跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1087新增论文
+804其中 AI 相关
+107已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-14 11:06 · 全站最近入库：2026-11-13 20:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-13 13:22 — 2026-11-14 13:22（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-14 11:06最近发现新增版本：2026-11-13 20:44库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,727 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 33 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 11:04（北京时间）
版本更新 · v2arXiv:2607.26515

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

Hei Yi Mak, Shadan Golestan, Hoang Le, Mehran Taghian Jazi, Yunke Peng, Yaoyuan Wang, Yao Wang, Junsong Wang 等 13 位作者

原文摘要

We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision. A systematic study reveals that the dominant source of degradation in FP4 RL is not training-side quantization error but rollout activation quantization: outliers stretch the dynamic range so far that a large number of activation values underflow to zero under FP4. Counterintuitively, restoring the training policy to higher precision while keeping the rollout in FP4 makes accuracy worse than full FP4 baseline, exposing rollout--training mismatch as the principal failure mode and ruling out standard pretraining-style fixes. We address this with Rollout Residual Quantization (Rollout-ResQ): a single residual correction term constrained to a hardware-friendly sparsity pattern, added only to the FP4 rollout matmul -- a lightweight correction that recovers most of the precision lost to outlier-driven underflow without inflating the rollout's compute footprint. On Qwen2.5-3B, Rollout-ResQ paired with the HiFloat4 (HiF4) format -- whose three-level hierarchical scaling preserves resolution under FP4's tight 4-bit budget -- closes the accuracy gap to BF16 from 3.59% to 1.39%, bringing fully quantized FP4 RL within close reach of full precision. Applied to the open-standard MXFP4, the same recipe narrows the gap from 13.6% to 5.3%, revealing that FP4 format choice is a key factor that determines the ceiling on recoverable accuracy. The experimental results on Qwen2.5-Math-7B further confirm the recovery benefits of Rollout-ResQ with HiF4. Together, these results establish HiF4 as the enabling format for end-to-end FP4 RL post-training, and Rollout-ResQ as the activation-side mechanism that makes the gap to BF16 closable.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12478

AuDiR: Diagnosing Audio Reasoning with Rule and Percept Interventions

Chengwei Wei, Yi Ma, Nancy F. Chen

原文摘要

Answer accuracy alone does not distinguish failures in acoustic perception, rule knowledge, and rule application. AuDiR (Audio Diagnostic Reasoning) examines these distinctions through controlled input interventions. Each item contains an audio clip, a multiple-choice question, a task-general rule, and a textual description of the acoustic observations needed to answer. Three conditions progressively supply the rule and observations; a fourth removes the audio while retaining the question and rule. The first correct diagnostic condition assigns an operational response label, without identifying a unique internal cause. The current benchmark contains 201 items in 18 families drawn from 9 sources, with answer references documented separately from percept extraction. In a preliminary evaluation of Gemini-3.8-flash, accuracy is 29.3% without supplied information, 31.3% with the rule, and 98.5% with the observations also supplied. No-audio accuracy is 23.9%, with a confidence interval containing the 25.0% chance rate. A family-level knowledge probe associates incomplete rule recall with larger gains from rule provision. These results show the benefit of supplying acoustic observations as text, while incomplete validation, possible recognition shortcuts, and non-monotonic responses limit stronger failure-attribution claims.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.18654

Kwai Summary Attention V2 Technical Report

OneRec Team, Chenglong Chu, Guohong Mu, Guowang Zhang, Hao Peng, Hui Wang, Jian Liang, Jiangxia Cao 等 33 位作者

原文摘要

Summary-token architectures such as Kwai Summary Attention (KSA) compress distant context into learnable Summary token per chunk, and hybrid variants interleave these layers with full attention to retain exact access to the original text. In such hybrid KSA-Full architecture, the interleaving inserted summary tokens are served as a streaming flow role across different layers. Although effective, however, it also introduce some bottlenecks: (1) the different layers summary compression chunk must be same, therefore hard to reach a flexible KV Cache compression, e.g., different layer set different summary compression chunk window. (2) in the full-attention layers, the summary token introduced additional computation cost, but such layer ignore them and still pay quadratic prefilling, therefore unfriendly to the computation side. Motivated by them, we developed the KSA V2, which not only achieves a more flexible KV cache memory compression but also reduces the computation cost in Full attention layer. Specifically, we found that the summary tokens can serve two roles: the KV memory and sparse indexer.

cs.LG · cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.05625

SHERLOC: Statistical Hypothesis Evaluation and Recovery for Learning Opponent Characteristics

Soyon Choi, Scott Alfeld, Meiyi Ma

原文摘要

When used in automated decision-making systems, machine learning (ML) models are vulnerable to data-manipulation attacks. Some defense mechanisms (e.g., adversarial regularization) directly affect the ML models while others (e.g., anomaly detection) act within the broader system. However, many defenses operate under a predefined threat model that assumes characteristics of the adversary, including their knowledge, capabilities, and objectives, are known and fixed. In practice, these characteristics may be unknown or evolve over time, creating a mismatch between the assumptions of the defender and the true attacker. In this paper, we study a new perspective on adversarial defense: focusing on the attacker, rather than the attack. We present and demonstrate SHERLOC, a framework for adversarial learning forensics -- namely, a detective that learns about the attacker from observed attack(s). We prove that, without additional knowledge, the attacker is non-identifiable --- multiple potential attackers would perform the same observed attack. This reveals an important distinction between reconstructing an attacker's behavior and recovering the attacker that generated it. We demonstrate empirically that SHERLOC is able to reconstruct a hypothesis attacker that is consistent with the observed attacks against various defender models (i.e., generalized least-squares linear regressors, logistic regressors, and polynomial classifiers) across various security-critical domains. Finally, we show that these inferred attackers need not match the ground truth attacker exactly to have downstream utility. Defenses using the SHERLOC-inferred attackers achieve approximately 90-100% of robustness improvement that would be achieved if the defender had access to the ground-truth attacker.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11529

Data Manipulation Attacks Against Machine Learning Integrated Cyber-Physical Systems

Soyon Choi, Scott Alfeld, Meiyi Ma

原文摘要

There is a well-established body of work demonstrating that individual machine learning (ML) algorithms can be manipulated or deceived. However, in many real-world systems, multiple ML algorithms are composed to enable automated decision-making, particularly in Cyber-Physical Systems (CPS). Often such systems use a composition of vision, planning, and other ML models to affect their internal state and ultimate take actions in the physical world. While there is a huge literature on the (in)security of ML algorithms, it is not immediately clear how an attacker might leverage their ability to trick individual learners when attacking the composition as a whole. We develop methods for creating an attack policy (a mapping from state to attack) for a data-manipulating attacker affecting a CPS or other state-machine-based AI compositions. We describe our framework, a basic threat model and corresponding methods for computing an optimal attack policy, as well as planned extensions. The goal of this work-in-progress paper is to stimulate conversation and forge new collaborations regarding the security of compositional learning.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.22142

RoboLineage: Agent-Native Data Lifecycle Governance Across Robot Policy Iterations

Qian Luo, Wentao Guo, Zhennan Qin, Nanchun Guo, Yunhan Zhao, Yi Ma, Yanchao Yang

原文摘要

We present RoboLineage, an agent-native data lifecycle governance system for robot policy iteration. Modern robot policies improve through repeated data collection, review, retraining, evaluation, and release decisions, but the evidence connecting these steps is often scattered across local tools, scripts, and expert memory. RoboLineage makes this lifecycle explicit by representing rollouts, reviews, dataset decisions, training runs, policy metadata, evaluations, deployment recommendations, and next-collection plans as typed lineage artifacts. Agents interpret embodied rollout evidence, adapt accepted data to existing training stacks, maintain data health, and summarize cross-iteration state under explicit artifact boundaries. In real-robot manipulation workflows, RoboLineage makes routine policy iteration faster and more auditable while maintaining downstream policy performance. We open source RoboLineage as a lightweight lifecycle layer for different robot embodiments and training families. Project page: https://robolineage.github.io/

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10509

Scaling Optimization-Oriented Hypernetworks for Implicit Neural Representations

Lulu Cai, Hanxiang Ren, Siyan Dong, Li Sun, Jiefeng Wu, Youyi Zheng, Yi Ma, Yanchao Yang

原文摘要

We present a hypernetwork that generates the parameters of an implicit neural representation (INR) for a given signal in a single forward pass, without test-time optimization. Existing hypernetworks for this problem either ignore the chain-rule structure of the test-time optimization that produces an INR or, when they preserve it, instantiate the structure with MLPs whose parameter count grows quartically in target-network width. Our central contribution is to show that this parameter-count cost is structural to the MLP instantiation, not to the optimization-oriented principle of preserving chain-rule structure, and to resolve it by replacing the MLP body with attention. The resulting hypernetwork combines three design choices: an output-neuron-centric tokenization that aligns the token axis with each layer's output-neuron axis; an information-flow consistency rule that fixes the role of every cross-attention module from the representation its output should occupy; and a token-space iterative rollout that realizes the five quantities one optimization step on the target INR computes as five cross-attention modules with parameter count independent of target-network width. Across five 2D and 3D INR generation benchmarks, our method outperforms the state-of-the-art single-pass and optimization-oriented baselines; scales to target-network widths at which the MLP-based optimization-oriented paradigm exhausts GPU memory; and produces the highest result on NeRF generation without ground-truth INR weights supervision.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2510.23254

Optimal In-context Adaptivity and Distributional Robustness of Transformers

Tianyi Ma, Tengyao Wang, Richard J. Samworth

原文摘要

We study in-context learning problems where a Transformer is pretrained on tasks drawn from a mixture distribution $π=\sum_{α\in\mathcal{A}} λ_α π_α$, called the pretraining prior, in which each mixture component $π_α$ is a distribution on tasks of a specific difficulty level indexed by $α$. Our goal is to understand the performance of the pretrained Transformer when evaluated on a different test distribution $μ$, consisting of tasks of fixed difficulty $β\in\mathcal{A}$, and with potential distribution shift relative to $π_β$, subject to the chi-squared divergence $χ^2(μ,π_β)$ being at most $κ$. In particular, we consider nonparametric regression problems with random smoothness, and multi-index models with both random smoothness and random effective dimension. We prove that a large Transformer pretrained on sufficient data achieves the optimal rate of convergence corresponding to the difficulty level $β$, uniformly over test distributions $μ$ in the chi-squared divergence ball. Thus, the pretrained Transformer is able to achieve faster rates of convergence on easier tasks and is robust to distribution shift at test time. Finally, we prove that even if an estimator had access to the test distribution $μ$, the convergence rate of its expected risk over $μ$ could not be faster than that of our pretrained Transformers, thereby providing a more appropriate optimality guarantee than minimax lower bounds.

stat.ML · cs.LG · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09091

TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework

Luzhan Yuan, Chao Mi, Xiahao Shi, Yi Mao, Shengsheng Niu, Xin Zhu, Jie He, Zhangang Lin 等 9 位作者

原文摘要

Generative modeling, particularly Decision Transformers, shows promise in auto-bidding strategies. However, it struggles with limited exploration in static offline datasets, vulnerability to dynamic environmental shifts, and a reliance on heuristic return-to-go (RTG) specifications that may yield suboptimal performance on unseen traffic. To address these challenges, we propose the Two-stage Uncertainty-aware Generative Auto-Bidding (TUGB) framework. TUGB integrates generative sequence modeling with Reinforcement Learning (RL). It employs a two-stage pipeline where a pre-trained Generative Bidding Model is fine-tuned via an ensemble-based Uncertainty-aware Environment Model. This approach quantifies epistemic uncertainty to penalize high-risk trajectories and evolves the policy from RTG-conditioning to direct bidding optimization. Extensive experiments demonstrate that TUGB significantly outperforms SOTA baselines. Notably, full-scale deployment on JD Search Ad achieved a 2.32\% increase in cost and 3.57\% in target cost, validating its industrial efficacy, while its successful adaptation to subsequent mechanism upgrades and JD Food Delivery Ad further validates TUGB's superior generalization capability.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.01834

Code Owns the Simulation, Jev Owns the Evaluation

Yaodong Yang, Hongyao Tang, Yi Ma, Xingyu Fan, Weixun Wang, Jinpeng Li, Tianpei Yang

原文摘要

Judgment models such as \jev{} return, in a single call and without reasoning text, a probability for each described option. This makes them attractive as an agent's action-selection layer, but it is unclear which decisions they can be trusted with. We test \jev{} on reflection tests, one-shot matrix games, the text game ALFWorld and robot control, and find a sharp boundary. \jev{} succeeds when the right option can be judged from what the input describes, which we call \emph{evaluation}. Specifically, it solves 99\% of the counterintuitive Cognitive Reflection Test questions. However, it fails when the right option depends on \emph{simulation} (i.e., predicting something not in the input), such as the opponent's action or the subgoal that must come first. In games, \jev{} plays suboptimally as if its rational opponent acted at random, because the opponent's action is not given. In ALFWorld, \jev{} favors commands that mention an object or place named in the task description. For example, given the task ``put a clean knife in the drawer'', \jev{} carries an unwashed knife straight to the drawer instead of first washing it at the sink. Surprisingly, many of these failures are not due to a lack of knowledge. Asked separately what the opponent will do, \jev{} usually answers correctly, and it responds well given the opponent's action. It fails when one call must both perform the simulation and evaluate based on it. This suggests letting code make the prediction or simulation. When code supplies it, such as a lookahead in ALFWorld and physics simulation in robot control, \jev{} becomes an expert controller through its general evaluation ability.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07515

LMGN: A Unified Policy Learning Model for Last-Mile Grasp-Navigation

Xuenmin Hu, Qingxue Qian, Wei Luo, Benyi Ma, Bo Tang, Long Chen

原文摘要

Legged robots equipped with manipulators have shown significant potential in the fields of daily life and industry in complex environments. However, existing methods mainly focus on global navigation or manipulation independently, while overlooking the last-mile navigation problem, where the robot must jointly determine the base placement, approach direction, and grasp execution to achieve reliable object grasping, and different manipulation stages require distinct control behaviors. To address these challenges, we propose Last-Mile Grasp-Navigation (LMGN), a unified policy learning model for Quadruped robot loco-manipulation. An Explicit Distance and Directional Reachability (ED-DR) representation is first introduced to explicitly represent the features of grasp-compatible base placement and approach direction. We then develop a semantically aligned Hierarchical Mixture-of-Experts (HMoE) policy that models stage-aware behaviors across the stages of base adjustment, pre-grasp alignment and grasp execution, and object lift. Finally, a new optimization method that jointly aligns navigation and manipulation, stage-dependent expert routing, and action-level consistency is proposed to optimize the HMoE policy. Extensive experiments on the Habitat and Isaac Gym simulators demonstrate that LMGN consistently outperforms state-of-the-art methods, denoting that integrating grasp-aware reachability with stage-aware policy learning significantly improves the success rates of last-mile navigation and target grasp for robots.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04376

Aligning Training and Rollout Policies for End-to-End FP4 RL on Mixture-of-Experts LLMs

Hei Yi Mak, Hoang Le, Mehran Taghian Jazi, Yunke Peng, Huan Lin, Zhengzhi Tang, Zhexu Liu, Yao Wang 等 11 位作者

原文摘要

In this work, we study end-to-end FP4 reinforcement learning (RL) post-training for Mixture-of-Experts (MoE) large language models. Recent work on FP4 RL has introduced effective recovery recipes that restore accuracy under aggressive low-precision quantization for dense models, but we find that the same approach yields no improvement over the naive FP4 baseline in the MoE setting. We conduct an in-depth study to understand why. Our analysis identifies the root cause in the routing mechanism unique to MoE: because the router makes discrete expert-selection decisions, training-inference policy alignment becomes acutely sensitive to whether the same recovery technique is applied symmetrically on the training and inference sides. When an asymmetric recipe is used-including the dense-model approach, which corrects only the rollout-training-inference alignment deteriorates sharply, as measured by the Pearson correlation coefficient between training and inference probabilities, and router selection matching rates. Building on this finding, we propose MoEResQ, a quantization-recovery recipe for MoE RL post-training that enforces symmetry between the training- and inference-side corrections. MoEResQ restores training-inference alignment and substantially closes the accuracy gap to full precision, establishing symmetric recovery as the key principle in FP4 RL for MoE models.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05137

A Random Matrix Analysis of Symmetric Tensor Unfolding

Tom Szwagier, Xiaoyi Mai, José Henrique de Morais Goulart

原文摘要

We study a fundamental problem in machine learning: partial recovery of a planted signal $\boldsymbol{v} \in \mathbb{S}^{n-1}$ from a spiked tensor $\boldsymbol{\mathsf{X}} = λ\, \boldsymbol{v}^{\otimes p} + \boldsymbol{\mathsf{Z}}$, where $\boldsymbol{\mathsf{Z}}$ has symmetric Gaussian entries of variance $\asymp n^{-1}$. While previous works replace $\boldsymbol{\mathsf{Z}}$ by an i.i.d. standard Gaussian tensor to circumvent technical difficulties caused by dependencies, this paper directly analyzes the symmetric model via random matrix theory. We show that the square unfolding algorithm is subject to a sharp phase transition for partial recovery at $λ\asymp n^{(p-2) / 4}$, validating an open conjecture from Montanari and Richard (2014). We get precise expressions for the limiting spectral distribution, deterministic equivalent, phase transition threshold and overlap. The main message is that unfolded symmetric tensors spectrally behave like standard Wigner matrices, up to simple transformations accounting for high-order symmetries. We consider extensions to multiple orthogonal spikes, recursive unfolding and non-square unfolding via disproportionate random matrix theory, leading to an interesting conjectured statistical-computational tradeoff regarding the choice of unfolding: square versus long.

stat.ML · cs.LG · math.PR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.28569

ECHO: Efficient Cascade with Homogeneous Operators for Distillation-Guided 100K-Sequence Modeling

Wenhao Li, Qinglin Jia, Chenghou Jin, Zihong Xian, Jiezhou Ji, Yanzhi Liu, Zezheng Wang, Bo Chen 等 12 位作者

原文摘要

Modeling lifetime user behavior sequences is essential for capturing long-range preferences in industrial recommendation, yet sequences containing up to 100K interactions make target-aware ranking prohibitively expensive. Search-based methods that retrieve from raw sequences incur candidate-dependent costs that grow with sequence length, whereas latent compression methods reduce computation at the expense of item-level addressability. We propose ECHO (Efficient Cascade with Homogeneous Operators), a framework that balances efficiency and fine-grained retrieval by retaining a subset of original event records per user through a Distilled Selector (DS) and retrieving a smaller set of target-relevant records for each candidate through a Target-aware Fine-grained Retriever (TFR). DS is supervised by a candidate-aware full-history teacher via per-target distillation, enabling target-aware user-level selection without requiring full-history computation for every candidate. The retriever and target-attention scorer share the relevance parameters learned by the teacher, ensuring consistent relevance estimation throughout the cascade. At a sequence length of 100K, ECHO reduces online sequence-branch FLOPs by approximately 160 times compared with a representative end-to-end model. Three deployment optimizations, including common user inputs, compact record encoding, and key-side projection absorption, further reduce memory, storage, and data-movement overhead. Experiments on KuaiRand-1K and an industrial-scale short-video platform demonstrate relative GAUC improvements ranging from 0.113% to 1.520% over state-of-the-art baselines across multiple tasks. Furthermore, online A/B tests in two production scenarios, Kuaishou and Kuaishou Lite, show that ECHO improves app usage time by 0.240% and 0.373%, respectively.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04087

ScienceVision: Can AI Observe and Reason Like a Scientist?

Tianyi Ma, Jing Gu, Haozhe Zhao, Liang Chen, Yunfan Zhang, Haijun Su, Jialong Wu, Le Xue 等 13 位作者

原文摘要

Scientific discovery builds on accurate observations interpreted through domain knowledge and reasoning. For scientific 3D data, this requires understanding structures and spatial relationships, from protein contacts to anatomical organization. Existing multimodal benchmarks largely evaluate text and 2D images, while scientific 3D evaluations vary in representations and protocols across disciplines, limiting cross-disciplinary comparison. To assess these foundational capabilities, we introduce ScienceVision, a cross-domain benchmark for scientific 3D understanding and reasoning through expert-level visual question answering (VQA). We construct 250 questions, with 50 each from Biology, Chemistry, Medical Imaging, Mechanical CAD, and Architecture, through a pipeline combining synthetic question generation with domain-expert review and annotation. Each task pairs a native 3D artifact with a scientific question, a specified response format, and a task-specific reference answer, requiring domain knowledge to be applied to geometric or topological evidence. We evaluate 12 models on the same questions in three settings: visual question answering with native 3D artifacts accessed through an agent harness's file and code-execution tools; the same workflow augmented with expert-inspired viewer inspection and measurement tools exposed through the Model Context Protocol (MCP); and visual question answering from prescribed rendered 2D images using an agent harness. All settings use the same task-specific deterministic final-answer scoring. The inspection environment supports view changes, target isolation, and slice inspection. In this main comparison, the best mean answer score is 0.53 out of 1. Mean scores in the native-artifact workflow without additional MCP tools exceed those in the rendered-image workflow for every model, by 17.2 percentage points on average.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01607

NatureFusion: Rethinking Infrared and Visible Image Fusion as Natural Complementary Enhancement

Jianfeng Ding, Linfeng Tang, Hao Zhang, Han Xu, Xunpeng Yi, Yibing Zhang, Meiqi Gong, Zhongyuan Wang 等 9 位作者

原文摘要

In the absence of ground truth, most existing infrared and visible image fusion methods pursue fidelity to the source images and directly superimpose two physically distinct modalities. As a result, salient infrared targets appear as bright patches of thermal radiation pasted onto the scene. These patches obscure the original color and texture of the targets, so the fused images look unnatural to human observers and deviate from the data distribution learned by vision models pretrained on visible images. Therefore, we redefine infrared and visible image fusion as natural complementary enhancement rather than source fidelity, and propose NatureFusion, which exploits cross-modal complementary cues to infer a clear and natural visible-style image from low-quality visible and infrared image pairs. Specifically, to address the lack of ground truth, we employ a generative foundation model as the teacher to directly generate visually natural fused images for supervision. Furthermore, to fully distill the teacher's generative capability while reducing computational cost, we fine-tune a pretrained generative model with conditional flow matching through a light-weight fusion adapter. Last but not least, to further improve downstream performance without sacrificing natural appearance, we freeze the fusion adapter and introduce a detector-supervised task adapter that strengthens the complementary contribution of infrared. Extensive comparisons with seven multi-modal fusion and seven single-modality enhancement methods demonstrate that NatureFusion generates visually natural fused images with the best perceptual quality. Detection and segmentation models pretrained on visible images achieve substantially higher accuracy on our fused images than on those of any competing method.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.40530

PhysCount：多模态大模型是在数视觉表象还是物理实体？

PhysCount: Do MLLMs Count Visual Appearances or Physical Entities?

Lidong Lu, Jiaxin Lv, Liangrui Dong, Xinyi Mao, Lidong Zou, Zhenquan Li, Tong Lu, Guo Chen

AI 速读 基于摘要

PhysCount 是一个新基准，用来检验多模态大模型能否区分图像中“可见的表象”与场景中“物理存在的实体”，并据此进行计数。

cs.CV

arXiv ↗PDF ↗
查看原文摘要

Images reveal appearances, but counting often asks about physical objects. A single entity may be visible directly, in several reflections, or through glass, so detecting every visible occurrence does not determine how many entities are present. Existing visual counting benchmarks rarely separate these two operations. We introduce PhysCount, a benchmark for evaluating whether multimodal large language models (MLLMs) can distinguish what appears in an image from what physically exists in the scene. PhysCount contains 546 real-world images and 4,595 human-written questions organized into 651 target-specific groups. For each group, annotators locate the relevant appearances, label how each is observed, and identify appearances of the same entity. Four complementary question families test the enumeration of appearances, the enumeration of physical entities, image-formation-specific counting, and appearance--entity correspondence. We measure both accuracy on each family and the proportion of groups answered entirely correctly. Across 40 MLLMs, counting visible appearances is substantially easier than recovering the identities that connect them. Even the strongest model answers every question correctly in only 13.36\% of groups. Performance declines when one entity produces many appearances or when its appearances cross observation modes. Higher image resolution improves access to visual evidence but brings limited gains in complete-group accuracy, whereas answering related questions jointly produces a marked improvement. These results expose a gap between recognizing what is visible and correctly recovering the physical entities behind those observations.

版本更新 · v2arXiv:2605.02697

Executor-Side Progressive Risk-Gated Actuation for Agentic AI in Wireless Supervisory Control

Zhenyu Liu, Yi Ma, Rahim Tafazolli

原文摘要

Agentic artificial intelligence built on large language models shows promise for automating Open Radio Access Network supervisory control. However, action-level safeguards alone may be insufficient: evidence acquisition consumes time and shared resources, and network changes can invalidate approvals before release. We propose Progressive Risk-Gated Actuation (PRGA), an executor-side model and contract governing intents from assessment to release or termination. PRGA combines local checks with selective retrieval of coordination evidence to reduce acquisition costs while preserving mandatory evidence requirements. Version and lease rechecks prevent release under invalidated approvals, while reevaluation requires recorded progress within each transaction's retry budget. Building on this contract, we formulate evidence allocation to maximize the expected whole-period rate of timely valid releases under risk, quality-of-service, deadline, and shared byte-budget constraints. For energy-saving and slice-protection workloads with stable daily load cycles, thresholds are selected offline and interpolated using an online load-phase estimate. On average over modeled start phases and quota levels, the allocation policy improves timely valid release rates over arrival-order fetching and an offline-selected global threshold under identical quotas and release checks. In OpenAirInterface radio emulation, an immediate scripted resend after a version-mismatch refusal raises on-time receiver delivery from 77.3% to 89.9% at modest additional command cost.

eess.SY · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39744

PAPERBENCHX: Can AI Reproduce Science Across Disciplines?

Ruoyu Wu, Zengji Tu, Aolong Sun, Tianyi Ma, Junren Li, Xinbo Xu, Li Fu, Ziyan Zhang 等 17 位作者

原文摘要

Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist: the target claim is known, yet recovering it still requires translating an incomplete scientific description into an executable experiment and producing evidence that can be independently verified. Existing research-reproduction benchmarks largely focus on AI and machine learning, where experiments share relatively homogeneous software stacks. Extending this capability across scientific disciplines introduces a different challenge: agents must operate domain-specific scientific software, make physical and numerical choices, diagnose long-running computations, and distinguish valid evidence from merely plausible outputs. We introduce PAPERBENCHX, a benchmark of 93 expert-constructed paper-reproduction tasks spanning 12 research areas across electromagnetics, photonics, chemistry, materials science, biology, and robotics. Each task provides the source paper, a public task specification, and a domain-native scientific environment involving specialized scientific software. Agents must reconstruct a key experiment, execute and diagnose it, and deliver a runnable workflow that supports the target scientific claim. To evaluate scientific validity rather than surface-level agreement, we replay every submission from scratch and score only regenerated evidence against expert-validated criteria. Across 10 frontier agent configurations, the best configuration fully reproduces only 14% tasks under the 90% threshold. Meanwhile, mean rubric scores range from 27.53% to 59.08%, indicating that substantial partial progress rarely translates into complete scientific reproduction. These results reveal a large gap between paper understanding and reliably producing reproducible scientific evidence.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.13406

Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement

Hongyao Tang, Yi Ma, Pengyi Li, Yifu Yuan

原文摘要

When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards autonomous and evolving intelligence, RSI is being claimed at many scales, while no single framework that formally describes these emerging instances exists. Its counterpart in the classical realm, iterative policy improvement, is characterized by generalized policy iteration (GPI), a framework of broad applicability with well-understood theoretical properties, but only where the update principle and the evaluation base lie outside the agent. In this paper, we propose Generalized Agent Iteration (GAI), a formal framework that describes iterative policy improvement and RSI as two cases of a single learning paradigm. GAI defines the agent as a configuration of modifiable components within a system and models the learning process as a cycle of agent evaluation and agent improvement. Two pivotal dials then distinguish the instances, in particular the systems that self-identify as RSI in recent work: whether the improving mechanism is part of the agent and whether the standard it is measured against is grounded outside it. The former dial delineates the boundary between GPI and RSI, and the latter determines a system's polarity as anchored, goal drift, or fully self-referential. Moreover, we use these coordinates to place existing systems on the same two axes and make the defects of recursive self-improvement statable one condition at a time. We see this paper as a first step toward exploring a formal characterization of RSI that rests on the classical account, makes existing systems comparable, and provides a principled basis for analyzing and designing new ones.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39322

MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion

Meiqi Gong, Hao Zhang, Jiayi Ma

原文摘要

Multimodal videos contain rich temporal cues that can facilitate faithful fusion. However, existing video fusion methods mainly rely on short-range temporal interactions, leaving valuable long-term information underexplored. Moreover, inconsistent fusion representations can cause flickering artifacts, undermining temporal coherence. To address these coupled challenges, we propose MemoryFusion, a two-stage framework integrating cross-temporal memory learning with progressive temporal refinement. Considering the complementary roles of adjacent and distant frames, the first stage combines a Short-Term Memory Bank for local temporal guidance with a Long-Term Memory Bank that preserves reliable historical information through a fusion-oriented update strategy. To mitigate temporal fluctuations, a Temporal Smoothing Module leverages soft motion cues for coarse background stabilization. Building upon the resulting fusion prior, The second stage further employs a lightweight 3D residual Temporal Refinement Module to correct remaining temporal inconsistencies while enhancing structural details. Extensive experiments demonstrate that MemoryFusion achieves superior fusion quality and temporal consistency over existing frame-based and video-based fusion methods. The source code is publicly available at https://github.com/Meiqi-Gong/MemoryFusion.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.39321

Satisficing Regret Minimization in Bandits with Knapsacks

Qing Feng, Tianyi Ma, Ruihao Zhu

原文摘要

We study satisficing regret minimization in bandits with knapsacks (BwK), where a learner sequentially selects randomized policies, i.e., distributions over arms, to obtain mean rewards above a satisficing threshold as frequently as possible while respecting finite resource budgets. The performance is measured by satisficing regret, the cumulative deficits of the selected policies' mean rewards below this threshold. Resource constraints introduce two difficulties: an algorithm can incur linear satisficing regret even with small standard regret as deficits to the threshold cannot be compensated, and random consumption can cause early resource depletion even when policies are feasible in expectation. To address these challenges, we propose SELECTwK, a general algorithmic template that uses a BwK learning oracle algorithm with sub-linear expected (standard) regret upper bound to search for and test candidate satisficing policies (i.e., policies whose mean rewards exceed satisficing threshold and whose expected resource consumption is feasible over the time horizon). Our regret analysis, supported by an LP-duality argument, establishes that SELECTwK attains constant expected satisficing regret when a satisficing policy exists. We further introduce a stronger regret condition that bounds the expected sum of positive reward deficits to the optimal one at each time step, under which SELECTwK achieves a sharper constant bound together with a sub-linear bound in the time horizon. As a complement, SELECTwK still preserves the oracle's sub-linear expected standard regret bound if the satisficing threshold is unattainable. Finally, we establish the oracle conditions and corresponding satisficing regret bound for existing finite-armed BwK and dynamic pricing algorithms, and conduct numerical experiments on dynamic pricing with limited inventory to demonstrate the empirical performance of SELECTwK.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.23111

Inherit4Rec: Parameter Inheritance for Efficient Scaling of Recommendation Models

Ruihao Zhang, Bo Chen, Xiao Wang, Jinlong Jiao, Tijian Hu, Qinglin Jia, Xiuqiang He, Xiangyu Zhao 等 11 位作者

原文摘要

Scaling model capacity has emerged as an effective approach to overcoming performance bottlenecks in industrial recommender systems. However, repeatedly training new models from scratch requires large amounts of data and substantial training resources. Parameter inheritance provides a promising route for both dense model growth and sparse conversion, yet existing methods for LLMs are primarily designed for static corpora and can suffer sharp performance drops under dynamically evolving recommendation data. To address these challenges, we propose Inherit4Rec, a parameter-inheritance framework that supports both Dense-to-Dense (D2D) growth and Dense-to-Sparse (D2S) conversion. Inherit4Rec-D2D combines hybrid growth with asymmetric training to preserve the forward function at expansion and maintain update continuity. Inherit4Rec-D2S constructs SMoE networks through co-activation-aware partitioning with a load-balancing loss, preserving dense-model capabilities while promoting balanced expert activation. Experiments on KuaiRand-1K and an industrial short-video recommendation dataset show that both transformations consistently outperform the SOTA inheritance baselines across all prediction objectives. These results demonstrate the effectiveness of Inherit4Rec for continual capacity expansion and computation-efficient sparse conversion in industrial recommender systems.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35637

SeeRF: Learning to See Beyond Fields of View via Generative Image Registration and Fusion

Xunpeng Yi, Yibing Zhang, Qinglong Yan, Yifan Lu, Han Xu, Jiayi Ma

原文摘要

Due to the inherent discrepancies in imaging viewpoints and field-of-view mismatches among multi-modal sensors, existing fusion methods have long struggled to achieve complete scene-level information integration beyond the limitation in sensor fields of view. Consequently, the generated fusion results often contain modality-specific regions and fusion artifacts, limiting the comprehensive representation of scene structures and semantic information. To address this challenge, we propose a generative registration-fusion framework, termed SeeRF. Specifically, it first introduces a deformation generation strategy based on the diffeomorphic stationary velocity field, combined with visual foundation model-guided feature extraction and a coarse-to-fine progressive multi-modal image registration module, to achieve accurate cross-modal flow estimation and generate valid field-of-view masks. Subsequently, the registration module is tightly coupled with the generative diffusion module for multi-modal completion and fusion, where the cross-modal control encoding module and the control residual feature encoder-decoder mechanism provide effective guidance. By leveraging the powerful prior modeling capability of generative diffusion models, the proposed framework overcomes the limitations imposed by shared fields of view and enables effective completion and natural fusion of non-overlapping field-of-view regions. Extensive experiments on multiple public datasets and real-world scenarios demonstrate that the proposed method achieves superior performance, validating its effectiveness, superiority, and robustness. The code will be available at https://github.com/XunpengYi/SeeRF.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35522

Generative Structure from Motion with Native 3D Diffusion

Haobin Duan, Binbin Huang, Mochu Xiang, Yiqun Zhao, Zibo Zhao, Yi Ma, Shenghua Gao

原文摘要

Recovering an object's 3D structure and camera motion from a few uncalibrated views is a fundamental problem in computer vision. Classical structure from motion methods recover 3D geometry consistent with the input images but cannot recover unseen regions; native generation methods produce plausible 3D objects which are related but not necessarily faithful to the input images. Methods simply concatenating reconstruction and generation allow error to cascade across the two stages, instead of producing a 3D object consistent with both the distribution and the input. We propose GenSfM, which integrates image-based 3D reconstruction with a native 3D diffusion model. In particular, we use a multi-modal diffusion transformer to jointly denoise the shape latent and per-view pose latents under shared self-attention, grounding generated geometry in the observed views while using object-level priors to infer unobserved regions. A compact 3D-native UV-volume tokenization keeps the joint sequence small as views are added, and a pose-aware stage refines geometry and texture by sampling per-voxel image features at the recovered camera poses. On Toys4k and GSO, for $4$ uncalibrated views, GenSfM improves novel-view PSNR by $3.2$-$4.5$ dB and reduces median Chamfer distance by $2.8$-$3.8\times$ over a strong native-3D generation baseline, while recovering input-view poses over $96\%$ Acc@$5^\circ$ without any external pose-estimation backbone, post-hoc optimization, or known intrinsics. Project page: https://dotb1ue.github.io/GenSfm/.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35036

Mapping the Solution-Set Structure of Grokking on Latin Squares

Zihan Gu, Lulu Zhao, Tianyi Ma, Hua Zhang, Wenbo Su, Yanan Cao, Yue Hu

原文摘要

Grokking is a delayed transition from memorisation to generalisation. A network first fits observed examples while remaining near chance on held-out inputs, then generalises abruptly. Prior work has focused mainly on this delay, finding that the network's main loss becomes weight decay after the fitting phase. We name the solution to this optimization problem as the minimum-norm endpoint, and study which tasks make all minimum-norm endpoints generalise from partial observations. Specifically, we model pairwise input tasks as edge colourings of $K_{q,q}$, with Latin colourings as our structured family, and classify each observed instance as all-good, mixed, or no-good by its endpoint set. Furthermore, we prove two contrasting results: (1) Finite-abelian-group families are asymptotically all-good from partial observations; (2) Under a uniform random Latin square, all-good tasks become asymptotically rare for observation-based learners, leaving mixed or no-good behaviour. Moreover, experiments show that relabellings of addition generalise despite their dense polynomial representations. Finally, on tasks of composite order, finite-training results suggest that predictors learn a coarse part of the output before the full label.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2609.00566

EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection

Guanzhong Sun, Junyi Ma, Yuxuan Wu, Wei Tang, Yanzi Miao

原文摘要

We propose EEG-VID, a task-guided latent predictive pretraining framework for EEG decoding under session and subject shifts. EEG-VID predicts future latent EEG states from recent history using an exponential-moving-average target encoder and weak task guidance, followed by supervised fine-tuning. Across VIG-48 and BCI Competition IV-2a/IV-2b, Stage 1 improves mean accuracy in 41 of 42 matched backbone-dataset-protocol comparisons, including all 12 leave-one-subject-out settings, with a maximum gain of 16.22 percentage points. On the 48-region cross-day VIG-48 task, EEG-VID achieves 6.52% Top-1 and 30.50% Top-5 accuracy. In a separate six-participant offline robot-scene study, candidate-constrained target selection reaches 40.24% versus a 25% chance level after subject-specific calibration. These results support task-guided latent prediction as a transferable pretraining strategy for EEG decoding and scene-constrained assistive target selection.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.17384

IndustryNav: Evaluating Spatial Reasoning and Safety of Embodied Agents in Dynamic Industrial Navigation

Yifan Li, Lichi Li, Anh Dao, Xinyu Zhou, Wenjun Huang, Tianyi Ma, Yicheng Qiao, Zheda Mai 等 18 位作者

原文摘要

Visual large language models (VLLMs) are increasingly used as embodied agents, yet industrial warehouses demand more than reaching a goal: agents must navigate safely around moving workers and vehicles. To evaluate embodied agents' goal reaching and safety, we introduce IndustryNav, a simulation environment with 24 warehouse scenes for closed-loop navigation to specified destinations. Alongside task success and efficiency, we introduce safety-aware metrics that capture collisions and near-collision warnings along each trajectory. Experiments with eleven leading open- and closed-source VLLMs and three navigation baselines show that agents can reach their goals yet collide with moving obstacles, exposing a gap between success and safe navigation. This gap matters in safety-critical settings, where a single collision can end the task. IndustryNav also supports policy learning through automated oracle trajectories and simulator interaction, with held-out scenes for generalization tests. These experiments show that policies can succeed on new routes in familiar warehouses yet fail to transfer to held-out layouts, making cross-scene generalization an open challenge.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.02481Berkeley BAIR

Flow Policy Gradients for Robot Control

Brent Yi, Hongsuk Choi, Himanshu Gaurav Singh, Xiaoyu Huang, Takara E. Truong, Carmelo Sferrazza, Yi Ma, Rocky Duan 等 12 位作者

原文摘要

Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action likelihoods, which constrain policy outputs to simple distributions like Gaussians. In this work, we show how flow matching policy gradients, a recent framework that bypasses likelihood computation, can be made effective for training and finetuning more expressive policies in challenging robot control settings. We introduce an improved objective that enables success in legged locomotion, humanoid motion tracking, and manipulation tasks, as well as robust sim-to-real transfer on two humanoid robots. We then present ablations and analysis on training dynamics. Results show how policies can exploit the flow representation for exploration when training from scratch, as well as improved finetuning robustness over baselines.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1266ACL Anthology · ACL 2026

Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry

Han Zhang, Zihan Gu Institute of Information Engineering, Chinese Academy of Sciences, Zhiyuan Wang, Tianyi Ma, Jiacheng Lu Shanghai Jiao Tong University, Xinyan Zhang independent, Yuhao Wei, Cheng Hua Shanghai Jiaotong University

原文摘要

While Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns. To address this issue, we introduce Neo-Classic, an evaluation benchmark that combines a constructionist Out-of-Sample (OOS) dataset with a suite of reverse understanding probes. Unlike traditional benchmarks that rely on verification or generation over historical corpora, Neo-Classic comprises strictly metrical poetry authored by contemporary experts, reducing the possibility of direct retrieval. We evaluate state-of-the-art models, including Qwen3-Max, Gemini-3-Pro, and DeepSeek-V3.2, across five behavioral probes designed to test hierarchical constraint satisfaction. Our results reveal two primary limitations. First, a performance gap of 20%–50% emerges when models transition from historical to contemporary texts. Second, models exhibit substantial difficulties in discourse-level ordering tasks, with standard accuracy remaining low (0–13%). Although expert-level guidance improves the performance of reasoning-enhanced models to 36%, a notable gap with human experts persists. These findings suggest that while current LLMs capture local formal patterns, they struggle with global hierarchical planning required for robust Linguistic-Aesthetic Reasoning.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表