# Research Papers — 2026-02 · bundle page 166 of 210

> Full-text markdown of papers #8251–8300 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/166
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/165.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/167.md)

### MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language Models

Authors: Haojin Wang, Yike Wang, Shangbin Feng, Hannaneh Hajishirzi, Yulia Tsvetkov
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.05307v3

Large reasoning models (LRMs) have demonstrated impressive reasoning capabilities, but their solutions are often verbose and computationally expensive, and taxing for users to read. In contrast, small language models (SLMs) produce concise outputs with lower inference costs, yet they frequently struggle on challenging multi-step reasoning tasks. Existing inference-time collaboration methods attempt to bridge this gap through imitation, encouraging SLMs to follow the reasoning process of LRMs. However, the student often inherits the mentor's overthinking, producing long and reflective reasoning chains while still falling short in accuracy. We propose MentorCollab, a collaboration method based on mentorship: the SLM remains the primary generator and consults the LRM only when additional reasoning support is needed. At sparsely sampled token positions, we probe for divergence between the two models and use a lightweight verifier to decide whether the SLM should follow a short lookahead segment from its mentor or continue on its own. Across 15 SLM-LRM pairs and 3 domains, our method achieves an average gain of 3.0%, with improvements of up to 8.0% in 12 settings. The resulting traces remain shorter than the mentor's, using only a small fraction of its tokens. These results demonstrate that selective, verified mentorship can boost reasoning accuracy while preserving concise generation.

---

### MentorCollab: Selective Large-to-Small Inference-Time Guidance for Efficient Reasoning

Authors: Haojin Wang, Yike Wang, Shangbin Feng, Hannaneh Hajishirzi, Yulia Tsvetkov
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.05307v2

Large reasoning models (LRMs) achieve strong performance by producing long chains of thought, but their inference costs are high and often generate redundant reasoning. Small language models (SLMs) are far more efficient, yet struggle on multi-step reasoning tasks. A natural idea is to let a large model guide a small one at inference time as a mentor, yet existing collaboration methods often promote imitation, resulting in verbose reasoning without consistent error correction. We propose MentorCollab, an inference-time collaboration method in which an LRM selectively and sparsely guides an SLM, rather than taking over generation. At randomly sampled token positions, we probe for divergences between the two models and use a lightweight verifier to decide whether the SLM should follow a short lookahead segment from its mentor or continue on its own. Across 15 SLM--LRM pairs and 3 domains (math reasoning, general knowledge, and commonsense reasoning), our method improves performance in 12 settings, with average gains of 3.0% and up to 8.0%, while adopting only having 18.4% tokens generated by the expensive mentor model on average. We find that short segments and selective probing are sufficient for effective collaboration. Our results show that selective inference-time guidance restores large-model reasoning ability without substantial inference overhead.

---

### FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion

Authors: Zhuokun Chen, Jianfei Cai, Bohan Zhuang
Published: 2026-02-05
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.05305v3

Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves inference efficiency via KV caching and block-wise causal inference and has been widely adopted in diffusion language models and video generation. However, in long-context settings, block diffusion still incurs substantial overhead from repeatedly computing attention over a growing KV cache. We identify an underexplored property of block diffusion: cross-step redundancy of attention within a block. Our analysis shows that attention outputs from tokens outside the current block remain largely stable across diffusion steps, while block-internal attention varies significantly. Based on this observation, we propose FlashBlock, a cached block-external attention mechanism that reuses stable attention output, reducing attention computation and KV cache access without modifying the diffusion process. Moreover, FlashBlock is orthogonal to sparse attention and can be combined as a complementary residual reuse strategy, substantially improving model accuracy under aggressive sparsification. Experiments on diffusion language models and video generation demonstrate up to 1.44$\times$ higher token throughput and up to 1.6$\times$ reduction in attention time, with negligible impact on generation quality. Project page: https://caesarhhh.github.io/FlashBlock/.

---

### A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms

Authors: Feng Zhu, Robert W. Heath, Aritra Mitra
Published: 2026-02-05
Categories: cs.LG, eess.SY, math.OC
arXiv: https://arxiv.org/abs/2602.05304v2

Stochastic variance-reduced algorithms such as Stochastic Average Gradient (SAG) and SAGA, and their deterministic counterparts like the Incremental Aggregated Gradient (IAG) method, have been extensively studied in large-scale machine learning. Despite their popularity, existing analyses for these algorithms are disparate, relying on different proof techniques tailored to each method. Furthermore, the original proof of SAG is known to be notoriously involved, requiring computer-aided analysis. Focusing on finite-sum optimization with smooth and strongly convex objective functions, our main contribution is to develop a single unified convergence analysis that applies to all three algorithms: SAG, SAGA, and IAG. Our analysis features two key steps: (i) establishing a bound on delays due to stochastic sub-sampling using simple concentration tools, and (ii) carefully designing a novel Lyapunov function that accounts for such delays. The resulting proof is short and modular, providing the first high-probability bounds for SAG and SAGA that can be seamlessly extended to non-convex objectives and Markov sampling. As an immediate byproduct of our new analysis technique, we obtain the best known rates for the IAG algorithm, significantly improving upon prior bounds.

---

### PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios

Authors: Chris Zhu, Sasha Cui, Will Sanok Dufallo, Runzhi Jin, Zhen Xu, Linjun Zhang, Daylian Cain
Published: 2026-02-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.05302v3

We present an in-depth evaluation of LLMs' ability to negotiate, a central business task requiring strategic reasoning, theory of mind, and economic value creation. To do so, we introduce PieArena, a large-scale negotiation benchmark grounded in multi-agent interactions over realistic scenarios adapted from MBA negotiation courses at an elite business school. We evaluate language agents across three pairing regimes: mirror-play, cross-play, and human-LM play. We develop a ranking model for continuous negotiation payoffs that yields order-invariant, uncertainty-quantified leaderboards while correcting for systematic experimental asymmetries. We further study the effects of joint-intentionality agentic scaffolding and find asymmetric gains, with large improvements for mid- and lower-tier LMs and diminishing returns for frontier LMs. As calibration anchors, we collect human-human and human-LM negotiation data from trained business school students, finding that a representative frontier language agent (GPT-5) matches or exceeds this human baseline in our evaluation settings. Beyond deal outcomes, PieArena provides a multi-dimensional behavioral profile that reveals cross-model heterogeneity in instruction compliance, computation accuracy, as well as judge-assessed deception and reputation, illustrating the value of evaluation beyond outcome-only leaderboards.

---

### Logarithmic-time Schedules for Scaling Language Models with Momentum

Authors: Damien Ferbach, Courtney Paquette, Gauthier Gidel, Katie Everett, Elliot Paquette
Published: 2026-02-05
Categories: stat.ML, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2602.05298v2

In practice, the hyperparameters $(β_1, β_2)$ and weight-decay $λ$ in AdamW are typically kept at fixed values. Is there any reason to do otherwise? We show that for large-scale language model training, the answer is yes: by exploiting the power-law structure of language data, one can design time-varying schedules for $(β_1, β_2, λ)$ that deliver substantial performance gains. We study logarithmic-time scheduling, in which the optimizer's gradient memory horizon grows with training time. Although naive variants of this are unstable, we show that suitable damping mechanisms restore stability while preserving the benefits of longer memory. Based on this, we present ADANA, an AdamW-like optimizer that couples log-time schedules with explicit damping to balance stability and performance. We empirically evaluate ADANA across transformer scalings (45M to 2.6B parameters), comparing against AdamW, Muon, and AdEMAMix. When properly tuned, ADANA achieves up to 40% compute efficiency relative to a tuned AdamW, with gains that persist--and even improve--as model scale increases. We further show that similar benefits arise when applying logarithmic-time scheduling to AdEMAMix, and that logarithmic-time weight-decay alone can yield significant improvements. Finally, we present variants of ADANA that mitigate potential failure modes and improve robustness.

---

### Aspect-Aware MOOC Recommendation in a Heterogeneous Network

Authors: Seongyeub Chu, Jongwoo Kim, Mun Yong Yi
Published: 2026-02-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.05297v1

MOOC recommendation systems have received increasing attention to help learners navigate and select preferred learning content. Traditional methods such as collaborative filtering and content-based filtering suffer from data sparsity and over-specialization. To alleviate these limitations, graph-based approaches have been proposed; however, they still rely heavily on manually predefined metapaths, which often capture only superficial structural relationships and impose substantial burdens on domain experts as well as significant engineering costs. To overcome these limitations, we propose AMR (Aspect-aware MOOC Recommendation), a novel framework that models path-specific multiple aspects by embedding the semantic content of nodes within each metapath. AMR automatically discovers metapaths through bi-directional walks, derives aspect-aware path representations using a bi-LSTM-based encoder, and incorporates these representations as edge features in the learner-learner and KC-KC subgraphs to achieve fine-grained semantically informed KC recommendations. Extensive experiments on the large-scale MOOCCube and PEEK datasets show that AMR consistently outperforms state-of-the-art graph neural network baselines across key metrics such as HR@K and nDCG@K. Further analysis confirms that AMR effectively captures rich path-specific aspect information, allowing more accurate recommendations than those methods that rely solely on predefined metapaths. The code will be available upon accepted.

---

### Fast-SAM3D: 3Dfy Anything in Images but Faster

Authors: Weilun Feng, Mingqiang Wu, Zhiliang Chen, Chuanguang Yang, Haotong Qin, Yuqi Li, Xiaokun Liu, Guoxin Fan, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu et al.
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05293v2

SAM3D enables scalable, open-world 3D reconstruction from complex scenes, yet its deployment is hindered by prohibitive inference latency. In this work, we conduct the \textbf{first systematic investigation} into its inference dynamics, revealing that generic acceleration strategies are brittle in this context. We demonstrate that these failures stem from neglecting the pipeline's inherent multi-level \textbf{heterogeneity}: the kinematic distinctiveness between shape and layout, the intrinsic sparsity of texture refinement, and the spectral variance across geometries. To address this, we present \textbf{Fast-SAM3D}, a training-free framework that dynamically aligns computation with instantaneous generation complexity. Our approach integrates three heterogeneity-aware mechanisms: (1) \textit{Modality-Aware Step Caching} to decouple structural evolution from sensitive layout updates; (2) \textit{Joint Spatiotemporal Token Carving} to concentrate refinement on high-entropy regions; and (3) \textit{Spectral-Aware Token Aggregation} to adapt decoding resolution. Extensive experiments demonstrate that Fast-SAM3D delivers up to \textbf{2.67$\times$} end-to-end speedup with negligible fidelity loss, establishing a new Pareto frontier for efficient single-view 3D generation. Our code is released in https://github.com/wlfeng0509/Fast-SAM3D.

---

### Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science

Authors: Jingru Fan, Dewen Liu, Yufan Dang, Huatao Li, Yuheng Wang, Wei Liu, Feiyu Duan, Xuanwen Ding, Shu Yao, Lin Wu, Ruijie Shi, Wai-Shing Leung et al.
Published: 2026-02-05
Categories: cs.CL, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2602.05289v1

Recent advancements in Large Language Models (LLMs) have greatly extended the capabilities of Multi-Agent Systems (MAS), demonstrating significant effectiveness across a wide range of complex and open-ended domains. However, despite this rapid progress, the field still relies heavily on empirical trial-and-error. It lacks a unified and principled scientific framework necessary for systematic optimization and improvement. This bottleneck stems from the ambiguity of attribution: first, the absence of a structured taxonomy of factors leaves researchers restricted to unguided adjustments; second, the lack of a unified metric fails to distinguish genuine collaboration gain from mere resource accumulation. In this paper, we advocate for a transition to design science through an integrated framework. We advocate to establish the collaboration gain metric ($Γ$) as the scientific standard to isolate intrinsic gains from increased budgets. Leveraging $Γ$, we propose a factor attribution paradigm to systematically identify collaboration-driving factors. To support this, we construct a systematic MAS factor library, structuring the design space into control-level presets and information-level dynamics. Ultimately, this framework facilitates the transition from blind experimentation to rigorous science, paving the way towards a true science of Collective AI.

---

### Position: Universal Time Series Foundation Models Rest on a Category Error

Authors: Xilin Dai, Wanxu Cai, Zhijian Xu, Qiang Xu
Published: 2026-02-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.05287v2

This position paper argues that the pursuit of "Universal Foundation Models for Time Series" rests on a fundamental category error, mistaking a structural Container for a semantic Modality. We contend that because time series hold incompatible generative processes (e.g., finance vs. fluid dynamics), monolithic models degenerate into expensive "Generic Filters" that fail to generalize under distributional drift. To address this, we introduce the "Autoregressive Blindness Bound," a theoretical limit proving that history-only models cannot predict intervention-driven regime shifts. We advocate replacing universality with a Causal Control Agent paradigm, where an agent leverages external context to orchestrate a hierarchy of specialized solvers, from frozen domain experts to lightweight Just-in-Time adaptors. We conclude by calling for a shift in benchmarks from "Zero-Shot Accuracy" to "Drift Adaptation Speed" to prioritize robust, control-theoretic systems.

---

### HealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction

Authors: Dahai Yu, Lin Jiang, Rongchao Xu, Guang Wang
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.05286v3

Healthcare facility visit prediction is essential for optimizing healthcare resource allocation and informing public health policy. Despite advanced machine learning methods being employed for better prediction performance, existing works usually formulate this task as a time-series forecasting problem without considering the intrinsic spatial dependencies of different types of healthcare facilities, and they also fail to provide reliable predictions under abnormal situations such as public emergencies. To advance existing research, we propose HealthMamba, an uncertainty-aware spatiotemporal framework for accurate and reliable healthcare facility visit prediction. HealthMamba comprises three key components: (i) a Unified Spatiotemporal Context Encoder that fuses heterogeneous static and dynamic information, (ii) a novel Graph State Space Model called GraphMamba for hierarchical spatiotemporal modeling, and (iii) a comprehensive uncertainty quantification module integrating three uncertainty quantification mechanisms for reliable prediction. We evaluate HealthMamba on four large-scale real-world datasets from California, New York, Texas, and Florida. Results show HealthMamba achieves around 6.0% improvement in prediction accuracy and 3.5% improvement in uncertainty quantification over state-of-the-art baselines.

---

### Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization

Authors: Minhuan Li, Jiequn Han, Pilar Cossio, Luhuan Wu
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.05285v2

A core challenge in structural biophysics is generating biomolecular conformations that are both physically plausible and consistent with experimental measurements. While sequence-to-structure diffusion models provide powerful priors, posterior sampling methods steer generation by perturbing atomic coordinates with gradients from experimental likelihoods. However, when the target lies in a low-density region of the prior, these methods require aggressive upweighting of the likelihood that can destabilize sampling and be sensitive to hyperparameters. We propose EmbedOpt, an inference-time steering framework that introduces an orthogonal optimization axis: rather than performing posterior sampling under a fixed prior, EmbedOpt directly optimizes the prior by updating the model's conditional embedding. This embedding space encodes rich coevolutionary signals, so optimizing it shifts the structural prior to align with experimental constraints. Empirically, EmbedOpt matches coordinate-based posterior sampling baselines on sparse distance constraints and outperforms them on cryo-electron microscopy map fitting, including real, noisy experimental ones. Furthermore, EmbedOpt's smooth optimization behavior yields robustness to hyperparameters spanning two orders of magnitude and enables comparable performance with fewer diffusion steps. Code is available at https://github.com/rs-station/embedopt.

---

### Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities

Authors: Pengyi Li, Elizaveta Goncharova, Andrey Kuznetsov, Ivan Oseledets
Published: 2026-02-05
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.05281v2

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy Optimization (GRPO), often converge to low-entropy policies, leading to severe mode collapse and limited output diversity. We analyze this issue from the perspective of sampling probability dynamics, identifying that the standard objective disproportionately reinforces the highest-likelihood paths, thereby suppressing valid alternative reasoning chains. To address this, we propose a novel Advantage Re-weighting Mechanism (ARM) designed to equilibrate the confidence levels across all correct responses. By incorporating Prompt Perplexity and Answer Confidence into the advantage estimation, our method dynamically reshapes the reward signal to attenuate the gradient updates of over-confident reasoning paths, while redistributing probability mass toward under-explored correct solutions. Empirical results demonstrate that our approach significantly enhances generative diversity and response entropy while maintaining competitive accuracy, effectively achieving a superior trade-off between exploration and exploitation in reasoning tasks. Empirical results on Qwen2.5 and DeepSeek models across mathematical and coding benchmarks show that ProGRPO significantly mitigates entropy collapse. Specifically, on Qwen2.5-7B, our method outperforms GRPO by 5.7% in Pass@1 and, notably, by 13.9% in Pass@32, highlighting its superior capability in generating diverse correct reasoning paths.

---

### Hallucination-Resistant Security Planning with a Large Language Model

Authors: Kim Hammar, Tansu Alpcan, Emil Lupu
Published: 2026-02-05
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2602.05279v1

Large language models (LLMs) are promising tools for supporting security management tasks, such as incident response planning. However, their unreliability and tendency to hallucinate remain significant challenges. In this paper, we address these challenges by introducing a principled framework for using an LLM as decision support in security management. Our framework integrates the LLM in an iterative loop where it generates candidate actions that are checked for consistency with system constraints and lookahead predictions. When consistency is low, we abstain from the generated actions and instead collect external feedback, e.g., by evaluating actions in a digital twin. This feedback is then used to refine the candidate actions through in-context learning (ICL). We prove that this design allows to control the hallucination risk by tuning the consistency threshold. Moreover, we establish a bound on the regret of ICL under certain assumptions. To evaluate our framework, we apply it to an incident response use case where the goal is to generate a response and recovery plan based on system logs. Experiments on four public datasets show that our framework reduces recovery times by up to 30% compared to frontier LLMs.

---

### Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs

Authors: Qi Li, Yanzhe Zhao, Yongxin Zhou, Yameng Wang, Yandong Yang, Yuanjia Zhou, Jinxiang Liu
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05275v2

Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrieval, which aims to find relevant items of various modalities for a given query. However, their practical application is often hindered by the substantial computational cost incurred from processing a large number of tokens from visual inputs. In this paper, we propose Magic-MM-Embedding, a series of novel models that achieve both high efficiency and state-of-the-art performance in universal multimodal embedding. Our approach is built on two synergistic pillars: (1) a highly efficient MLLM architecture incorporating visual token compression to drastically reduce inference latency and training time, and (2) a multi-stage progressive training strategy designed to not only recover but significantly boost performance. This coarse-to-fine training paradigm begins with extensive continued training to restore multimodal understanding and generation capabilities, progresses to large-scale contrastive pretraining and hard negative mining to enhance discriminative power, and culminates in a task-aware fine-tuning stage guided by an MLLM-as-a-Judge for precise data curation. Comprehensive experiments show that our model outperforms existing methods by a large margin while being more inference-efficient.

---

### Asymptotically optimal sequential change detection for bounded means

Authors: Ashwin Ram, Aaditya Ramdas
Published: 2026-02-05
Categories: math.ST, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2602.05272v1

We consider the problem of quickest changepoint detection under the Average Run Length (ARL) constraint where the pre-change and post-change laws lie in composite families $\mathscr{P}$ and $\mathscr{Q}$ respectively. In such a problem, a massive challenge is characterizing the best possible detection delay when the "hardest" pre-change law in $\mathscr{P}$ depends on the unknown post-change law $Q\in\mathscr{Q}$. And typical simple-hypothesis likelihood-ratio arguments for Page-CUSUM and Shiryaev-Roberts do not at all apply here. To that end, we derive a universal sharp lower bound in full generality for any ARL-calibrated changepoint detector in the low type-I error ($γ\to\infty$ regime) of the order $\log(γ)/\mathrm{KL}_{\mathrm{inf}}(Q,\mathscr{P})$. We show achievability of this universal lower bound by proving a tight matching upper bound (with the same sharp $\logγ$ constant) in the important bounded mean detection setting. In addition, for separated mean shifts, we also we derive a uniform minimax guarantee of this achievability over the alternatives.

---

### Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning

Authors: Shengqin Jiang, Xiaoran Feng, Yuankai Qi, Haokui Zhang, Renlong Hang, Qingshan Liu, Lina Yao, Quan Z. Sheng, Ming-Hsuan Yang
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05271v1

Few-shot class-incremental learning (FSCIL) seeks to continuously learn new classes from very limited samples while preserving previously acquired knowledge. Traditional methods often utilize a frozen pre-trained feature extractor to generate static class prototypes, which suffer from the inherent representation bias of the backbone. While recent prompt-based tuning methods attempt to adapt the backbone via minimal parameter updates, given the constraint of extreme data scarcity, the model's capacity to assimilate novel information and substantively enhance its global discriminative power is inherently limited. In this paper, we propose a novel shift in perspective: freezing the feature extractor while fine-tuning the prototypes. We argue that the primary challenge in FSCIL is not feature acquisition, but rather the optimization of decision regions within a static, high-quality feature space. To this end, we introduce an efficient prototype fine-tuning framework that evolves static centroids into dynamic, learnable components. The framework employs a dual-calibration method consisting of class-specific and task-aware offsets. These components function synergistically to improve the discriminative capacity of prototypes for ongoing incremental classes. Extensive results demonstrate that our method attains superior performance across multiple benchmarks while requiring minimal learnable parameters.

---

### Hybrid Gated Flow (HGF): Stabilizing 1.58-bit LLMs via Selective Low-Rank Correction

Authors: David Alejandro Trejo Pizzo
Published: 2026-02-05
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.05269v1

The deployment of Large Language Models (LLMs) on edge devices is fundamentally constrained by the "Memory Wall" -- a hardware limitation where memory bandwidth, not compute, becomes the bottleneck. Recent 1.58-bit quantization techniques (e.g., BitNet b1.58) dramatically reduce memory footprint but typically incur a perplexity degradation of 20-25% compared to FP16 baselines. In this work, we introduce Hybrid Gated Flow (HGF), a dual-stream architecture that couples a 1.58-bit ternary backbone with a learnable, low-rank FP16 correction path controlled by adaptive gates. Through extensive experiments on the TinyStories dataset across two training regimes (2500 and 3500 steps), we demonstrate that HGF 5.4 achieves a validation loss of 0.9306 compared to BitNet's 1.0294, recovering approximately 55% of the quality gap between pure ternary quantization and the FP16 baseline (0.8490). This recovery is achieved with only ~12-15% memory overhead beyond the ternary backbone. Furthermore, we provide empirical evidence for an emergent phenomenon: quantization as structural regularization. While a full-precision differential attention baseline (Diff_Only) exhibited training instability with validation loss exceeding 1.68, the ternary-anchored HGF maintained robust convergence throughout training. Finally, we report preliminary results extending this architecture to 1.2B and 3B parameter models trained on SlimPajama and FineWeb-Edu. These larger-scale experiments confirm that the architectural stability and quality recovery observed in small-scale proxies scale linearly to production-grade language modeling regimes.

---

### Beyond Cosine Similarity

Authors: Xinbo Ai
Published: 2026-02-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.05266v1

Cosine similarity, the standard metric for measuring semantic similarity in vector spaces, is mathematically grounded in the Cauchy-Schwarz inequality, which inherently limits it to capturing linear relationships--a constraint that fails to model the complex, nonlinear structures of real-world semantic spaces. We advance this theoretical underpinning by deriving a tighter upper bound for the dot product than the classical Cauchy-Schwarz bound. This new bound leads directly to recos, a similarity metric that normalizes the dot product by the sorted vector components. recos relaxes the condition for perfect similarity from strict linear dependence to ordinal concordance, thereby capturing a broader class of relationships. Extensive experiments across 11 embedding models--spanning static, contextualized, and universal types--demonstrate that recos consistently outperforms traditional cosine similarity, achieving higher correlation with human judgments on standard Semantic Textual Similarity (STS) benchmarks. Our work establishes recos as a mathematically principled and empirically superior alternative, offering enhanced accuracy for semantic analysis in complex embedding spaces.

---

### ReGLA: Efficient Receptive-Field Modeling with Gated Linear Attention Network

Authors: Junzhou Li, Manqi Zhao, Yilin Gao, Zhiheng Yu, Yin Li, Dongsheng Jiang, Li Xiao
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05262v1

Balancing accuracy and latency on high-resolution images is a critical challenge for lightweight models, particularly for Transformer-based architectures that often suffer from excessive latency. To address this issue, we introduce \textbf{ReGLA}, a series of lightweight hybrid networks, which integrates efficient convolutions for local feature extraction with ReLU-based gated linear attention for global modeling. The design incorporates three key innovations: the Efficient Large Receptive Field (ELRF) module for enhancing convolutional efficiency while preserving a large receptive field; the ReLU Gated Modulated Attention (RGMA) module for maintaining linear complexity while enhancing local feature representation; and a multi-teacher distillation strategy to boost performance on downstream tasks. Extensive experiments validate the superiority of ReGLA; particularly the ReGLA-M achieves \textbf{80.85\%} Top-1 accuracy on ImageNet-1K at $224px$, with only \textbf{4.98 ms} latency at $512px$. Furthermore, ReGLA outperforms similarly scaled iFormer models in downstream tasks, achieving gains of \textbf{3.1\%} AP on COCO object detection and \textbf{3.6\%} mIoU on ADE20K semantic segmentation, establishing it as a state-of-the-art solution for high-resolution visual applications.

---

### Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR

Authors: Fanfan Liu, Youyang Yin, Peng Shi, Siqi Yang, Zhixiong Zeng, Haibo Qiu
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.05261v1

Recent applications of Reinforcement Learning with Verifiable Rewards (RLVR) to Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated significant success in enhancing reasoning capabilities for complex tasks. During RLVR training, an increase in response length is often regarded as a key factor contributing to the growth of reasoning ability. However, the patterns of change in response length vary significantly across different RLVR algorithms during the training process. To provide a fundamental explanation for these variations, this paper conducts an in-depth analysis of the components of mainstream RLVR algorithms. We present a theoretical analysis of the factors influencing response length and validate our theory through extensive experimentation. Building upon these theoretical findings, we propose the Length-Unbiased Sequence Policy Optimization (LUSPO) algorithm. Specifically, we rectify the length bias inherent in Group Sequence Policy Optimization (GSPO), rendering its loss function unbiased with respect to response length and thereby resolving the issue of response length collapse. We conduct extensive experiments across mathematical reasoning benchmarks and multimodal reasoning scenarios, where LUSPO consistently achieves superior performance. Empirical results demonstrate that LUSPO represents a novel, state-of-the-art optimization strategy compared to existing methods such as GRPO and GSPO.

---

### An Asymptotic Law of the Iterated Logarithm for $\mathrm{KL}_{\inf}$

Authors: Ashwin Ram, Aaditya Ramdas
Published: 2026-02-05
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.05259v1

The population $\mathrm{KL}_{\inf}$ is a fundamental quantity that appears in lower bounds for (asymptotically) optimal regret of pure-exploration stochastic bandit algorithms, and optimal stopping time of sequential tests. Motivated by this, an empirical $\mathrm{KL}_{\inf}$ statistic is frequently used in the design of (asymptotically) optimal bandit algorithms and sequential tests. While nonasymptotic concentration bounds for the empirical $\mathrm{KL}_{\inf}$ have been developed, their optimality in terms of constants and rates is questionable, and their generality is limited (usually to bounded observations). The fundamental limits of nonasymptotic concentration are often described by the asymptotic fluctuations of the statistics. With that motivation, this paper presents a tight (upper and lower) law of the iterated logarithm for empirical $\mathrm{KL}_{\inf}$ applying to extremely general (unbounded) data.

---

### CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs

Authors: Haoran Li, Sucheng Ren, Alan Yuille, Feng Wang
Published: 2026-02-05
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.05258v1

Rotary Positional Embedding (RoPE) is a key component of context scaling in Large Language Models (LLMs). While various methods have been proposed to adapt RoPE to longer contexts, their guiding principles generally fall into two categories: (1) out-of-distribution (OOD) mitigation, which scales RoPE frequencies to accommodate unseen positions, and (2) Semantic Modeling, which posits that the attention scores computed with RoPE should always prioritize semantically similar tokens. In this work, we unify these seemingly distinct objectives through a minimalist intervention, namely CoPE: soft clipping lowfrequency components of RoPE. CoPE not only eliminates OOD outliers and refines semantic signals, but also prevents spectral leakage caused by hard clipping. Extensive experiments demonstrate that simply applying our soft clipping strategy to RoPE yields significant performance gains that scale up to 256k context length, validating our theoretical analysis and establishing CoPE as a new state-of-the-art for length generalization. Our code, data, and models are available at https://github.com/hrlics/CoPE.

---

### RFM-Pose:Reinforcement-Guided Flow Matching for Fast Category-Level 6D Pose Estimation

Authors: Diya He, Qingchen Liu, Cong Zhang, Jiahu Qin
Published: 2026-02-05
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.05257v1

Object pose estimation is a fundamental problem in computer vision and plays a critical role in virtual reality and embodied intelligence, where agents must understand and interact with objects in 3D space. Recently, score based generative models have to some extent solved the rotational symmetry ambiguity problem in category level pose estimation, but their efficiency remains limited by the high sampling cost of score-based diffusion. In this work, we propose a new framework, RFM-Pose, that accelerates category-level 6D object pose generation while actively evaluating sampled hypotheses. To improve sampling efficiency, we adopt a flow-matching generative model and generate pose candidates along an optimal transport path from a simple prior to the pose distribution. To further refine these candidates, we cast the flow-matching sampling process as a Markov decision process and apply proximal policy optimization to fine-tune the sampling policy. In particular, we interpret the flow field as a learnable policy and map an estimator to a value network, enabling joint optimization of pose generation and hypothesis scoring within a reinforcement learning framework. Experiments on the REAL275 benchmark demonstrate that RFM-Pose achieves favorable performance while significantly reducing computational cost. Moreover, similar to prior work, our approach can be readily adapted to object pose tracking and attains competitive results in this setting.

---

### Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks

Authors: Guangwei Zhang, Jianing Zhu, Cheng Qian, Neil Gong, Rada Mihalcea, Zhaozhuo Xu, Jingrui He, Jiaqi Ma, Yun Huang, Chaowei Xiao, Bo Li, Ahmed Abbasi et al.
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.05252v2

We present Copyright Detective, the first interactive forensic system for detecting, analyzing, and visualizing potential copyright risks in LLM outputs. The system treats copyright infringement versus compliance as an evidence discovery process rather than a static classification task due to the complex nature of copyright law. It integrates multiple detection paradigms, including content recall testing, paraphrase-level similarity analysis, persuasive jailbreak probing, and unlearning verification, within a unified and extensible framework. Through interactive prompting, response collection, and iterative workflows, our system enables systematic auditing of verbatim memorization and paraphrase-level leakage, supporting responsible deployment and transparent evaluation of LLM copyright risks even with black-box access.

---

### TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training

Authors: Guanjie Cheng, Boyi Li, Lingyu Sun, Mengying Zhu, Yangyang Wu, Xinkui Zhao, Shuiguang Deng
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.05251v1

Large-scale multimodal pre-trained models like CLIP rely heavily on high-quality training data, yet raw web-crawled datasets are often noisy, misaligned, and redundant, leading to inefficient training and suboptimal generalization. Existing data selection methods are either heuristic-based, suffering from bias and limited diversity, or data-driven but task-agnostic, failing to optimize for multi-task scenarios. To address these gaps, we introduce TADS (Task-Aware Data Selection), a novel framework for multi-task multimodal pre-training that integrates Intrinsic Quality, Task Relevance, and Distributional Diversity into a learnable value function. TADS employs a comprehensive quality assessment system with unimodal and cross-modal operators, quantifies task relevance via interpretable similarity vectors, and optimizes diversity through cluster-based weighting. A feedback-driven meta-learning mechanism adaptively refines the selection strategy based on proxy model performance across multiple downstream tasks. Experiments on CC12M demonstrate that TADS achieves superior zero-shot performance on benchmarks like ImageNet, CIFAR-100, MS-COCO, and Flickr30K, using only 36% of the data while outperforming baselines by an average of 1.0%. This highlights that TADS significantly enhances data efficiency by curating a high-utility subset that yields a much higher performance ceiling within the same computational constraints.

---

### Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images

Authors: Jieyun Tan, Shuo Liu, Guibin Zhang, Ziqi Li, Jian Geng, Lei Zhang, Lei Cao
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05250v1

Automated detection of electron dense deposits (EDD) in glomerular disease is hindered by the scarcity of high-quality labeled data. While crowdsourcing reduces annotation cost, it introduces label noise. We propose an active label cleaning method to efficiently denoise crowdsourced datasets. Our approach uses active learning to select the most valuable noisy samples for expert re-annotation, building high-accuracy cleaning models. A Label Selection Module leverages discrepancies between crowdsourced labels and model predictions for both sample selection and instance-level noise grading. Experiments show our method achieves 67.18% AP\textsubscript{50} on a private dataset, an 18.83% improvement over training on noisy labels. This performance reaches 95.79% of that with full expert annotation while reducing annotation cost by 73.30%. The method provides a practical, cost-effective solution for developing reliable medical AI with limited expert resources.

---

### Automatic Cognitive Task Generation for In-Situ Evaluation of Embodied Agents

Authors: Xinyi He, Ying Yang, Chuanjian Fu, Sihan Guo, Songchun Zhu, Lifeng Fan, Zhenliang Zhang, Yujia Peng
Published: 2026-02-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.05249v1

As general intelligent agents are poised for widespread deployment in diverse households, evaluation tailored to each unique unseen 3D environment has become a critical prerequisite. However, existing benchmarks suffer from severe data contamination and a lack of scene specificity, inadequate for assessing agent capabilities in unseen settings. To address this, we propose a dynamic in-situ task generation method for unseen environments inspired by human cognition. We define tasks through a structured graph representation and construct a two-stage interaction-evolution task generation system for embodied agents (TEA). In the interaction stage, the agent actively interacts with the environment, creating a loop between task execution and generation that allows for continuous task generation. In the evolution stage, task graph modeling allows us to recombine and reuse existing tasks to generate new ones without external data. Experiments across 10 unseen scenes demonstrate that TEA automatically generated 87,876 tasks in two cycles, which human verification confirmed to be physically reasonable and encompassing essential daily cognitive capabilities. Benchmarking SOTA models against humans on our in-situ tasks reveals that models, despite excelling on public benchmarks, perform surprisingly poorly on basic perception tasks, severely lack 3D interaction awareness and show high sensitivity to task types in reasoning. These sobering findings highlight the necessity of in-situ evaluation before deploying agents into real-world human environments.

---

### CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers

Authors: Boxiang Zhang, Baijian Yang
Published: 2026-02-05
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.05243v2

Transformers achieve strong accuracy but incur high compute and memory cost. Structured pruning reduces inference cost, but most methods rely on retraining or multi-stage optimization, which limits post-training deployment. We propose CORP, a closed-form one-shot structured pruning method that removes MLP dimensions and attention substructures using only unlabeled calibration data without gradients or fine-tuning. CORP formulates structured pruning as a representation recovery problem. It models removed components as affine functions of retained components and derives closed-form ridge regression solutions that fold compensation into model weights. This minimizes a layer-local affine/logit reconstruction objective under the calibration distribution. Experiments on ImageNet with DeiT reveal strong redundancy in both MLP and attention representations. With CORP, models retain high accuracy under aggressive sparsity. On DeiT-Huge, CORP achieves 83.27% Top-1 accuracy after pruning 50\% of both MLP and attention structures.

---

### EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering

Authors: Chenhui Mao, Yuanting Lei, Zhixiang Wei, Ming Liang, Zhixiang Wang, Jingxuan Xu, Dajun Chen, Wei Jiang, Yong Li
Published: 2026-02-05
Categories: cs.SE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.05242v1

Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bug fixing. However, its practical adoption remains limited due to significant computational overhead, primarily driven by two key challenges: (1) the high cost associated with deploying excessively large ensembles, and (2) the lack of a reliable mechanism for selecting the optimal candidate solution, ultimately constraining the performance gains that can be realized. To address these challenges, we propose Entropy-Guided Stepwise Scaling (EGSS), a novel TTS framework that dynamically balances efficiency and effectiveness through entropy-guided adaptive search and robust test-suite augmentation. Extensive experiments on SWE-Bench-Verified demonstrate that EGSS consistently boosts performance by 5-10% across all evaluated models. Specifically, it increases the resolved ratio of Kimi-K2-Intruct from 63.2% to 72.2%, and GLM-4.6 from 65.8% to 74.6%. Furthermore, when paired with GLM-4.6, EGSS achieves a new state-of-the-art among open-source large language models. In addition to these accuracy improvements, EGSS reduces inference-time token usage by over 28% compared to existing TTS methods, achieving simultaneous gains in both effectiveness and computational efficiency.

---

### Explainable AI: A Combined XAI Framework for Explaining Brain Tumour Detection Models

Authors: Patrick McGonagle, William Farrelly, Kevin Curran
Published: 2026-02-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.05240v1

This study explores the integration of multiple Explainable AI (XAI) techniques to enhance the interpretability of deep learning models for brain tumour detection. A custom Convolutional Neural Network (CNN) was developed and trained on the BraTS 2021 dataset, achieving 91.24% accuracy in distinguishing between tumour and non-tumour regions. This research combines Gradient-weighted Class Activation Mapping (GRAD-CAM), Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanations (SHAP) to provide comprehensive insights into the model's decision-making process. This multi-technique approach successfully identified both full and partial tumours, offering layered explanations ranging from broad regions of interest to pixel-level details. GRAD-CAM highlighted important spatial regions, LRP provided detailed pixel-level relevance and SHAP quantified feature contributions. The integrated approach effectively explained model predictions, including cases with partial tumour visibility thus showing superior explanatory power compared to individual XAI methods. This research enhances transparency and trust in AI-driven medical imaging analysis by offering a more comprehensive perspective on the model's reasoning. The study demonstrates the potential of integrated XAI techniques in improving the reliability and interpretability of AI systems in healthcare, particularly for critical tasks like brain tumour detection.

---

### PatchFlow: Leveraging a Flow-Based Model with Patch Features

Authors: Boxiang Zhang, Baijian Yang, Xiaoming Wang, Corey Vian
Published: 2026-02-05
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.05238v1

Die casting plays a crucial role across various industries due to its ability to craft intricate shapes with high precision and smooth surfaces. However, surface defects remain a major issue that impedes die casting quality control. Recently, computer vision techniques have been explored to automate and improve defect detection. In this work, we combine local neighbor-aware patch features with a normalizing flow model and bridge the gap between the generic pretrained feature extractor and industrial product images by introducing an adapter module to increase the efficiency and accuracy of automated anomaly detection. Compared to state-of-the-art methods, our approach reduces the error rate by 20\% on the MVTec AD dataset, achieving an image-level AUROC of 99.28\%. Our approach has also enhanced performance on the VisA dataset , achieving an image-level AUROC of 96.48\%. Compared to the state-of-the-art models, this represents a 28.2\% reduction in error. Additionally, experiments on a proprietary die casting dataset yield an accuracy of 95.77\% for anomaly detection, without requiring any anomalous samples for training. Our method illustrates the potential of leveraging computer vision and deep learning techniques to advance inspection capabilities for the die casting industry

---

### FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapters

Authors: Zhilin Liang, Yuxiang Wang, Zimu Zhou, Hainan Zhang, Boyi Liu, Yongxin Tong
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.05235v2

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge to improve factuality and reduce hallucinations. Yet most deployments assume a centralized corpus, which is infeasible in privacy aware domains where knowledge remains siloed. This motivates federated RAG (FedRAG), where a central LLM server collaborates with distributed silos without sharing raw documents. In context RAG violates this requirement by transmitting verbatim documents, whereas parametric RAG encodes documents into lightweight adapters that merge with a frozen LLM at inference, avoiding raw-text exchange. We adopt the parametric approach but face two unique challenges induced by FedRAG: high storage and communication from per-document adapters, and destructive aggregation caused by indiscriminately merging multiple adapters. We present FedMosaic, the first federated RAG framework built on parametric adapters. FedMosaic clusters semantically related documents into multi-document adapters with document-specific masks to reduce overhead while preserving specificity, and performs selective adapter aggregation to combine only relevance-aligned, nonconflicting adapters. Experiments show that FedMosaic achieves an average 10.9% higher accuracy than state-of-the-art methods in four categories, while lowering storage costs by 78.8% to 86.3% and communication costs by 91.4%, and never sharing raw documents.

---

### Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions

Authors: Yuntai Bao, Xuhong Zhang, Jintao Chen, Ge Su, Yuxiang Cai, Hao Peng, Bing Sun, Haiqin Weng, Liu Yan, Jianwei Yin
Published: 2026-02-05
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.05234v2

Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from fine-tuning, current methods are susceptible to overfitting and often underperform, sometimes generating unnatural outputs. We hypothesize that this is because effective steering requires the faithful identification of internal model mechanisms, not the enforcement of external preferences. To this end, we build on the principles of distributed alignment search (DAS), the standard for causal variable localization, to propose a new steering method: Concept DAS (CDAS). While we adopt the core mechanism of DAS, distributed interchange intervention (DII), we introduce a novel distribution matching objective tailored for the steering task by aligning intervened output distributions with counterfactual distributions. CDAS differs from prior work in two main ways: first, it learns interventions via weak-supervised distribution matching rather than probability maximization; second, it uses DIIs that naturally enable bi-directional steering and allow steering factors to be derived from data, reducing the effort required for hyperparameter tuning and resulting in more faithful and stable control. On AxBench, a large-scale model steering benchmark, we show that CDAS does not always outperform preference-optimization methods but may benefit more from increased model scale. In two safety-related case studies, overriding refusal behaviors of safety-aligned models and neutralizing a chain-of-thought backdoor, CDAS achieves systematic steering while maintaining general model utility. These results indicate that CDAS is complementary to preference-optimization approaches and conditionally constitutes a robust approach to intervention-based model steering. Our code is available at https://github.com/colored-dye/concept_das.

---

### Balanced Anomaly-guided Ego-graph Diffusion Model for Inductive Graph Anomaly Detection

Authors: Chunyu Wei, Siyuan He, Yu Wang, Yueguo Chen, Yunhai Wang, Bing Bai, Yidong Zhang, Yong Xie, Shunming Zhang, Fei Wang
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.05232v1

Graph anomaly detection (GAD) is crucial in applications like fraud detection and cybersecurity. Despite recent advancements using graph neural networks (GNNs), two major challenges persist. At the model level, most methods adopt a transductive learning paradigm, which assumes static graph structures, making them unsuitable for dynamic, evolving networks. At the data level, the extreme class imbalance, where anomalous nodes are rare, leads to biased models that fail to generalize to unseen anomalies. These challenges are interdependent: static transductive frameworks limit effective data augmentation, while imbalance exacerbates model distortion in inductive learning settings. To address these challenges, we propose a novel data-centric framework that integrates dynamic graph modeling with balanced anomaly synthesis. Our framework features: (1) a discrete ego-graph diffusion model, which captures the local topology of anomalies to generate ego-graphs aligned with anomalous structural distribution, and (2) a curriculum anomaly augmentation mechanism, which dynamically adjusts synthetic data generation during training, focusing on underrepresented anomaly patterns to improve detection and generalization. Experiments on five datasets demonstrate that the effectiveness of our framework.

---

### ZeroS: Zero-Sum Linear Attention for Efficient Transformers

Authors: Jiecheng Lu, Xu Han, Yan Sun, Viresh Pati, Yubin Kim, Siddhartha Somani, Shihao Yang
Published: 2026-02-05
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2602.05230v1

Linear attention methods offer Transformers $O(N)$ complexity but typically underperform standard softmax attention. We identify two fundamental limitations affecting these approaches: the restriction to convex combinations that only permits additive information blending, and uniform accumulated weight bias that dilutes attention in long contexts. We propose Zero-Sum Linear Attention (ZeroS), which addresses these limitations by removing the constant zero-order term $1/t$ and reweighting the remaining zero-sum softmax residuals. This modification creates mathematically stable weights, enabling both positive and negative values and allowing a single attention layer to perform contrastive operations. While maintaining $O(N)$ complexity, ZeroS theoretically expands the set of representable functions compared to convex combinations. Empirically, it matches or exceeds standard softmax attention across various sequence modeling benchmarks.

---

### Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink

Authors: Guozhi Liu, Weiwei Lin, Tiansheng Huang, Ruichao Mo, Qi Mu, Xiumin Wang, Li Shen
Published: 2026-02-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.05228v2

Harmful fine-tuning can invalidate safety alignment of large language models, exposing significant safety risks. In this paper, we utilize the attention sink mechanism to mitigate harmful fine-tuning. Specifically, we first measure a statistic named \emph{sink divergence} for each attention head and observe that \emph{different attention heads exhibit two different signs of sink divergence}. To understand its safety implications, we conduct experiments and find that the number of attention heads of positive sink divergence increases along with the increase of the model's harmfulness when undergoing harmful fine-tuning. Based on this finding, we propose a separable sink divergence hypothesis -- \emph{attention heads associating with learning harmful patterns during fine-tuning are separable by their sign of sink divergence}. Based on the hypothesis, we propose a fine-tuning-stage defense, dubbed Surgery. Surgery utilizes a regularizer for sink divergence suppression, which steers attention heads toward the negative sink divergence group, thereby reducing the model's tendency to learn and amplify harmful patterns. Extensive experiments demonstrate that Surgery improves defense performance by 5.90\%, 11.25\%, and 9.55\% on the BeaverTails, HarmBench, and SorryBench benchmarks, respectively. Source code is available on https://github.com/Lslland/Surgery.

---

### Radon--Wasserstein Gradient Flows for Interacting-Particle Sampling in High Dimensions

Authors: Elias Hess-Childs, Dejan Slepčev, Lantian Xu
Published: 2026-02-05
Categories: stat.ML, cs.LG, math.AP, math.NA, stat.ME
arXiv: https://arxiv.org/abs/2602.05227v2

Gradient flows of the Kullback--Leibler (KL) divergence, such as the Fokker--Planck equation and Stein Variational Gradient Descent, evolve a distribution toward a target density known only up to a normalizing constant. We introduce new gradient flows of the KL divergence with a remarkable combination of properties: they admit accurate interacting-particle approximations in high dimensions, and the per-step cost scales linearly in both the number of particles and the dimension. These gradient flows are based on new transportation-based Riemannian geometries on the space of probability measures: the Radon--Wasserstein geometry and the related Regularized Radon--Wasserstein (RRW) geometry. We define these geometries using the Radon transform so that the gradient-flow velocities depend only on one-dimensional projections. This yields interacting-particle-based algorithms whose per-step cost follows from efficient Fast Fourier Transform-based evaluation of the required 1D convolutions. We additionally provide numerical experiments that study the performance of the proposed algorithms and compare convergence behavior and quantization. Finally, we prove some theoretical results including well-posedness of the flows and long-time convergence guarantees for the RRW flow.

---

### Metric space valued Fréchet regression

Authors: László Györfi, Pierre Humbert, Batiste Le Bars
Published: 2026-02-05
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.05225v1

We consider the problem of estimating the Fréchet and conditional Fréchet mean from data taking values in separable metric spaces. Unlike Euclidean spaces, where well-established methods are available, there is no practical estimator that works universally for all metric spaces. Therefore, we introduce a computable estimator for the Fréchet mean based on random quantization techniques and establish its universal consistency across any separable metric spaces. Additionally, we propose another estimator for the conditional Fréchet mean, leveraging data-driven partitioning and quantization, and demonstrate its universal consistency when the output space is any Banach space.

---

### Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions

Authors: Jinchuan Tian, Haoran Wang, Bo-Hao Su, Chien-yu Huang, Qingzheng Wang, Jiatong Shi, William Chen, Xun Gong, Siddhant Arora, Chin-Jou Li, Masao Someki, Takashi Maekaku et al.
Published: 2026-02-05
Categories: cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2602.05220v4

Current audio foundation models typically rely on rigid, task-specific supervision (e.g., speech recognition), addressing isolated factors of audio rather than the whole. In contrast, human processes audio holistically, seamlessly bridging raw audio waveform with abstract cognitive concepts (e.g., all perception details of audio events) to execute complex tasks. Grounded in this philosophy, we introduce Bagpiper, an 8B audio foundation model that interprets physical audio via rich captions, i.e., comprehensive natural language descriptions that encapsulate the critical cognitive concepts inherent in the audio. By pre-training on a massive corpus of 600B tokens, the model establishes a robust bidirectional mapping between raw audio and this high-level conceptual space. During fine-tuning, Bagpiper adopts a caption-then-process workflow, simulating an intermediate cognitive reasoning step to solve diverse tasks without knowing prior task-specific practice. Experimentally, Bagpiper achieves universal generation that can uniformly generate speech, sound effects, music, and their arbitrary combinations. It also maintains comparable performance with the 7B Qwen-2.5-Omni for audio understanding. To the best of our knowledge, Bagpiper is among the first works that achieve open-ended audio understanding and generation on speech, sound, and music. Model, data, and code will be released at Bagpiper Home Page.

---

### Private Prediction via Shrinkage

Authors: Chao Yan
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.05219v1

We study differentially private prediction introduced by Dwork and Feldman (COLT 2018): an algorithm receives one labeled sample set $S$ and then answers a stream of unlabeled queries while the output transcript remains $(\varepsilon,δ)$-differentially private with respect to $S$. Standard composition yields a $\sqrt{T}$ dependence for $T$ queries. We show that this dependence can be reduced to polylogarithmic in $T$ in streaming settings. For an oblivious online adversary and any concept class $\mathcal{C}$, we give a private predictor that answers $T$ queries with $|S|= \tilde{O}(VC(\mathcal{C})^{3.5}\log^{3.5}T)$ labeled examples. For an adaptive online adversary and halfspaces over $\mathbb{R}^d$, we obtain $|S|=\tilde{O}\left(d^{5.5}\log T\right)$.

---

### Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsification

Authors: Jiahao Nie, Yun Xing, Wenbin An, Qingsong Zhao, Jiawei Shao, Yap-Peng Tan, Alex C. Kot, Shijian Lu, Xuelong Li
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05218v1

Motivated by the success of the Segment Anything Model (SAM) in promptable segmentation, recent studies leverage SAM to develop training-free solutions for few-shot segmentation, which aims to predict object masks in the target image based on a few reference exemplars. These SAM-based methods typically rely on point matching between reference and target images and use the matched dense points as prompts for mask prediction. However, we observe that dense points perform poorly in Cross-Domain Few-Shot Segmentation (CD-FSS), where target images are from medical or satellite domains. We attribute this issue to large domain shifts that disrupt the point-image interactions learned by SAM, and find that point density plays a crucial role under such conditions. To address this challenge, we propose Conditional Point Sparsification (CPS), a training-free approach that adaptively guides SAM interactions for cross-domain images based on reference exemplars. Leveraging ground-truth masks, the reference images provide reliable guidance for adaptively sparsifying dense matched points, enabling more accurate segmentation results. Extensive experiments demonstrate that CPS outperforms existing training-free SAM-based methods across diverse CD-FSS datasets.

---

### Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation

Authors: Jiahao Nie, Guanqiao Fu, Wenbin An, Yap-Peng Tan, Alex C. Kot, Shijian Lu
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05217v2

Cross-Domain Few-Shot Segmentation aims to segment categories in data-scarce domains conditioned on a few exemplars. Typical methods first establish few-shot capability in a large-scale source domain and then adapt it to target domains. However, due to the limited quantity and diversity of target samples, existing methods still exhibit constrained performance. Moreover, the source-trained model's initially weak few-shot capability in target domains, coupled with substantial domain gaps, severely hinders the effective utilization of target samples and further impedes adaptation. To this end, we propose Multi-view Progressive Adaptation, which progressively adapts few-shot capability to target domains from both data and strategy perspectives. (i) From the data perspective, we introduce Hybrid Progressive Augmentation, which progressively generates more diverse and complex views through cumulative strong augmentations, thereby creating increasingly challenging learning scenarios. (ii) From the strategy perspective, we design Dual-chain Multi-view Prediction, which fully leverages these progressively complex views through sequential and parallel learning paths under extensive supervision. By jointly enforcing prediction consistency across diverse and complex views, MPA achieves both robust and accurate adaptation to target domains. Extensive experiments demonstrate that MPA effectively adapts few-shot capability to target domains, outperforming state-of-the-art methods by a large margin (+7.0%).

---

### Semantic Search over 9 Million Mathematical Theorems

Authors: Luke Alexander, Eric Leonen, Sophie Szeto, Artemii Remizov, Ignacio Tejeda, Jarod Alper, Giovanni Inchiostro, Vasily Ilin
Published: 2026-02-05
Categories: cs.IR, cs.AI, math.HO
arXiv: https://arxiv.org/abs/2602.05216v2

Searching for mathematical results remains difficult: most existing tools retrieve entire papers, while mathematicians and theorem-proving agents often seek a specific theorem, lemma, or proposition that answers a query. While semantic search has seen rapid progress, its behavior on large, highly technical corpora such as research-level mathematical theorems remains poorly understood. In this work, we introduce and study semantic theorem retrieval at scale over a unified corpus of $9.2$ million theorem statements extracted from arXiv and seven other sources, representing the largest publicly available corpus of human-authored, research-level theorems. We represent each theorem with a short natural-language description as a retrieval representation and systematically analyze how representation context, language model choice, embedding model, and prompting strategy affect retrieval quality. On a curated evaluation set of theorem-search queries written by professional mathematicians, our approach substantially improves both theorem-level and paper-level retrieval compared to existing baselines, demonstrating that semantic theorem search is feasible and effective at web scale. The project page, search tool, dataset, REST API, and MCP server are available at theoremsearch.com.

---

### E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching

Authors: Jiahao Nie, Wenbin An, Gongjie Zhang, Yicheng Xu, Yap-Peng Tan, Alex C. Kot, Shijian Lu
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05215v1

Despite recent advances in Video Large Language Models (Vid-LLMs), Temporal Video Grounding (TVG), which aims to precisely localize time segments corresponding to query events, remains a significant challenge. Existing methods often match start and end frames by comparing frame features with two separate tokens, relying heavily on exact timestamps. However, this approach fails to capture the event's semantic continuity and integrity, leading to ambiguities. To address this, we propose E.M.Ground, a novel Vid-LLM for TVG that focuses on holistic and coherent event perception. E.M.Ground introduces three key innovations: (i) a special <event> token that aggregates information from all frames of a query event, preserving semantic continuity for accurate event matching; (ii) Savitzky-Golay smoothing to reduce noise in token-to-frame similarities across timestamps, improving prediction accuracy; (iii) multi-grained frame feature aggregation to enhance matching reliability and temporal understanding, compensating for compression-induced information loss. Extensive experiments on benchmark datasets show that E.M.Ground consistently outperforms state-of-the-art Vid-LLMs by significant margins.

---

### Disentangled Representation Learning via Flow Matching

Authors: Jinjin Chi, Taoping Liu, Mengtao Yin, Ximing Li, Yongcheng Jing, Jialie Shen, Leszek Rutkowski, Dacheng Tao
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.05214v2

Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating process. Recent advances in generative modeling have introduced new paradigms for learning such representations. However, existing diffusion-based methods encourage factor independence via inductive biases, yet frequently lack strong semantic alignment. In this work, we propose a flow matching-based framework for disentangled representation learning, which casts disentanglement as learning factor-conditioned flows in a compact latent space. To enforce explicit semantic alignment, we introduce a non-overlap (orthogonality) regularizer that suppresses cross-factor interference and reduces information leakage between factors. Extensive experiments across multiple datasets demonstrate consistent improvements over representative baselines, yielding higher disentanglement scores as well as improved controllability and sample fidelity.

---

### Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures

Authors: Chuqin Zhou, Xiaoyue Ling, Yunuo Chen, Jincheng Dai, Guo Lu, Wenjun Zhang
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05213v1

While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods leveraging semantic priors from pretrained models have emerged as a promising paradigm. However, existing approaches are fundamentally constrained by a tradeoff between semantic faithfulness and perceptual realism. Methods based on explicit representations preserve content structure but often lack fine-grained textures, whereas implicit methods can synthesize visually plausible details at the cost of semantic drift. In this work, we propose a unified framework that bridges this gap by coherently integrating explicit and implicit representations in a training-free manner. Specifically, We condition a diffusion model on explicit high-level semantics while employing reverse-channel coding to implicitly convey fine-grained details. Moreover, we introduce a plug-in encoder that enables flexible control of the distortion-perception tradeoff by modulating the implicit information. Extensive experiments demonstrate that the proposed framework achieves state-of-the-art rate-perception performance, outperforming existing methods and surpassing DiffC by 29.92%, 19.33%, and 20.89% in DISTS BD-Rate on the Kodak, DIV2K, and CLIC2020 datasets, respectively.

---

### Quantifying the Knowledge Proximity Between Academic and Industry Research: An Entity and Semantic Perspective

Authors: Hongye Zhao, Yi Zhao, Chengzhi Zhang
Published: 2026-02-05
Categories: cs.CL, cs.DL
arXiv: https://arxiv.org/abs/2602.05211v1

The academia and industry are characterized by a reciprocal shaping and dynamic feedback mechanism. Despite distinct institutional logics, they have adapted closely in collaborative publishing and talent mobility, demonstrating tension between institutional divergence and intensive collaboration. Existing studies on their knowledge proximity mainly rely on macro indicators such as the number of collaborative papers or patents, lacking an analysis of knowledge units in the literature. This has led to an insufficient grasp of fine-grained knowledge proximity between industry and academia, potentially undermining collaboration frameworks and resource allocation efficiency. To remedy the limitation, this study quantifies the trajectory of academia-industry co-evolution through fine-grained entities and semantic space. In the entity measurement part, we extract fine-grained knowledge entities via pre-trained models, measure sequence overlaps using cosine similarity, and analyze topological features through complex network analysis. At the semantic level, we employ unsupervised contrastive learning to quantify convergence in semantic spaces by measuring cross-institutional textual similarities. Finally, we use citation distribution patterns to examine correlations between bidirectional knowledge flows and similarity. Analysis reveals that knowledge proximity between academia and industry rises, particularly following technological change. This provides textual evidence of bidirectional adaptation in co-evolution. Additionally, academia's knowledge dominance weakens during technological paradigm shifts. The dataset and code for this paper can be accessed at https://github.com/tinierZhao/Academic-Industrial-associations.

---

### Context-Aware Asymmetric Ensembling for Interpretable Retinopathy of Prematurity Screening via Active Query and Vascular Attention

Authors: Md. Mehedi Hassan, Taufiq Hasan
Published: 2026-02-05
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.05208v2

Retinopathy of Prematurity (ROP) is among the major causes of preventable childhood blindness. Automated screening remains challenging, primarily due to limited data availability and the complex condition involving both structural staging and microvascular abnormalities. Current deep learning models depend heavily on large private datasets and passive multimodal fusion, which commonly fail to generalize on small, imbalanced public cohorts. We thus propose the Context-Aware Asymmetric Ensemble Model (CAA Ensemble) that simulates clinical reasoning through two specialized streams. First, the Multi-Scale Active Query Network (MS-AQNet) serves as a structure specialist, utilizing clinical contexts as dynamic query vectors to spatially control visual feature extraction for localization of the fibrovascular ridge. Secondly, VascuMIL encodes Vascular Topology Maps (VMAP) within a gated Multiple Instance Learning (MIL) network to precisely identify vascular tortuosity. A synergistic meta-learner ensembles these orthogonal signals to resolve diagnostic discordance across multiple objectives. Tested on a highly imbalanced cohort of 188 infants (6,004 images), the framework attained State-of-the-Art performance on two distinct clinical tasks: achieving a Macro F1-Score of 0.93 for Broad ROP staging and an AUC of 0.996 for Plus Disease detection. Crucially, the system features `Glass Box' transparency through counterfactual attention heatmaps and vascular threat maps, proving that clinical metadata dictates the model's visual search. Additionally, this study demonstrates that architectural inductive bias can serve as an effective bridge for the medical AI data gap.

---

### ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated Inference

Authors: Chunyat Wu, Jiajun Deng, Zhengxi Liu, Zheqi Dai, Haolin He, Qiuqiang Kong
Published: 2026-02-05
Categories: eess.AS, cs.AI
arXiv: https://arxiv.org/abs/2602.05207v1

Although diffusion-based, non-autoregressive text-to-speech (TTS) systems have demonstrated impressive zero-shot synthesis capabilities, their efficacy is still hindered by two key challenges: the difficulty of text-speech alignment modeling and the high computational overhead of the iterative denoising process. To address these limitations, we propose ARCHI-TTS that features a dedicated semantic aligner to ensure robust temporal and semantic consistency between text and audio. To overcome high computational inference costs, ARCHI-TTS employs an efficient inference strategy that reuses encoder features across denoising steps, drastically accelerating synthesis without performance degradation. An auxiliary CTC loss applied to the condition encoder further enhances the semantic understanding. Experimental results demonstrate that ARCHI-TTS achieves a WER of 1.98% on LibriSpeech-PC test-clean, and 1.47%/1.42% on SeedTTS test-en/test-zh with a high inference efficiency, consistently outperforming recent state-of-the-art TTS systems.

---