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

+2新增论文
+2其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-12 21:36 · 全站最近入库：2026-11-12 06:37各信源进度 →

统计口径与数据新鲜度

统计 2026-11-11 22:25 — 2026-11-12 22:25（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：2026-11-12 21:36最近发现新增版本：2026-11-12 06:37库内论文最新更新时间：2026-11-11 08:00

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。

21,675 已收录论文18,323 AI 相关6,056 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 45 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-12 21:30（北京时间）
新论文 · v1arXiv:2611.14035

ScaleBrain: A Scale-Consistent Framework for EEG Foundation Models

Minyu Zhou, Yajing Wu, Yongqiang Tang, Wang Jia, Wensheng Zhang

原文摘要

Foundation models pre-trained on large unlabeled electroencephalography (EEG) corpora have emerged as a transformative paradigm for Brain-Computer Interface (BCI) applications. Recent EEG foundation models have shown that multi-scale representations derived from fixed-length patches can improve EEG representation learning. Existing frameworks commonly construct temporal scales through feature-level operations. However, these operations leave the correspondence between learned features and scale-specific characteristics of the original EEG signals implicit. Moreover, when the self-supervised objective is not aligned with the multi-scale input representations, information at some temporal scales may receive insufficient supervision during pre-training. In light of this, we propose ScaleBrain, a scale-consistent pre-training framework that explicitly coordinates multi-scale representations of EEG from both the model input and optimization objective sides. Specifically, ScaleBrain introduces multi-scale EEG tokenization to represent the same EEG segment through analysis windows with different temporal spans and shared temporal anchors, and pairs these representations with scale-specific reconstruction to align with the multi-scale input structure and provide supervision across temporal resolutions during self-supervised learning. We further develop an axial spatio-temporal attention mechanism to contextualize the fused multi-scale representation along spatial and temporal dimensions. Extensive evaluations on six public BCI benchmarks against 12 representative baselines show that ScaleBrain achieves the highest mean Balanced Accuracy on five datasets and ranks third on the remaining one, with only 5.0M parameters, demonstrating strong performance and favorable parameter efficiency.

cs.LG · eess.SP · q-bio.NC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.12253

Is Online Linear Optimization Sufficient for Strategic Robustness?

Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng

原文摘要

We consider bidding in repeated Bayesian first-price auctions. Bidding algorithms that achieve optimal regret have been extensively studied, but their strategic robustness to the seller's manipulation remains relatively underexplored. Bidding algorithms based on no-swap-regret algorithms achieve both desirable properties, but are suboptimal in terms of statistical and computational efficiency. In contrast, online gradient ascent is the only algorithm that achieves $O(\sqrt{TK})$ regret and strategic robustness [KSS24], where $T$ denotes the number of auctions and $K$ the number of bids. In this paper, we explore whether simple online linear optimization (OLO) algorithms suffice for bidding algorithms with both desirable properties. Our main result shows that sublinear linearized regret is sufficient for strategic robustness. Specifically, we construct simple black-box reductions that convert any OLO algorithm into a strategically robust no-regret bidding algorithm, in both known and unknown value distribution settings. For the known value distribution case, our reduction yields a bidding algorithm that achieves $O(\sqrt{T \log K})$ regret and strategic robustness (with exponential improvement on the $K$-dependence compared to [KSS24]). Moreover, we can further exploit the single-strategy benchmark and construct a bidding algorithm with $O(\sqrt{T(\log K+\log T)})$ regret and $O(1)$ strategic robustness. For the unknown value distribution case, our reduction gives a bidding algorithm with high-probability $O(\sqrt{T (\log K+\log(T/δ)})$ regret and strategic robustness, while removing the bounded density assumption made in [KSS24].

cs.GT · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13539

Exploiting Feature-invariant Scaling Laws for Efficient A/B Experimentation in Recommendation Systems

Zhiliang Chen, Sammy Nammari, Jiahao Su, Xiaoqiang Luo

原文摘要

Researchers and engineers improve recommendation systems by performing A/B experiments with new model architectures, optimization methods, and data features. However, running full-scale experiments (e.g., full-model training with online data) for every feature change is prohibitively computationally intensive, while the result from a single small-scale experiment is often misleading. To address this challenge, we show that modern recommendation models exhibit feature-invariant scaling: the change of a model's performance follows a predictable scaling-law even when different feature changes are applied to the baseline model. We introduce an efficient method that exploits scaling-laws and uses statistical inference to predict (with confidence intervals) the full-scale effect of an A/B experiment in recommendation systems. This enables practitioners to efficiently filter out neutral or regressive feature changes with only small-scale experimentation. We validate our method on three distinct recommendation model families---Wukong, HSTU, and LLM-based recommendation models---across more than 40 architectural, optimization, and data changes. Our method accurately distinguishes beneficial feature changes from neutral and regressive ones while using only a fraction of the compute required for full-scale evaluation. It also identifies several changes that improve HSTU's state-of-the-art performance on MovieLens-20M. Our results demonstrate that scaling laws can be practically exploited to make compute-efficient decisions for improving industrial-scale recommendation systems.

cs.IR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2605.21139

Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving

Yang Wu, Qiang Meng, Zhaojiang Liu, Youquan Liu, Jian Yang, Jin Xie

原文摘要

Current end-to-end autonomous driving models are fundamentally constrained by the behavioral cloning ceiling of imitation learning. While reinforcement learning offers a path to smarter autonomy, it demands two missing pieces of infrastructure: (1) a cognitive foundation that understands traffic semantics and driving intent, and (2) a foresighted physical environment that can anticipate the consequences of candidate actions. To this end, we propose CoPhy, a CognitivePhysical reinforcement learning framework for autonomous driving. To distill to think, we distill VLM knowledge into the BEV encoder and then discard the VLM entirely, retaining cognitive ability at zero inference cost while releasing the cognitive channel as a pluggable interface for optional human language commands. To foresee to act, we build an auto-regressive BEV world model that explicitly predicts future semantic maps conditioned on candidate actions, serving as an interpretable physical sandbox from which safety metrics are directly derived. Built upon this dual infrastructure, we optimize the driving policy via GRPO with a novel dual-reward mechanism: a physical reward derived from BEV rollouts enforces hard safety constraints, while a cognitive reward from a language-aligned scorer ensures intent compliance. Extensive experiments demonstrate that CoPhy not only achieves state-of-the-art results on NAVSIM v1 and v2 benchmarks, but also enables safer driving via cognitively informed scene compliance and flexible intent control through user-defined language instructions. Project page: https://wuyang98.github.io/CoPhy/.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.21317

CRAFT: Conflict-Resolved Aggregation for Federated Training

Ziqi Wang, Qiang Liu, Nils Thuerey

原文摘要

The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (FL) under heterogeneous data distributions. Naive averaging can produce a global update that improves the global objective while conflicting with specific clients, causing degradation for those clients. In this work, we propose CRAFT (Conflict-Resolved Aggregation for Federated Training), a new aggregation framework that treats the global update as a geometric correction problem. We formulate aggregation as finding the update closest to a reference direction while satisfying conflict-free alignment constraints. We derive a closed-form expression for the constrained optimization problem, avoiding the computational overhead of iterative solvers. Furthermore, we use a layer-wise adaptation to address conflicts at varying feature granularities. We provide a theoretical analysis showing that CRAFT promotes a common-descent structure and mitigates conflicts through its projection geometry. Extensive experiments on heterogeneous benchmarks demonstrate that CRAFT improves the accuracy of the global model while reducing performance disparity across clients compared with state-of-the-art baselines. The source code for CRAFT is available at https://github.com/tum-pbs/CRAFT.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.06923

Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation

Ziheng Li, Zexu Sun, Jinman Zhao, Erxue Min, Yongcheng Zeng, Hui Wu, Hengyi Cai, Shuaiqiang Wang 等 11 位作者

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models (LLMs). However, existing RLVR methods often suffer from exploration inefficiency due to mismatches between problem difficulty and model capability: overly difficult problems hinder reasoning path discovery, while overly simple problems offer little learning signal. To address this, we first formalize the effect of problem difficulty by quantifying the relationship between loss descent magnitude and rollout accuracy. Building on this analysis, we propose SEELE, a supervision-aided RLVR framework that dynamically adjusts problem difficulty to lie within the high-performance region. SEELE augments each training sample by appending a hint (part of a full solution) for difficulty reduction. Unlike previous hint-based approaches, SEELE deliberately computes the hint length for each individual problem to achieve an optimal difficulty. The optimal hint length is determined via multi-round rollout sampling, where an item response theory model fits accuracy-hint pairs from previous rounds to predict the next-round hint. This instance-level, real-time difficulty adjustment aligns problem difficulty with the evolving model capability, thereby improving exploration efficiency. Experiments show that SEELE outperforms Group Relative Policy Optimization (GRPO) and Supervised Fine-tuning (SFT) by +10.0 and +8.4 points, respectively, and exceeds the best prior supervision-aided approach by +3.8 points on average across six math reasoning benchmarks.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12109

SkillDuet: Co-Evolving Models and Skills through Response Feedback

Xingguang Ji, Ziqiang Dong, Yubo Zhang, Xi Leng, Yang Yang, Guanjun Jiang

原文摘要

During reinforcement learning, experience can be both internalized in LLM parameters and retained externally as reusable textual skills. Parameter updates alter the model's behavior and the interaction experience from which new skills are extracted. These skills, in turn, guide the model's subsequent interactions and parameter updates. As the model's capabilities evolve, previously beneficial skills may become redundant or detrimental. We present SkillDuet, a framework that coordinates parameter updates and skill evolution through model response feedback. Skills extracted from on-policy trajectories guide parameter updates through OPD at every step. A response-based score, Strength, ranks candidate skills by the magnitude of the shift they induce in the current model's responses, and the highest-scoring skills are periodically consolidated into a persistent global skill set (Global). The updated model and Global jointly guide subsequent interactions, generating experience for further parameter and skill updates. With Qwen3-4B, SkillDuet achieves success rates of 98.57% on ALFWorld and 92.97% on WebShop, exceeding the matched SEED-API baseline by 2.86 and 5.47 percentage points, respectively. Ablations show that response-based skill selection and Global consolidation improve task performance. Further experiments show that the benefits of retained skills depend on both their content and their compatibility with the model. SkillDuet provides a concrete mechanism for model-skill co-evolution and skill-level recursive self-improvement.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11526

A Stability Analysis of AdamW: Unstable Equilibria and Non-Convergence

Baiyu Su, Lizhang Chen, Qiang Liu

原文摘要

AdamW is ubiquitous in deep learning, yet its behavior remains poorly understood. We analyze its dynamics through the lens of dynamical systems and show that AdamW admits an implicit fixed-point objective: its fixed points coincide with the stationary points of a constrained and regularized optimization problem. However, not all of these fixed points are stable under AdamW's dynamics, and stability depends sensitively on curvature, weight decay, and momentum parameters. Even in one-dimensional settings, equilibria may be unstable, and trajectories can exhibit persistent oscillations rather than convergence to them. We further extend the analysis to higher dimensions, deriving sufficient conditions for local stability of the continuous-time dynamics, and propose a convergent modification that preserves AdamW's fixed points. These results clarify what optimization problem AdamW is associated with, when its convergence can be expected, and how its dynamics could inspire more reliable optimizers.

cs.LG · math.OC · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.18516

Signed Rectified Flow: Negativity-Controlled Generation

Runlong Liao, Baiyu Su, Lizhang Chen, Qiang Liu

原文摘要

We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure $π^{sign} = (1+α)π^+ - απ^-$, where $α>0$, $π^+$ is the distribution to promote, and $π^-$ is the distribution to suppress. Although direct sampling from a signed measure is not well-defined, Signed RF induces a valid generative process that concentrates probability in regions where the signed measure is positive while provably excluding regions dominated by its negative component. It therefore provides a principled framework for incorporating negative information and exclusion constraints into generative modeling. We analyze the signed continuity equation underlying Signed RF and use a charged-particle interpretation to explain how negative mass forms exclusion barriers. This theory further motivates practical adaptive guidance algorithms. Across several applications, Signed RF improves the fidelity-diversity trade-off on ImageNet, reduces nearest-neighbor similarity in anti-memorization experiments, and reduces nudity induced by adversarial prompts in Stable Diffusion 3.5 while preserving CLIP and aesthetic scores.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10824

AutoC2V: Synthesis-Guided LLM Training for QoR-Optimized C++-to-Verilog Generation

Guanqi Lyu, Fei Zhao, Zhaojun Lu, Jiaji He, Yongqiang Lyu

原文摘要

High-level synthesis (HLS) can translate C/C++ kernels into register-transfer level (RTL) designs, yet generating high-quality hardware still relies heavily on manual pragma tuning and repeated synthesis evaluation. We propose AutoC2V, a C++-to-Verilog generation framework driven by real synthesis feedback that enables large language models (LLMs) to directly generate RTL with improved quality of results (QoR) from synthesizable C++ kernels. We construct training data from real synthesis results, including synthesizable C++ source code, the corresponding Verilog RTL, QoR metrics, and optimization objectives. Using this dataset, we align the model toward synthesis-aware RTL generation through Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO). To reduce the high cost of repeatedly invoking real synthesis during GRPO, we design the QoR Prediction Reward Model (QoR RM), which predicts latency and resource metrics by encoding RTL into long-context semantic representations, thereby providing low-cost and continuous QoR reward signals for policy optimization. Experimental results demonstrate that AutoC2V not only substantially improves RTL functional pass rates, but also achieves superior latency and resource optimization compared to the unfine-tuned base model, representative HLS optimization approaches (HLSPilot, LLM-DSE, and AutoDSE), and advanced general-purpose commercial models (Claude Opus 4.8, GPT-5.5, Gemini 3.1 Pro, DeepSeek v4 Pro, and GLM-5.2). These results indicate that combining real synthesis data with efficient QoR reward modeling can further improve the ability of LLMs to generate high-quality RTL.

cs.AR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.17623

RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning

Kunwang Zheng, Xinyu Sun, Yu Cao, Shuocheng Li, Lei Cheng, Ying Liu, Qilong Zhang, Jinlong Chen 等 10 位作者

原文摘要

Rubric-based reinforcement learning grades a response against many written criteria but collapses them into one reward, which discards the detail the rubric carries and gives no GRPO reward gradient when a group's responses tie. A frozen teacher that reads the rubric as privileged context provides token-level supervision, but we observe an early plateau in the gains over GRPO. RELAY uses advantages and rewards to select positive-advantage and low-scoring zero-advantage rollouts, and monitors the distillation loss to decide when to retire the teacher. Stage 1 combines selective distillation from a frozen teacher with GRPO; a plateau detector then removes the teacher, and Stage 2 continues with GRPO alone. Calibrated on one model-domain pair and reused unchanged in three others, the plateau detector fires between steps 122 and 171. RELAY scores highest in-domain among the compared methods in all four settings, ahead of GRPO on RaR-Medicine by 4.62 points with Qwen3-1.7B and 6.02 with Qwen3-4B. On Qwen3-1.7B/Medicine, removing the teacher from a shared checkpoint outperforms keeping, weakening or refreshing it. Distilling selected rollouts covering about half the response tokens also outperforms distilling all rollouts at a matched average coefficient.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10570

Deep backward multistep high-order regression methods for high dimensional nonlinear parabolic partial differential equations

Qiang Han, Shaolin Ji, Zihao Xv

原文摘要

We propose a deep backward multistep high-order regression (MHDBR) method for semilinear parabolic partial differential equations through their backward stochastic differential equation representations. The method combines multistep time discretization with regression targets formed by conditional expectations. Under explicit regularity, starting-value, forward-approximation and network-moment assumptions, we prove an error bound separating time discretization, conditional Monte Carlo sampling and neural-network approximation. The analysis assumes exact population minimization; finite-training-sample generalization and optimization errors are not included. For generators independent of the gradient variable, suitably constrained GroupSort networks and sufficiently large conditional sample sizes give order $J$ in the stated nodal $L^2$ error norm. The required network sizes depend on dimension, so this result does not establish dimension-independent complexity. We present a reproducible time-discretization test satisfying the analytical assumptions and three broader neural-network benchmarks, whose relation to the assumptions is discussed explicitly.

stat.ML · cs.LG · math.AP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.30667

StarWM: Self-Supervised Trained Attention Routing for Robust World Models

Zeqiang Zhang, Fabian Wurzberger, Maximilian Otte, Daniel Schmid, Sebastian Gottwald, Arne Peter Raulf, Daniel Alexander Braun

原文摘要

A robust world model must strike the balance between faithfully capturing environmental dynamics and abstracting away from irrelevant content. While reconstruction-based world models ensure faithful supervision, they misallocate representational capacity by pixel area rather than dynamics relevance for visual tasks, which can cause task-irrelevant content to dominate the learned representation. Alternatively, reconstruction-free methods avoid this bias but risk discarding possibly relevant information. We propose StarWM, which uses a cross-attention module trained on self-supervised dynamics to decide where reconstruction applies. A dual-stream decoder then restricts reconstruction to the attended regions, with stop-gradient barriers preventing interference between the two objectives. These components allows reconstruction to supervise the visual content of attended regions without contaminating the latent with non-predictive information. On DeepMind Control with dynamic video backgrounds, default (reward-free) StarWM achieves the strongest performance under random-frame distractors and substantially outperforms reconstruction-based baselines under sequential video. In addition, its reward-augmented variant matches or exceeds reconstruction-free methods on sequential video, achieving the highest overall return across all distractor regimes. Mechanistic probing confirms \starwm{} preserves state attributes with near-perfect fidelity through long-horizon imagination while systematically discarding distractors. Code is available on GitHub.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10186

Projected Neural Additive Models as Universal Approximators

Nhon N. Phan, Qiang Du, John D. Clayton, WaiChing Sun

原文摘要

Neural additive models (NAMs) offer interpretability but lack expressivity due to their rigid additive structure, whereas multi-layer perceptrons (MLPs) achieve universal approximation at the cost of transparency. We establish the first theoretical foundation for projected neural additive models (PNAMs), which augment NAMs with a learnable linear transformation $\boldsymbol{T}$ to capture cross-variable interactions. While standard NAMs cannot approximate even the simplest interaction term $χ_1 χ_2$ because their cross-derivatives are identically zero, we prove that PNAMs are universal approximators and characterize the minimum number of projections required for exact polynomial representation. Furthermore, we derive an approximation rate of $\mathcal{O}(M^{-s / (N - 1)})$ for $\mathcal{C}^s$ functions (i.e., functions with $s$ continuous derivatives), where $M$ denotes the number of projections and $N$ the input dimension; this rate is known to be optimal for ridge function approximation. To recover interpretability from the projected inputs, we introduce structured sparsity regularizers and post-hoc symbolic regression techniques that enable global input ranking, parameter pruning, and the conversion of learned bases into compact analytical expressions. Experiments on knot theory invariants, MNIST, and phase field fracture mechanics demonstrate that PNAMs match or surpass similar architectures in accuracy while discovering salient features and yielding symbolic models with orders of magnitude fewer parameters.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.03203

PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction

Daniel C. MacRae, Luuk van der Hoek, Robert van der Wal, Suzanne P. M. de Vette, Hendrike Neh, Baoqiang Ma, Peter M. A. van Ooijen, Lisanne V. van Dijk

原文摘要

Three-dimensional medical image data and computer-aided decision making, particularly using deep learning, are becoming increasingly important in the medical field. To aid in these developments we introduce PR3DICTR: Platform for Research in 3D Image Classification and sTandardised tRaining. Built using community-standard distributions (PyTorch and MONAI), PR3DICTR provides an open-access, flexible and convenient framework for prediction model development, with an explicit focus on classification using three-dimensional medical image data. By combining modular design principles and standardization, it aims to alleviate developmental burden whilst retaining adjustability. It provides users with a wealth of pre-established functionality, for instance in model architecture design options, hyper-parameter solutions and training methodologies, but still gives users the opportunity and freedom to ``plug in'' their own solutions or modules. PR3DICTR can be applied to any binary or event-based three-dimensional classification task and can work with as little as two lines of code.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09175

SIFR: Stable Signed Flow Reinforcement

Runlong Liao, Xingqian Xu, Lizhang Chen, Baiyu Su, Yufan Huang, Zhonghao Wang, Akash Gokul, Ming-Yu Liu 等 10 位作者

原文摘要

Reward-based fine-tuning of flow models requires effectively promoting high-reward and suppressing low-reward samples, while maintaining training stability over many rounds of iterative updates. Iterative reward fine-tuning provides a simple starting point, but the positive reward weights give no explicit unfitting signal, and repeated reweighting concentrates the distribution and causes collapse. We propose Stable Signed Flow Reinforcement (SIFR), which replaces the reward weights by signed advantages to supply the missing unfitting signal, and constrains the velocity drift from a reference model to stabilize the updates, with a Lagrange multiplier that adapts the regularization strength to a prescribed drift budget. We further show that existing flow RL methods fall within this framework: they implicitly minimize the signed loss, differing in their regularization choices. We validate SIFR on SD3.5 Medium (2.5B) and FLUX.2 Klein (9B) and scale it to Cosmos 3 Super Text2Image (64B): across all 12 backbone--reward pairs with preference and rule-based rewards, it matches or exceeds existing methods, reaches their peak rewards much faster, and keeps improving over long training where they plateau or collapse.

cs.LG · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08924

ResQAdam: Residual-Preserving Adaptive Optimization for Memory-Efficient Quantization Aware Training

Liqun Ma, Shengkun Tang, Liangyu Wang, Lin Zhao, Wei Luo, Xinjun Niu, Spandan Tiwari, Ashish Sirasao 等 10 位作者

原文摘要

Quantization-aware training (QAT) is the most reliable way to obtain accurate low-bit large language models (LLMs), but training with AdamW keeps two dense FP32 states for every weight matrix. We find that low-rank memory-efficient optimizers such as GaLore and LDAdam degrade substantially in QAT. A considerable part of the QAT momentum lies outside its top-r singular subspace, and projection-based methods discard this part at every step. We further observe that this residual remains useful when only its sign is kept. Based on these observations, we propose ResQAdam. It keeps a single BF16 momentum, applies Adam only to the r x r coordinates of the principal subspace, and adds a normalized sign update computed from the residual. We evaluate ResQAdam with two from-scratch QAT methods and three QAT fine-tuning pipelines, with weights quantized down to 2 bits. It reduces optimizer-state memory by 71% to 74% relative to AdamW, stays close to AdamW in most settings, and lowers training throughput by less than 2%.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.23457

RLVR$^{2}$: Reinforcement Learning with Verifiable Rubric-based Ranking

Hao Li, Zhengkun Zhang, Gangqiang Hu, Zhen Zhang, Yude Gao, Dai Dai, Jing Liu

原文摘要

Reinforcement Learning with Verifiable Rewards (RLVR) is expanding from tasks with well-defined correctness signals, such as mathematics and code, toward multifaceted quality requirements specified by multi-dimensional rubrics. Since policy optimization consumes one scalar per rollout, rubric-based pipelines must map multiple criterion scores into a scalar reward. This aggregation is often treated as score scaling, but it implicitly determines how quality dimensions trade off during training. The prevailing practice, normalizing each criterion and taking a linear combination, assumes that cardinal score differences are comparable across criteria and that gains on one criterion compensate for failures on another; both assumptions are unreliable when criteria are semantically heterogeneous. We propose Reinforcement Learning with Verifiable Rubric-based Ranking (RLVR$^2$), a verifiable ranking paradigm for rubric-based RLVR. For each criterion, RLVR$^2$ converts rubric scores into criterion-specific within-group ordinal outcomes, recovers a latent utility from the resulting comparison matrix, and merges these utilities into one training signal. By retaining only within-group ordering and discarding raw score magnitudes, RLVR$^2$ avoids calibrating heterogeneous rubric scales. It further supports objective-preserving attribute adjustment: auxiliary attributes that correlate with observed rankings but are not training objectives can enter the estimation without expanding the rubric or rewarding them directly. Across three model scales and 16 benchmarks, RLVR$^2$ consistently outperforms representative rubric-based baselines, achieving the best overall performance on most benchmarks at every scale. Analysis shows it controls systematic effects tied to reasoning efficiency and response formatting while preserving the quality objective.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07512

RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples

Chao Zhou, Shenghua He, Jiaxin Mo, Qiangguo Yu, Fengchuang Xing

原文摘要

Decision-based sparse attacks must reduce perturbation support using only the victim's predicted label. The best restoration strategy varies as support contracts: coarse removal works early, while tail states need finer, history-aware tests. We propose RLGPA, an online reinforcement learning method that schedules support-reduction executors and their granularity under a hard query budget. A masked Dueling Double DQN selects among seven stable policy--scale actions; each action produces support-relative restoration groups that are rebuilt after every macro decision. A feasibility-preserving executor commits only adversarial restorations and feeds support gain and query cost back to the planner. Under the matched top-1-label oracle, RLGPA reaches 61\% targeted ASR at sparsity 0.01 on CIFAR-10 (vs. 25\% SparseEvo, 0\% Pointwise), and 75.5\%/73.0\% on ResNet50/ViT at sparsity 0.005 (vs. 29.0\%/15.5\%). A fixed-probe test reduces median \(L_0\) from 165 to 23 after 40 images without any update. State-blind and state-shuffled controls degrade significantly, confirming that the learned policy uses attack state; the main gains come from state-conditioned executor scheduling and dynamic repartition. The source code is publicly available at https://github.com/Acui001/RLGPA.git.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06728

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

Shuai Dong, Kanghui Tian, Linghan Chen, Wenqi Shao, Hongrui Wu, Haowen Hou, Yongfu Zhu, Xuehui Wang 等 23 位作者

原文摘要

Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with existing approaches emphasizing reward design while retaining a single trajectory-level advantage across turns. Such shared credit can reinforce redundant replies after earlier successes and discourage useful follow-ups after earlier failures. We propose TurnWise, a turn-level GRPO framework that aligns learning with individual streaming decisions. TurnWise addresses the mismatch between trajectory-level feedback and turn-level interaction, promoting informative responses and reducing redundancy. Specifically, turn-level credit assignment uses silence-completed prefix scoring to construct group-relative advantages from each decision's remaining return, separating its learning signal from earlier rewards. Turn-mean policy optimization averages token losses within each turn and then across turns, giving response and waiting decisions equal weight regardless of output length. These complementary designs improve streaming policy learning without a learned critic or additional rollouts. Extensive experiments show our method outperforms prior RL approaches for streaming video understanding.

cs.CV · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06151

CARM: Conformal Adaptive Risk Masking for Reliable Scientific Super-Resolution

Guangtao Zhang, Haonan Wu, Junxuan Gao, Zhengyang Liu, Zhaoxi Zeng, Zhihao Li, Jianguo Huang, Zhiqiang Liu

原文摘要

Deep learning-based super-resolution (SR) can reconstruct fine-scale Earth-observation fields from coarse observations, but reconstruction accuracy alone does not provide a calibrated rule for identifying reliable spatial regions. Conformal Mask Calibration (CMC), built on conformal risk control, converts a spatial uncertainty score into a trust mask and controls the expected worst-case local distortion under exchangeability. However, its fixed threshold can become miscalibrated in Earth-observation streams affected by seasonality and episodic events. We propose $\textit{CARM}$ (Conformal Adaptive Risk Masking), a statistical framework for adaptive spatial risk control under temporal distribution shift. CARM maintains experts with heterogeneous update rates and aggregates their threshold proposals online using an asymmetric surrogate loss, balancing rapid adaptation to distribution changes against stability during relatively stationary periods. All updates are causal and use only mature feedback available after a fixed delay, allowing CARM to operate with any SR model that provides a spatial uncertainty score. We prove that the time-averaged mask-conditioned risk converges to at most $α$ at an $O(1/T)$ rate, without distributional assumptions and for any choice of aggregation weights across experts. On a daily South China Sea chlorophyll-$\textit{a}$ SR stream, CARM reduces the empirical violation rate from $43.49\%$ to $9.38\%$ and the moving-average exceedance frequency from $47.29\%$ to $1.22\%$ at $α=0.10$, while retaining a non-trivial trusted region. Experiments on ERA5 wind and OSTIA sea-surface temperature further show consistent relative improvements across multiple SR backbones.

cs.AI · cs.LG · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05828

Autonomy and Coordination in Intelligent Manufacturing: A Recursive Autonomous Agent Framework

Yuning Chen, Hongda Zhang, Linqiang Hu, Ziqing Zhou, Yi Liu, Zhao Huang, Ding Zhou, Haining Xu

原文摘要

Intelligent production requires systems to make decisions and organize work according to production goals and operating conditions. It also requires continuous adjustment through feedback. This paper analyzes intelligence in human production organizations from a complex adaptive systems (CAS) perspective. The analysis identifies two coupled mechanisms: individual autonomy and collective coordination. Individual autonomy enables actors to form local decisions using available information. Collective coordination aligns these decisions with shared goals and joint constraints. Learning and adaptation improve both mechanisms over time. A production-system model formalizes how local decision rules and coordination jointly form system decisions. On this basis, we propose the Recursive Autonomous Agent (RAA) framework, which combines goal-driven autonomous agents with a recursive organizational structure. Goal contracts define local objectives and operating boundaries, while capability contracts support the selection and composition of production units. Common interfaces allow coordinated groups to participate as units in larger organizations, connecting equipment, production lines, and factories. RAA thus provides an engineering approach to next-generation intelligent manufacturing, translating the requirements of intelligence, openness, and system-wide integration into mechanisms for autonomous and coordinated production.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.15284

Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning

Qiang Liu, Felix Koehler, Benjamin Holzschuh, Nils Thuerey

原文摘要

We introduce Tadpole, a novel foundation model for three-dimensional partial differential equations (PDEs) that addresses key challenges in transferability, scalability to high dimensionality, and multi-functionality. Tadpole is pre-trained as an autoencoder on synthetic 3D PDE data generated by an efficient online data-generation framework. This enables large-scale, diverse training without storage or I/O overhead, demonstrated by scaling to an equivalent of hundreds of terabytes of training data. By autoencoding single-channel spatial crops, Tadpole learns rich and transferable representations across heterogeneous physical systems with varying numbers of state variables and spatial resolutions. Although pre-trained solely as an autoencoder, Tadpole can be efficiently applied for multiple downstream tasks beyond reconstruction, including dynamics learning and generative modeling. For dynamics learning, we propose a novel parameter-efficient fine-tuning strategy that integrates low-rank adaptation, latent-space transformations, and reintroduced skip connections, achieving accurate temporal modeling with a minimal number of trainable parameters. Tadpole demonstrates strong fine-tuning performance across various downstream tasks, highlighting its versatility and effectiveness as a foundation model for 3D PDE learning. Source code and pre-trained weights of Tadpole are available at https://tum-pbs.github.io/tadpole/.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02774

DIKT: A Diagnostic and Interpretable Knowledge Tracing Framework for Prediction and Model-based Learning Analysis

Yi-Qiang Wu, Shaohui Chen, Hanlin Li, Baolin Yi

原文摘要

Knowledge tracing is a key component of intelligent educational systems. However, most existing methods mainly focus on response prediction, providing limited support for explaining predicted outcomes and improving students' learning states. This paper proposes Diagnostic and Interpretable Knowledge Tracing (DIKT), which integrates response prediction, skill-level diagnosis, and model-based learning analysis. DIKT generates bounded cognitive-state trajectories and decomposes the final response probability into skill-wise probabilities. The trajectories reveal students' evolving strengths and weaknesses, while the skill-wise probabilities identify the skills that most strongly constrain the prediction. Based on these diagnostic results, DIKT supports direct cognitive-state intervention and effective-learning-duration-based what-if analysis to examine how hypothetical adjustments affect current predictions and subsequent state evolution. DIKT combines Bayesian multi-head attention, conditional variational recurrent inference, a logistic-growth decoder, and multiplicative skill-wise prediction. Experiments on three benchmark datasets show that DIKT outperforms all evaluated baselines, with an average absolute AUC gain of 2.04 percentage points. Other experiments further demonstrate that DIKT supports educationally meaningful diagnostic analysis and provides informative diagnostic indicators for downstream applications, extending knowledge tracing from response prediction to interpretable diagnosis and model-based learning analysis.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.15786

DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation

Xinyue Xu, Jieqiang Sun, Jing, Dai, Siyuan Chen, Lanjie Ma, Ke Sun, Bin Zhao 等 12 位作者

原文摘要

A dexterous hand succeeds or fails through contact, yet every scalable record of human manipulation (video, vision-based hand tracking, motion capture) observes how the hand moves and misses how it pushes. We present DexCanvas, a hybrid real-synthetic dataset of 7,000 hours of dexterous hand-object interaction with per-frame contact points and contact forces, grown from 70 hours of optical motion capture that spans 21 manipulation types, from power and precision grasps to in-hand manipulation. The forces come from a real-to-sim pipeline: one reinforcement learning (RL) policy, conditioned on object geometry and manipulation type, drives an actuated MANO hand in physics simulation to reproduce each captured object trajectory, and the simulator measures the contacts that produce the reproduced motion. The policy reproduces 87.5% of the demonstrations and still succeeds on 80.9% of rollouts from perturbed initial object poses; these perturbed rollouts expand the 70 captured hours a hundredfold. On six YCB objects absent from the capture set it succeeds 72.5% of the time. The contact channels make better policies: a Diffusion Policy that observes DexCanvas contact features succeeds 82.2% of the time, against 67.5% without them, over 18,522 trials. Contact-driven retargeting carries the same demonstrations to two dexterous robot hands, where the RL stage again produces stable rollouts. A first release of 111,857 force-annotated trajectories is publicly available on Hugging Face.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2506.04235

A Comprehensive Benchmark of Computational Models for Antibody--Antigen Binding Affinity

Xinyan Zhao, Yi-Ching Tang, Victor J Cantu, Junseok Lee, Adam E Stogsdill, Ibraheem M Hamdi, Ashwin Kumar Ramesh, Zhiqiang An 等 10 位作者

原文摘要

Computational antibody design requires benchmarks that measure functional binding rather than similarity to natural sequences. Here we present AbBiBench, which treats the antibody--antigen complex as the evaluation unit and harmonizes 216,560 experimental measurements spanning 13 antibodies and 9 antigens. We compare 20 computational approaches without task-specific training or fine-tuning. The analyses show that global structure-conditioned inverse folding yields the strongest and most consistent affinity rankings, whereas antibody-specific fine-tuning does not consistently improve performance. Across models, rankings are more useful for prioritizing likely affinity gains than for excluding weak variants. In a subsequent case study, multi-objective evaluation of model-generated F045-092 CDR-H3 variants for H1N1 binding revealed a trade-off between predicted binding potential and evolutionary sequence plausibility; all 21 selected candidates produced H1-reactive ELISA signals. AbBiBench provides an open framework for developing and evaluating function-aware antibody design methods.

q-bio.QM · cs.AI · cs.CE · cs.LG · q-bio.BM

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.03016

DELTA: Robustly Training Label-Conditional Diffusion Models with Weak Annotations

Dong-Dong Wu, Jiacheng Cui, Wei Wang, Zhiqiang Shen, Masashi Sugiyama

原文摘要

While label-conditional diffusion models have recently exhibited remarkable generative capabilities, their success heavily relies on massive, cleanly labeled datasets. In practice, categorical supervision is rarely perfect: it is often corrupted by noise, clouded by ambiguity, or partially missing. Training directly on such weak annotations severely degrades generation quality, and existing robust methods offer only fragmented solutions that depend on scarce auxiliary priors. To overcome these limitations, we propose DELTA, a unified framework that robustly trains Diffusion modELs across all three weak annoTAtion types. By treating the unknown true label as a latent variable, DELTA optimizes a principled variational objective that jointly recovers the clean data distribution and infers the true label posteriors. To make this joint training computationally tractable, we further introduce a median-centered timestep sampling strategy that efficiently concentrates estimation where the diffusion process is most informative. Extensive experiments on synthetic and real-world benchmarks demonstrate that DELTA produces high-fidelity, class-consistent samples across diverse weak supervision scenarios, outperforming specialized baselines while demanding strictly less prior knowledge.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.40726

Li$^{2}$SAO: Lifting Light Single-Rollout Asynchronous RL Optimization via Group-Relative Actor-Critic Bootstrapping

Zichen Bai, Yanli Wang, Yang Liu, Junhao Shi, Xueqin Liu, Jinguo Sun, Muye Li, Shaoqiang Zheng 等 12 位作者

原文摘要

Asynchronous reinforcement learning (RL) is becoming a mainstream paradigm for post-training large language models (LLMs), as it improves training efficiency by updating the model as rollouts arrive. Recent work argues that group-wise sampling in GRPO does not naturally fit asynchronous RL training because rollout lengths follow a long-tailed distribution, and proposes Single-rollout Asynchronous Optimization (SAO) to improve stability and off-policy behavior, especially on agentic tasks. However, SAO relies on a closed-source value model obtained from scaling value pretraining. In this paper, we analyze GRPO and LiSAO, our lightweight reproduction of SAO without the pretrained value model, on single-turn reasoning and multi-turn agentic tasks. We find that GRPO outperforms LiSAO on reasoning tasks, while the reverse holds on agentic tasks. Since the value model of LiSAO is not yet well trained , LiSAO lags behind GRPO substantially in early training steps. To address this issue, we propose Li$^{2}$SAO, which Lifts Light Single-rollout Asynchronous Optimization with group-relative actor-critic bootstrapping: while the critic is cold, a group-relative advantage trains the actor and a group-centered return trains the critic, after which training switches to single-rollout GAE. Experiments show that Li$^{2}$SAO catches up with or surpasses GRPO in early training and further raises the later performance ceiling. Code is available at https://github.com/jd-cc-coder/Li2SAO.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.09737

Mosquito acoustic identification at unseen recording sites: practical limits of common transfer remedies for vector surveillance

Yucheng Gong, Rui Zhou, Binbin Zeng, Qiang Ren, Hongjin Hui

原文摘要

Passive acoustic monitoring could widen mosquito surveillance, but a classifier trained under one set of recording conditions often fails when moved to a new site, device or enclosure. On a nine-species, five-condition corpus of about 271,000 recordings, the published baseline identifies species at 0.881 balanced accuracy under conditions it has seen and 0.175 under held-out ones. Using that corpus's leave-domain protocol, we asked which transfer strategy is most reliable when a program brings a new site online. Using fixed features from a pre-trained bioacoustic model and a small classifier improved held-out-condition balanced accuracy to 0.305, without updating backbone weights and in minutes of training per site. Four widely used additions did not improve transfer: rebalancing training across recording conditions, fine-tuning the backbone and fusing a weaker second modality each reduced accuracy, and a six-term objective reduced to a single alignment term. Rebalancing reversed direction across four encoders, helping weak representations and harming strong ones. Genus-level aggregation was more accurate than species-level classification (about 0.50 against 0.30), suggesting genus-level screening may be the more realistic operating point here. These results come from one corpus under one protocol, and are dataset-bounded guidance rather than validated general rules.

eess.AS · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01677

Xiaomi Auto World Model 2.0: Causal World Models for Real-World Driving and Embodied Intelligence

Zhenxin Zhu, Zhijian Huang, Cheng Chi, Yuru Wang, Jianhua Wu, Jiayi Guan, Yonggang Li, Mingfei Tu 等 23 位作者

原文摘要

We present Xiaomi Auto World Model 2.0, a unified streaming causal world model for Physical AI. It models and generates causal physical evolution in the real world, and unifies heterogeneous conditioning inputs for view-consistent generation. The architecture integrates View-Temporal Attention (VTA) to capture cross-view spatial dependencies and temporal dynamics, together with Multi-view Rotary Position Encoding (RoPE) to encode positional relationships across views and time. WorldRec 2.0 reconstructs static and dynamic 3D Gaussians from multi-view, multi-temporal observations in a single forward pass and uses their renderings as explicit scene context to preserve geometry and appearance during long-horizon generation. Conditioning inputs are fused through VAE latent concatenation in a shared representation space. We incorporate Gated Linear Attention (GLA) into the temporal layers of VTA for efficient streaming inference, reducing computation and KV-cache memory during multi-view rollouts. A physical-interaction data pipeline covers diverse interactions and long-tailed events. From Pre-train onward, these data are combined with large-scale videos and heterogeneous visual modalities to learn visual, geometric, and dynamic priors. During Mid-train, training across diverse view configurations further improves the model's ability to capture how actions and object states shape subsequent scene evolution. After distillation-based Post-train, we apply the model to closed-loop simulation, closed-loop training, and World Action Model (WAM) applications. These applications generate physically consistent future states and support world-state prediction, policy learning, and action generation for Physical AI.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗