibrated parameters are shared with utilities, preserving data privacy. The proposed load model is calibrated by real-world operational load data from the MIT Supercloud, ASU Sol, Blue Waters, and ASHRAE datasets. Then it is integrated into the ANDES platform and evaluated on the IEEE 39-bus, NPCC 140-bus, and WECC 179-bus systems. We find that interactions among LELs can fundamentally alter post-disturbance recovery behavior, producing compound disconnection-reconnection dynamics and delayed stabilization that are not captured by uncalibrated load models. --- ### Geometry-Aware Rotary Position Embedding for Consistent Video World Model Authors: Chendong Xiang, Jiajun Liu, Jintao Zhang, Xiao Yang, Zhengwei Fang, Shizun Wang, Zijun Wang, Yingtian Zou, Hang Su, Jun Zhu Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07854v3 Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial persistence: they fail to maintain stable scene structures over long trajectories, frequently hallucinating details when cameras revisit previously observed locations. We identify that this geometric drift stems from reliance on screen-space positional embeddings, which conflict with the projective geometry required for 3D consistency. We introduce \textbf{ViewRope}, a geometry-aware encoding that injects camera-ray directions directly into video transformer self-attention layers. By parameterizing attention with relative ray geometry rather than pixel locality, ViewRope provides a model-native inductive bias for retrieving 3D-consistent content across temporal gaps. We further propose \textbf{Geometry-Aware Frame-Sparse Attention}, which exploits these geometric cues to selectively attend to relevant historical frames, improving efficiency without sacrificing memory consistency. We also present \textbf{ViewBench}, a diagnostic suite measuring loop-closure fidelity and geometric drift. Our results demonstrate that ViewRope substantially improves long-term consistency while reducing computational costs. --- ### Emergent Misalignment is Easy, Narrow Misalignment is Hard Authors: Anna Soligo, Edward Turner, Senthooran Rajamanoharan, Neel Nanda Published: 2026-02-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.07852v1 Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated settings. Concerningly, a pre-registered survey of experts failed to predict this result, highlighting our poor understanding of the inductive biases governing learning and generalisation in LLMs. We use emergent misalignment (EM) as a case study to investigate these inductive biases and find that models can just learn the narrow dataset task, but that the general solution appears to be more stable and more efficient. To establish this, we build on the result that different EM finetunes converge to the same linear representation of general misalignment, which can be used to mediate misaligned behaviour. We find a linear representation of the narrow solution also exists, and can be learned by introducing a KL divergence loss. Comparing these representations reveals that general misalignment achieves lower loss, is more robust to perturbations, and is more influential in the pre-training distribution. This work isolates a concrete representation of general misalignment for monitoring and mitigation. More broadly, it offers a detailed case study and preliminary metrics for investigating how inductive biases shape generalisation in LLMs. We open-source all code, datasets and model finetunes. --- ### LQA: A Lightweight Quantized-Adaptive Framework for Vision-Language Models on the Edge Authors: Xin Wang, Hong Jia, Hualin Zhou, Sheng Guang Wang, Yu Zhang, Ting Dang, Tao Gu Published: 2026-02-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07849v3 Deploying Vision-Language Models (VLMs) on edge devices is challenged by resource constraints and performance degradation under distribution shifts. While test-time adaptation (TTA) can counteract such shifts, existing methods are too resource-intensive for on-device deployment. To address this challenge, we propose LQA, a lightweight, quantized-adaptive framework for VLMs that combines a modality-aware quantization strategy with gradient-free test-time adaptation. We introduce Selective Hybrid Quantization (SHQ) and a quantized, gradient-free adaptation mechanism to enable robust and efficient VLM deployment on resource-constrained hardware. Experiments across both synthetic and real-world distribution shifts show that LQA improves overall adaptation performance by 4.5\%, uses less memory than full-precision models, and significantly outperforms gradient-based TTA methods, achieving up to 19.9$\times$ lower memory usage across seven open-source datasets. These results demonstrate that LQA offers a practical pathway for robust, privacy-preserving, and efficient VLM deployment on edge devices. --- ### MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation Authors: Shijie Wang, Pengfei Li, Yikun Fu, Kaifeng Liu, Fangyuan Li, Yang Liu, Xiaowei Sun, Zonglin Li, Siyao Zhao, Jian Zhao, Kai Tian, Dong Li et al. Published: 2026-02-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.07848v1 While the complex reasoning capability of Large Language Models (LLMs) has attracted significant attention, single-agent systems often encounter inherent performance ceilings in complex tasks such as code generation. Multi-agent collaboration offers a promising avenue to transcend these boundaries. However, existing frameworks typically rely on prompt-based test-time interactions or multi-role configurations trained with homogeneous parameters, limiting error correction capabilities and strategic diversity. In this paper, we propose a Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2), which integrates policy learning with multi-agent tree search by formulating the multi-agent collaborative exploration process as a dynamic and learnable environment. By allowing agents to iteratively explore and refine within the environment, the framework facilitates evolution from parameter-sharing homogeneous multi-role training to heterogeneous multi-agent training, breaking through single-agent capability limits. We also introduce an efficient inference strategy MARTI-MARS2-T+ to fully exploit the scaling potential of multi-agent collaboration at test time. We conduct extensive experiments across varied model scales (8B, 14B, and 32B) on challenging code generation benchmarks. Utilizing two collaborating 32B models, MARTI-MARS2 achieves 77.7%, outperforming strong baselines like GPT-5.1. Furthermore, MARTI-MARS2 reveals a novel scaling law: shifting from single-agent to homogeneous multi-role and ultimately to heterogeneous multi-agent paradigms progressively yields higher RL performance ceilings, robust TTS capabilities, and greater policy diversity, suggesting that policy diversity is critical for scaling intelligence via multi-agent reinforcement learning. --- ### Evaluating and Calibrating LLM Confidence on Questions with Multiple Correct Answers Authors: Yuhan Wang, Shiyu Ni, Zhikai Ding, Zihang Zhan, Yuanzi Li, Keping Bi Published: 2026-02-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.07842v2 Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied under single-answer question answering. In this paper, we show that these methods break down in the presence of multiple valid answers, where disagreement among equally correct responses leads to systematic underestimation of confidence. To enable a systematic study of this phenomenon, we introduce MACE, a benchmark of 12,000 factual questions spanning six domains with varying numbers of correct answers. Experiments across 15 representative calibration methods and four LLM families (7B-72B) reveal that while accuracy increases with answer cardinality, estimated confidence consistently decreases, causing severe miscalibration for questions with mixed answer counts. To address this issue, we propose Semantic Confidence Aggregation (SCA), which aggregates confidence over multiple high-probability sampled responses. SCA achieves state-of-the-art calibration performance under mixed-answer settings while preserving strong calibration on single-answer questions. --- ### SAGE: Scalable AI Governance & Evaluation Authors: Benjamin Le, Xueying Lu, Nick Stern, Wenqiong Liu, Igor Lapchuk, Xiang Li, Baofen Zheng, Kevin Rosenberg, Jiewen Huang, Zhe Zhang, Abraham Cabangbang, Satej Milind Wagle et al. Published: 2026-02-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.07840v4 Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained human oversight and the high-throughput requirements of production systems. While traditional approaches rely on engagement proxies or sparse manual review, these methods often fail to capture the full scope of high-impact relevance failures. We present \textbf{SAGE} (Scalable AI Governance \& Evaluation), a framework that operationalizes high-quality human product judgment as a scalable evaluation signal. At the core of SAGE is a bidirectional calibration loop where natural-language \emph{Policy}, curated \emph{Precedent}, and an \emph{LLM Surrogate Judge} co-evolve. SAGE systematically resolves semantic ambiguities and misalignments, transforming subjective relevance judgment into an executable, multi-dimensional rubric with near human-level agreement. To bridge the gap between frontier model reasoning and industrial-scale inference, we apply teacher-student distillation to transfer high-fidelity judgments into compact student surrogates at \textbf{92$\times$} lower cost. Deployed within LinkedIn Search ecosystems, SAGE guided model iteration through simulation-driven development, distilling policy-aligned models for online serving and enabling rapid offline evaluation. In production, it powered policy oversight that measured ramped model variants and detected regressions invisible to engagement metrics. Collectively, these drove a \textbf{0.25\%} lift in LinkedIn daily active users. --- ### TodoEvolve: Learning to Architect Agent Planning Systems Authors: Jiaxi Liu, Yanzuo Jiang, Guibin Zhang, Zihan Zhang, Heng Chang, Zhenfei Yin, Qibing Ren, Junchi Yan Published: 2026-02-08 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.07839v1 Planning has become a central capability for contemporary agent systems in navigating complex, long-horizon tasks, yet existing approaches predominantly rely on fixed, hand-crafted planning structures that lack the flexibility to adapt to the structural diversity of open-ended problems. To address this limitation, we introduce TodoEvolve, a meta-planning paradigm that autonomously synthesizes and dynamically revises task-specific planning architectures. Specifically, we first construct PlanFactory, a modular design space that standardizes diverse planning paradigms within a unified codebase encompassing topology, initialization, adaptation, and navigation, thereby providing a common interface for heterogeneous planning patterns. Leveraging PlanFactory, we collect high-quality planning trajectories and train Todo-14B via \textit{Impedance-Guided Preference Optimization} (IGPO), a multi-objective reinforcement learning objective that encourages the generation of planning systems that are performant, stable, and token-efficient across arbitrary tasks and agent backbones. Empirical evaluations on five agentic benchmarks demonstrate that TodoEvolve consistently surpasses carefully engineered planning modules while maintaining economical API costs and runtime overhead. --- ### VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping Authors: Sanoojan Baliah, Yohan Abeysinghe, Rusiru Thushara, Khan Muhammad, Abhinav Dhall, Karthik Nandakumar, Muhammad Haris Khan Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07835v2 We present a training-free, plug-and-play method, namely VFace, for high-quality face swapping in videos. It can be seamlessly integrated with image-based face swapping approaches built on diffusion models. First, we introduce a Frequency Spectrum Attention Interpolation technique to facilitate generation and intact key identity characteristics. Second, we achieve Target Structure Guidance via plug-and-play attention injection to better align the structural features from the target frame to the generation. Third, we present a Flow-Guided Attention Temporal Smoothening mechanism that enforces spatiotemporal coherence without modifying the underlying diffusion model to reduce temporal inconsistencies typically encountered in frame-wise generation. Our method requires no additional training or video-specific fine-tuning. Extensive experiments show that our method significantly enhances temporal consistency and visual fidelity, offering a practical and modular solution for video-based face swapping. Our code is available at https://github.com/Sanoojan/VFace. --- ### Interpretable Analytic Calabi-Yau Metrics via Symbolic Distillation Authors: D Yang Eng Published: 2026-02-08 Categories: cs.LG, math.DG arXiv: https://arxiv.org/abs/2602.07834v2 The pointwise determinant ratio \( R_ψ(z)\equiv \log\!\left(\frac{\det g_{\mathrm{RF}}(z;ψ)}{\det g_{\mathrm{FS}}(z)}\right) \) measures how the Ricci-flat metric on the Dwork quintic departs from the Fubini--Study baseline. We ask whether this scalar observable can be described compactly in terms of a small number of projective invariants, and whether the same scaffold remains usable across complex-structure moduli. Using Donaldson's $k=10$ balanced metric as an algebraic teacher and symbolic regression on sampled points, we find that, within the restricted moduli-only feature class studied here, two low-order symmetric features, the power sum $p_2=\sum_i |z_i|^4$ and the cubic elementary symmetric polynomial $σ_3=e_3$, already capture most of the teacher variation. A degree-3 polynomial in $(p_2,σ_3)$ achieves held-out test $R^2=0.946$, while adding the remaining low-order symmetric generators changes this by less than $10^{-3}$. Within the same two-feature space, symbolic regression identifies a five-term rational-polynomial expression that matches the $k=10$ teacher with $R^2=0.9994$. Refitting the same functional scaffold across $ψ\in(0,0.8)$ keeps the mean determinant-ratio proxy $\langle R_ψ\rangle$ within $0.01\%$ of the local teachers on the sampled point clouds and yields smoothly varying fitted coefficients over the studied range. The holomorphic Yukawa coupling $κ_{111}=5$ is reproduced as a normalization check only. Taken together, these results provide a compact symbolic description of one metric-derived scalar observable on the Dwork family, while remaining bounded by the finite-$k$ teacher used for distillation rather than establishing a closed-form Ricci-flat metric. --- ### SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models Authors: Weijiang Lv, Yaoxuan Feng, Xiaobo Xia, Jiayu Wang, Yan Jing, Wenchao Chen, Bo Chen Published: 2026-02-08 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.07833v1 Chain-of-Thought reasoning is widely used to improve the interpretability of multimodal large language models (MLLMs), yet the faithfulness of the generated reasoning traces remains unclear. Prior work has mainly focused on perceptual hallucinations, leaving reasoning level unfaithfulness underexplored. To isolate faithfulness from linguistic priors, we introduce SPD-Faith Bench, a diagnostic benchmark based on fine-grained image difference reasoning that enforces explicit visual comparison. Evaluations on state-of-the-art MLLMs reveal two systematic failure modes, perceptual blindness and perception-reasoning dissociation. We trace these failures to decaying visual attention and representation shifts in the residual stream. Guided by this analysis, we propose SAGE, a train-free visual evidence-calibrated framework that improves visual routing and aligns reasoning with perception. Our results highlight the importance of explicitly evaluating faithfulness beyond response correctness. Our benchmark and codes are available at https://github.com/Johanson-colab/SPD-Faith-Bench. --- ### rePIRL: Learn PRM with Inverse RL for LLM Reasoning Authors: Xian Wu, Kaijie Zhu, Ying Zhang, Lun Wang, Wenbo Guo Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07832v3 Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking. In LLM reasoning, existing works also explore various solutions for learning effective process reward models (PRM) with or without the help of an expert policy. However, existing methods either rely on strong assumptions about the expert policies (e.g., requiring their reward functions) or suffer intrinsic limitations (e.g., entropy collapse), resulting in weak PRMs or limited generalizability. In this paper, we introduce rePIRL, an inverse RL-inspired framework that learns effective PRMs with minimal assumptions about expert policies. Specifically, we design a dual learning process that updates the policy and the PRM interchangeably. Our learning algorithm has customized techniques to address the challenges of scaling traditional inverse RL to LLMs. We theoretically show that our proposed learning framework can unify both online and offline PRM learning methods, justifying that rePIRL can learn PRMs with minimal assumptions. Empirical evaluations on standardized math and coding reasoning datasets demonstrate the effectiveness of rePIRL over existing methods. We further show the application of our trained PRM in test-time training, test-time scaling, and providing an early signal for training hard problems. Finally, we validate our training recipe and key design choices via a detailed ablation study. --- ### Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning Authors: Jiahui Zhou, Dan Li, Boxin Li, Xiao Zhang, Erli Meng, Lin Li, Zhuomin Chen, Jian Lou, See-Kiong Ng Published: 2026-02-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.07830v2 Time series is a pervasive data type across various application domains, rendering the reasonable solving of diverse time series tasks a long-standing goal. Recent advances in large language models (LLMs), especially their reasoning abilities unlocked through reinforcement learning (RL), have opened new opportunities for tackling tasks with long Chain-of-Thought (CoT) reasoning. However, leveraging LLM reasoning for time series remains in its infancy, hindered by the absence of carefully curated time series CoT data for training, limited data efficiency caused by underexplored data scheduling, and the lack of RL algorithms tailored for exploiting such time series CoT data. In this paper, we introduce VeriTime, a framework that tailors LLMs for time series reasoning through data synthesis, data scheduling, and RL training. First, we propose a data synthesis pipeline that constructs a TS-text multimodal dataset with process-verifiable annotations. Second, we design a data scheduling mechanism that arranges training samples according to a principled hierarchy of difficulty and task taxonomy. Third, we develop a two-stage reinforcement finetuning featuring fine-grained, multi-objective rewards that leverage verifiable process-level CoT data. Extensive experiments show that VeriTime substantially boosts LLM performance across diverse time series reasoning tasks. Notably, it enables compact 3B, 4B models to achieve reasoning capabilities on par with or exceeding those of larger proprietary LLMs. --- ### Efficient Representations are Controllable Representations Authors: Charles Ye, Jasmine Cui Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07828v1 What is the most brute-force way to install interpretable, controllable features into a model's activations? Controlling how LLMs internally represent concepts typically requires sophisticated methods to first identify, then intervene on the model's existing feature geometry. We bypass all of this. We finetune an LLM with a simple auxiliary loss, training 16 of its 3072 residual stream dimensions to be inert interpretability flags that simply indicate what concepts are required for generation. The model reorganizes around them anyway, learning to rely on these flags during actual generation tasks. As a result, these inert flags become genuine internal features: interpretable control switches that allow us to steer generation at inference time. Why does this work? When a feature is reliably supplied at a fixed location, gradient descent gradually eliminates redundant encodings elsewhere, and the model erodes its own alternative representations. A model's efficiency pressure is a lever - exploitable to induce interpretable, controllable representations. --- ### Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection Authors: Guoting Wei, Xia Yuan, Yang Zhou, Haizhao Jing, Yu Liu, Xianbiao Qi, Chunxia Zhao, Haokui Zhang, Rong Xiao Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07827v1 Open-Vocabulary Aerial Detection (OVAD) and Remote Sensing Visual Grounding (RSVG) have emerged as two key paradigms for aerial scene understanding. However, each paradigm suffers from inherent limitations when operating in isolation: OVAD is restricted to coarse category-level semantics, while RSVG is structurally limited to single-target localization. These limitations prevent existing methods from simultaneously supporting rich semantic understanding and multi-target detection. To address this, we propose OTA-Det, the first unified framework that bridges both paradigms into a cohesive architecture. Specifically, we introduce a task reformulation strategy that unifies task objectives and supervision mechanisms, enabling joint training across datasets from both paradigms with dense supervision signals. Furthermore, we propose a dense semantic alignment strategy that establishes explicit correspondence at multiple granularities, from holistic expressions to individual attributes, enabling fine-grained semantic understanding. To ensure real-time efficiency, OTA-Det builds upon the RT-DETR architecture, extending it from closed-set detection to open-text detection by introducing several high efficient modules, achieving state-of-the-art performance on six benchmarks spanning both OVAD and RSVG tasks while maintaining real-time inference at 34 FPS. --- ### Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training Authors: Yiwei Qin, Zhen Huang, Tiantian Mi, Weiye Si, Chenyang Zhou, Qipeng Guo, Siyuan Feng, Pengfei Liu Published: 2026-02-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.07824v1 Data quality determines foundation model performance, yet systematic processing frameworks are lacking. We introduce Data Darwinism, a ten-level taxonomy (L0-L9) that conceptualizes data-model co-evolution: advanced models produce superior data for next-generation systems. We validate this on scientific literature by constructing Darwin-Science, a 900B-token corpus (L0-L5). We identify a learnability gap in raw scientific text, which we bridge via L4 (Generative Refinement) and L5 (Cognitive Completion) using frontier LLMs to explicate reasoning and terminology. To ensure rigorous attribution, we pre-trained daVinci-origin-3B/7B models from scratch, excluding scientific content to create contamination-free baselines. After 600B tokens of continued pre-training, Darwin-Science outperforms baselines by +2.12 (3B) and +2.95 (7B) points across 20+ benchmarks, rising to +5.60 and +8.40 points on domain-aligned tasks. Systematic progression to L5 yields a +1.36 total gain, confirming that higher-level processing unlocks latent data value. We release the Darwin-Science corpus and daVinci-origin models to enable principled, co-evolutionary development. --- ### Back to Physics: Operator-Guided Generative Paths for SMS MRI Reconstruction Authors: Zhibo Chen, Yu Guan, Yajuan Huang, Chaoqi Chen, XiangJi, Qiuyun Fan, Dong Liang, Qiegen Liu Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07820v1 Simultaneous multi-slice (SMS) imaging with in-plane undersampling enables highly accelerated MRI but yields a strongly coupled inverse problem with deterministic inter-slice interference and missing k-space data. Most diffusion-based reconstructions are formulated around Gaussian-noise corruption and rely on additional consistency steps to incorporate SMS physics, which can be mismatched to the operator-governed degradations in SMS acquisition. We propose an operator-guided framework that models the degradation trajectory using known acquisition operators and inverts this process via deterministic updates. Within this framework, we introduce an operator-conditional dual-stream interaction network (OCDI-Net) that explicitly disentangles target-slice content from inter-slice interference and predicts structured degradations for operator-aligned inversion, and we instantiate reconstruction as a two-stage chained inference procedure that performs SMS slice separation followed by in-plane completion. Experiments on fastMRI brain data and prospectively acquired in vivo diffusion MRI data demonstrate improved fidelity and reduced slice leakage over conventional and learning-based SMS reconstructions. --- ### DINO-Mix: Distilling Foundational Knowledge with Cross-Domain CutMix for Semi-supervised Class-imbalanced Medical Image Segmentation Authors: Xinyu Liu, Guolei Sun Published: 2026-02-08 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.07819v1 Semi-supervised learning (SSL) has emerged as a critical paradigm for medical image segmentation, mitigating the immense cost of dense annotations. However, prevailing SSL frameworks are fundamentally "inward-looking", recycling information and biases solely from within the target dataset. This design triggers a vicious cycle of confirmation bias under class imbalance, leading to the catastrophic failure to recognize minority classes. To dismantle this systemic issue, we propose a paradigm shift to a multi-level "outward-looking" framework. Our primary innovation is Foundational Knowledge Distillation (FKD), which looks outward beyond the confines of medical imaging by introducing a pre-trained visual foundation model, DINOv3, as an unbiased external semantic teacher. Instead of trusting the student's biased high confidence, our method distills knowledge from DINOv3's robust understanding of high semantic uniqueness, providing a stable, cross-domain supervisory signal that anchors the learning of minority classes. To complement this core strategy, we further look outward within the data by proposing Progressive Imbalance-aware CutMix (PIC), which creates a dynamic curriculum that adaptively forces the model to focus on minority classes in both labeled and unlabeled subsets. This layered strategy forms our framework, DINO-Mix, which breaks the vicious cycle of bias and achieves remarkable performance on challenging semi-supervised class-imbalanced medical image segmentation benchmarks Synapse and AMOS. --- ### Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures Authors: Simiao Ren, Xingyu Shen, Ankit Raj, Albert Dai, Caroline, Zhang, Yuan Xu, Zexi Chen, Siqi Wu, Chen Gong, Yuxin Zhang Published: 2026-02-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07815v2 Facial age estimation plays a critical role in content moderation, age verification, and deepfake detection. However, no prior benchmark has systematically compared modern vision-language models (VLMs) with specialized age estimation architectures. We present the first large-scale cross-paradigm benchmark, evaluating 34 models - 22 specialized architectures with publicly available pretrained weights and 12 general-purpose VLMs - across eight standard datasets (UTKFace, IMDB-WIKI, MORPH, AFAD, CACD, FG-NET, APPA-REAL, and AgeDB), totaling 1,100 test images per model. Our key finding is striking: zero-shot VLMs significantly outperform most specialized models, achieving an average mean absolute error (MAE) of 5.65 years compared to 9.88 years for non-LLM models. The best-performing VLM (Gemini 3 Flash Preview, MAE 4.32) surpasses the strongest non-LLM model (MiVOLO, MAE 5.10) by 15%. MiVOLO - unique in combining face and body features using Vision Transformers - is the only specialized model that remains competitive with VLMs. We further analyze age verification at the 18-year threshold and find that most non-LLM models exhibit false adult rates between 39% and 100% for minors, whereas VLMs reduce this to 16%-29%. Additionally, coarse age binning (8-9 classes) consistently increases MAE beyond 13 years. Stratified analysis across 14 age groups reveals that all models struggle most at extreme ages (under 5 and over 65). Overall, these findings challenge the assumption that task-specific architectures are necessary for high-performance age estimation and suggest that future work should focus on distilling VLM capabilities into efficient specialized models. --- ### How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study Authors: Simiao Ren, Yuchen Zhou, Xingyu Shen, Kidus Zewde, Tommy Duong, George Huang, Hatsanai, Tiangratanakul, Tsang, Ng, En Wei, Jiayu Xue Published: 2026-02-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.07814v1 As AI-generated images proliferate across digital platforms, reliable detection methods have become critical for combating misinformation and maintaining content authenticity. While numerous deepfake detection methods have been proposed, existing benchmarks predominantly evaluate fine-tuned models, leaving a critical gap in understanding out-of-the-box performance -- the most common deployment scenario for practitioners. We present the first comprehensive zero-shot evaluation of 16 state-of-the-art detection methods, comprising 23 pretrained detector variants (due to multiple released versions of certain detectors), across 12 diverse datasets, comprising 2.6~million image samples spanning 291 unique generators including modern diffusion models. Our systematic analysis reveals striking findings: (1)~no universal winner exists, with detector rankings exhibiting substantial instability (Spearman~$ρ$: 0.01 -- 0.87 across dataset pairs); (2)~a 37~percentage-point performance gap separates the best detector (75.0\% mean accuracy) from the worst (37.5\%); (3)~training data alignment critically impacts generalization, causing up to 20--60\% performance variance within architecturally identical detector families; (4)~modern commercial generators (Flux~Dev, Firefly~v4, Midjourney~v7) defeat most detectors, achieving only 18--30\% average accuracy; and (5)~we identify three systematic failure patterns affecting cross-dataset generalization. Statistical analysis confirms significant performance differences between detectors (Friedman test: $χ^2$=121.01, $p<10^{-16}$, Kendall~$W$=0.524). Our findings challenge the ``one-size-fits-all'' detector paradigm and provide actionable deployment guidelines, demonstrating that practitioners must carefully select detectors based on their specific threat landscape rather than relying on published benchmark performance. --- ### LLMs Know More About Numbers than They Can Say Authors: Fengting Yuchi, Li Du, Jason Eisner Published: 2026-02-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.07812v2 Although state-of-the-art LLMs can solve math problems, we find that they make errors on numerical comparisons with mixed notation: "Which is larger, $5.7 \times 10^2$ or $580$?" This raises a fundamental question: Do LLMs even know how big these numbers are? We probe the hidden states of several smaller open-source LLMs. A single linear projection of an appropriate hidden layer encodes the log-magnitudes of both kinds of numerals, allowing us to recover the numbers with relative error of about 2.3% (on restricted synthetic text) or 19.06% (on scientific papers). Furthermore, the hidden state after reading a pair of numerals encodes their ranking, with a linear classifier achieving over 90% accuracy. Yet surprisingly, when explicitly asked to rank the same pairs of numerals, these LLMs achieve only 50-70% accuracy, with worse performance for models whose probes are less effective. Finally, we show that incorporating the classifier probe's log-loss as an auxiliary objective during finetuning brings an additional 3.22% improvement in verbalized accuracy over base models, demonstrating that improving models' internal magnitude representations can enhance their numerical reasoning capabilities. Our code is available at https://github.com/VCY019/Numeracy-Probing. --- ### Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models Authors: Xuan Ding, Pengyu Tong, Ranjie Duan, Yunjian Zhang, Rui Sun, Yao Zhu Published: 2026-02-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.07804v1 While large language models (LLMs) demonstrate impressive performance across various tasks, their deployment in real-world scenarios is still constrained by high computational demands. Layer-wise pruning, a commonly employed strategy to mitigate inference costs, can partially address this challenge. However, existing approaches generally depend on static heuristic rules and fail to account for the interdependencies among layers, thereby limiting the effectiveness of the pruning process. To this end, this paper proposes a game-theoretic framework that formulates layer pruning as a cooperative game in which each layer acts as a player and model performance serves as the utility. As computing exact Shapley values is computationally infeasible for large language models (LLMs), we propose using a lightweight surrogate network to estimate layer-wise marginal contributions. This network can predict LLM performance for arbitrary layer combinations at a low computational cost. Additionally, we employ stratified Monte Carlo mask sampling to further reduce the cost of Sharpley value estimation. This approach captures inter-layer dependencies and dynamically identifies critical layers for pruning. Extensive experiments demonstrate the consistent superiority of our method in terms of perplexity and zero-shot accuracy, achieving more efficient and effective layer-wise pruning for large language models. --- ### SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis Authors: Jiale Qian, Hao Meng, Tian Zheng, Pengcheng Zhu, Haopeng Lin, Yuhang Dai, Hanke Xie, Wenxiao Cao, Ruixuan Shang, Jun Wu, Hongmei Liu, Hanlin Wen et al. Published: 2026-02-08 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2602.07803v2 While recent years have witnessed rapid progress in speech synthesis, open-source singing voice synthesis (SVS) systems still face significant barriers to industrial deployment, particularly in terms of robustness and zero-shot generalization. In this report, we introduce SoulX-Singer, a high-quality open-source SVS system designed with practical deployment considerations in mind. SoulX-Singer supports controllable singing generation conditioned on either symbolic musical scores (MIDI) or melodic representations, enabling flexible and expressive control in real-world production workflows. Trained on more than 42,000 hours of vocal data, the system supports Mandarin Chinese, English, and Cantonese and consistently achieves state-of-the-art synthesis quality across languages under diverse musical conditions. Furthermore, to enable reliable evaluation of zero-shot SVS performance in practical scenarios, we construct SoulX-Singer-Eval, a dedicated benchmark with strict training-test disentanglement, facilitating systematic assessment in zero-shot settings. --- ### VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos Authors: Wenqi Liu, Yunxiao Wang, Shijie Ma, Meng Liu, Qile Su, Tianke Zhang, Haonan Fan, Changyi Liu, Kaiyu Jiang, Jiankang Chen, Kaiyu Tang, Bin Wen et al. Published: 2026-02-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.07801v4 In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic thinking-with-videos framework that jointly models video grounding and question answering. VideoTemp-o3 exhibits strong localization capability, supports on-demand clipping, and can refine inaccurate localizations. Specifically, in the supervised fine-tuning stage, we design a unified masking mechanism that encourages exploration while preventing noise. For reinforcement learning, we introduce dedicated rewards to mitigate reward hacking. Besides, from the data perspective, we develop an effective pipeline to construct high-quality long video grounded QA data, along with a corresponding benchmark for systematic evaluation across various video durations. Experimental results demonstrate that our method achieves remarkable performance on both long video understanding and grounding. --- ### Approximating Matrix Functions with Deep Neural Networks and Transformers Authors: Rahul Padmanabhan, Simone Brugiapaglia Published: 2026-02-08 Categories: cs.LG, cs.NE, math.NA arXiv: https://arxiv.org/abs/2602.07800v1 Transformers have revolutionized natural language processing, but their use for numerical computation has received less attention. We study the approximation of matrix functions, which map scalar functions to matrices, using neural networks including transformers. We focus on functions mapping square matrices to square matrices of the same dimension. These types of matrix functions appear throughout scientific computing, e.g., the matrix exponential in continuous-time Markov chains and the matrix sign function in stability analysis of dynamical systems. In this paper, we make two contributions. First, we prove bounds on the width and depth of ReLU networks needed to approximate the matrix exponential to an arbitrary precision. Second, we show experimentally that a transformer encoder-decoder with suitable numerical encodings can approximate certain matrix functions at a relative error of 5% with high probability. Our study reveals that the encoding scheme strongly affects performance, with different schemes working better for different functions. --- ### Fairness Aware Reward Optimization Authors: Ching Lam Choi, Vighnesh Subramaniam, Phillip Isola, Antonio Torralba, Stefanie Jegelka Published: 2026-02-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.07799v1 Demographic skews in human preference data propagate systematic unfairness through reward models into aligned LLMs. We introduce Fairness Aware Reward Optimization (Faro), an in-processing framework that trains reward models under demographic parity, equalized odds, or counterfactual fairness constraints. We provide the first theoretical analysis of reward-level fairness in LLM alignment, establishing: (i) provable fairness certificates for Faro-trained rewards with controllable slack; a (ii) formal characterization of the accuracy-fairness trade-off induced by KL-regularized fine-tuning, proving fairness transfers from reward to policy; and the (iii) existence of a non-empty Pareto frontier. Unlike pre- and post-processing methods, Faro ensures reward models are simultaneously ordinal (ranking correctly), cardinal (calibrated), and fair. Across multiple LLMs and benchmarks, Faro significantly reduces bias and harmful generations while maintaining or improving model quality. ---