跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+979新增论文
+781其中 AI 相关
+119已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 23:01 — 2026-11-20 23:01(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:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58库内论文最新更新时间:2026-11-20 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。

28,961 已收录论文24,030 AI 相关8,912 有修订112 HF 社区发现

浏览论文库

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 50 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
版本更新 · v2arXiv:2611.15073

When Does Causality Help in Multivariate Time-Series Anomaly Detection?

Long Zhang, Wei Huang, Aishui Rao, Jian Hu, Binxiang Wu, Jie Li, Chen Gong, Linxi Feng

原文摘要

Causality-aware scoring is common in multivariate time-series anomaly detection, yet the literature rarely states when it helps. Holding one causality-guided autoencoder (DeCauAE) fixed, we vary graph quality, anomaly type and protocol against ground truth. Graph quality fixes the payoff: on a twenty-variable DAG the gain over a graph-free autoencoder decays as the graph is corrupted. Anomaly type fixes the target: the structural factor lifts window F1 from 0.800 to 0.976 where anomalies break conditional structure, and its advantage vanishes below a break severity s 0.3. Protocol fixes the ranking: point-adjusted F1 lets a random score match the full model, while range-aware VUS separates the autoencoder family from the classical baselines. On real benchmarks the causal module pays only where density makes a system eligible and cross-subsample reproducibility selects entities inside it; enabling it everywhere costs 0.012 VUS-ROC. The structural factor also transfers to classical detectors .

cs.LG

新论文 · v1arXiv:2611.25452

FamilySpace: From Emergent Chemical Semantics to Controllable Crystal Generation

Haowei Hua, Irwin King, Wanyu Lin

原文摘要

Latent crystal generative models typically combine a variational autoencoder (VAE) for learning atom-wise representations with a flow model that transports a simple source distribution to the learned latent distribution. However, previous studies have mainly focused on the quality of generated crystals, leaving the structure and generative utility of the atom-wise latent space largely unexplored. In this work, we show that even a vanilla crystal VAE implicitly organizes atom-wise latent representations according to elemental families, with different families occupying largely separated regions of the latent space. We term this phenomenon emergent chemical semantics. This structure suggests that sampling from a family-specific latent region can bias the decoder toward atoms from the corresponding elemental family. Building on this insight, we propose FamilySpace, a framework for controlling the elemental-family composition of generated crystals. FamilySpace assigns each elemental family a distinct source component, forming a family-indexed multi-source distribution, and trains a flow model using source-target pairs matched by family. In inference, a user-specified family template selects the source component for each atom-wise representation, enabling direct control over the family composition of generated crystals. Experiments on MP-20 and MPTS-52 show that FamilySpace achieves competitive crystal-generation performance while matching prescribed elemental-family compositions. Moreover, selected family templates increase the fraction of generated crystals predicted to be stable or metastable, demonstrating that latent-space composition control can support targeted exploration of promising chemical regions without additional optimization techniques such as reinforcement learning. Code is available at https://github.com/hhw11/FamilySpace

cs.LG · cond-mat.mtrl-sci

新论文 · v1arXiv:2611.25429

Evolve Where It Matters: Coverage-Guided Self-Evolution of Agent Skills

Boyin Tan, Jiadong Zhang, Xiaosong Ma, Chun Jason Xue, Xiaowei Huang, Youcheng Sun

原文摘要

Agent skills package procedural knowledge as natural-language instructions, and a skill helps only when its instructions are correct and properly followed by the agent. Self-evolving agents revise their own skills from the runs they make, but existing methods judge each run as a whole, by its outcome or by where it went wrong, and cannot tell whether a failure comes from a wrong instruction or from one the agent did not follow. Instruction-level coverage was introduced to test skills and labels each instruction of a run as follow, not-follow, or not covered, which separates these causes. We leverage it for skill self-evolution with SkillPlumber, a framework in which an agent evolves its own skills where coverage shows they fall short. A persistent root cause analysis agent turns each label into a revision question and checks each revision against the next run, while a maintainer distills investigations across tasks into a shared strategy library. Across three benchmarks and three executors, SkillPlumber solves 64.7% to 70.5% of the tasks, 25.6 to 30.4 percentage points higher than the initial skill and 8.7 to 14.0 percentage points higher than the strongest baseline, and removing coverage reduces recovered failures by 20.8% on SkillsBench with GPT-5.5.

cs.CL · cs.AI

新论文 · v1arXiv:2611.24084

From Restoration to Redrawing: Revitalizing Ancient Chinese Characters by SVG Code Generation and Editing

Weiguang Zhang, Linhua Dong, Bin Dong, Shanshan Jiang, Maizhen Ning, Xiaoqiang Kang, Kun Zhang, Hao Xu 等 12 位作者

原文摘要

Hanjian manuscripts written on Han Dynasty bamboo and wooden slips are invaluable heritage of ancient Chinese writing but suffer from damaged ink and incomplete strokes. Existing image-to-image restoration methods may alter observed strokes and offer limited control over stroke geometry. Inspired by experts' manual redrawing practices, we address these issues by introducing \textbf{ReDraw}, a two-stage vision-language model(VLM) that reformulates character restoration as Scalable Vector Graphics(SVG) code generation and editing. Stage one targets faithful vectorization of observed strokes geometry or conservative tracing of mildly degraded strokes. Guided by skeleton chain-of-thought reasoning and reinforcement learning with structure-aware rewards, stage two predicts skeletons before contours to redraw severely incomplete strokes by appending paths while keeping existing SVG paths unchanged. To support training, we develop a multi-layer data synthesis pipeline that disentangles ink, material, and degradation to generate 1.2M samples, and derive up to 6,400 adaptation pairs from 320 annotated real glyphs. Experiments demonstrate synthetic restoration performance and adaptability to real Hanjian glyphs. Code and demo will be available upon acceptance.

cs.CV

版本更新 · v2arXiv:2609.34335

SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Enhancement

Yanwei Huang, Mingxuan Zhu, Shujie Li, Shiyuan Liu, Yuanxing Zhang, Arpit Narechania

原文摘要

Achieving high-quality cinematic text-to-video generation remains challenging for non-experts, whose prompts often lack professional narrative and creative design. Existing prompt enhancement (PE) methods and static cinematic skills offer limited capabilities for exploring diverse creative realizations. We propose SkillPE, a creativity-oriented PE framework that systematically evolves reusable cinematic skills through reference-guided exploration. Starting from expert-provided cinematic knowledge, SkillPE initializes and normalizes 20 structured seed skills. It then retrieves movie references categorized as resonators (good matches), dissonants (weak matches), and divergents (creatively inspiring near-misses). Resonators and dissonants refine skill applicability and execution, while divergents inspire alternative cinematic realizations through controlled mutations that preserve user intent. Candidate skills are assessed through generated videos along prompt fidelity, cinematic quality, narrative appeal, and creativity to construct the final skill libraries. Experiments on StoryEval and VBench demonstrate improvements of up to 1.10 points over seed skills and 1.02 points over the strongest external baseline on a 7-point four-dimensional evaluation scale. Overall, SkillPE offers a practical approach to balancing fidelity and creativity in cinematic text-to-video generation.

cs.CV · cs.AI

新论文 · v1arXiv:2611.22700

EM-SDTrack: Efficient Multi-Scale Spike-driven Tracking for Event Cameras

Yimeng Shan, Haodi Wu, Wei Zheng, Xiaowei Ye, Shuai Wang, Yu Liang, Wei Hua, Chenxiao Dou 等 9 位作者

原文摘要

Event-driven spiking neural networks (SNNs) match the sparse spatiotemporal output of event cameras, making spike-driven trackers highly attractive for neuromorphic edge deployment. However, events reveal a target only through their spatial distribution, whose extent varies more than tenfold within one sequence. Event tracking therefore demands multi-scale representation, which existing spike-driven trackers lack. Transferring multi-scale schemes from artificial neural networks either breaks spike-driven inference with floating-point multiplication or repeats backbone computation across input scales. To address this, we propose Spike-driven Multi-Scale Interaction (SDMI), which performs cross-scale interaction in a single spiking forward pass. Its core, Dyadic Spike Sampling (DSS), restricts sampling coordinates to dyadic fractions and thus requires only shifts and additions. The resulting M-SDTrack is fully spike-driven at inference. For tighter edge budgets, we further propose Polarity-Privileged Distillation (PPD), which distils M-SDTrack into EM-SDTrack. PPD treats the event counts cancelled by the voxel representation as privileged information. Its core constraint, Polarity-Guided Curvature Distillation (PGCD), aligns the curvature of the template-search relation under polarity-guided perturbations. On FE108, FELT and VisEvent, M-SDTrack achieves state-of-the-art accuracy with an AUC of 65.1, 41.7 and 42.0. EM-SDTrack retains 99% of the accuracy of its teacher M-SDTrack-Tiny with 27% of its energy and 18% of its parameters. On the Lynxi KA200 neuromorphic chip, it runs losslessly in real time at 116 FPS and 0.12 W.

cs.NE

新论文 · v1arXiv:2611.21235

Language-model agents' beliefs can be manipulated via truthful evidence in open channel

Jinwei Hu, Qisong He, Xinmiao Huang, Youcheng Sun, Yi Dong, Xiaowei Huang

原文摘要

Language-model agents' beliefs can be manipulated through open channels such as social media, even when the information they receive is truthful. When agents fill gaps between fragments with self-induced relationships, they may accept those relationships as established facts and pass the resulting rumours to others. Drawing on cognitive theory of narrative understanding and film theory of montage, we introduce Generative Montage to operationalize this failure, termed narrative overfitting, by coordinating agents to arrange truthful fragments into misleading narratives. Across 1,090 rumour targets from six Twitter events, agents often accepted rumours overconfidently, with overall acceptance exceeding 65 percent in twelve of fourteen models. Acceptance remained above 50 percent after majority voting or review of the same evidence, showing how errors can reach downstream decisions. To explain this susceptibility, fragment interventions identify posts that influence belief within complete narratives. Synthetic controls then show that similar response patterns arise from valid evidence, separating belief influence from evidential support. This distinction motivates Grounded Monitor, a proof-of-concept neuro-symbolic runtime monitor that checks direct evidential support to guide agents' judgements, improving decision accuracy by 5.6 to 29.0 percentage points across original and anonymized settings. These findings expose a cognitive route to rumour amplification and support monitoring inferred relationships before agent-generated conclusions guide public decisions.

cs.AI · cs.CL · cs.MA · cs.SI

新论文 · v1arXiv:2611.19861

HBF-EventLab: A Discrete-Event Simulator for Studying Host-Device Coordination in High Bandwidth Flash

Ziqing Mei, Yiwei Huang, Zhiyi Zeng, Yuhao Xiao, Pu Pang, Quan Chen, Deze Zeng, Minyi Guo

原文摘要

High Bandwidth Flash (HBF) combines NAND flash density with high-bandwidth accelerator connectivity, offering additional memory capacity for large language model inference. However, limited hardware availability makes it difficult to evaluate how host behavior and device resource constraints jointly affect HBF request processing. We present HBF-EventLab, an open-source, transaction-level discrete-event simulator based on the Open Compute Project HBF specification. HBF-EventLab connects host request dispatch, command admission, fragmented write assembly, read dispatch, NAND execution, and completion feedback within a shared event loop. It explicitly models distinct resource lifetimes and separates configurable scheduling policies from ordering and resource constraints, enabling controlled exploration of host-device coordination. Experiments show how resource limits, address interleaving, fragment arrival patterns, and scheduling policies affect write completion and request latency. The results highlight the need to consider resource limits and scheduling policies jointly, accounting for their interactions with write assembly and read eligibility. We also integrate HBF-EventLab with real GPU execution of Qwen3-0.6B, combining profiled GPU activity durations with simulated weight-access delays to estimate time to first token and time per output token, with logits and output tokens remaining bitwise identical to those from native GPU execution. HBF-EventLab provides a configurable foundation for studying HBF mechanisms, exploring scheduling policies, and assessing how HBF access delays affect application-level timing. The source code is publicly available at https://github.com/sjtu-epcc/HBF-EventLab.

cs.AR · cs.ET

版本更新 · v3arXiv:2602.12683

Flow Matching from Viewpoint of Proximal Operators

Kenji Fukumizu, Wei Huang, Han Bao, Shuntuo Xu, Nisha Chandramoorthy

原文摘要

We discuss the dynamics of Optimal Transport Conditional Flow Matching (OT-CFM) under the manifold hypothesis, where the support of the target distribution is a low dimensional manifold. We first derive an exact proximal expression of the vector field, using an extended Brenier potential for the OT; the vector field can be expressed by a denoiser, which is presented as the proximal operator associated with the potential function. Based on this explicit proximal form of the vector field, we analyze the manifold stability for perturbations to initial points, using the Lyapunov exponents of the dynamics. By analyzing the local behavior with the tools in convex analysis, we show that the dynamics contract linearly in the perturbation of the normal directions to the manifold, while perturbations in the tangential directions are preserved; this implies the stability of the manifold structure to the perturbations. To justify the theoretical arguments on the population OT, we also establish the convergence of minibatch OT-CFM with neural network learning to population OT-CFM under regularity and stability assumptions, with rate exponents governed by the intrinsic dimension of the data manifold. Experiments on synthetic data, MNIST, and CIFAR-10 support the predicted geometric behavior.

cs.LG · stat.ML

新论文 · v1arXiv:2611.17866

Active Learning of Temporal Specifications through Distinguishing Queries

Rajarshi Roy, Xiaowei Huang

原文摘要

Temporal specifications are essential for verification and monitoring, yet writing formulas that capture the intended behaviour is difficult. Active learning derives such specifications through interaction between a learner and a teacher, but remains underexplored for temporal logics. Existing approaches require the teacher to answer equivalence queries and to construct counterexamples, and they often rely on SAT-based learning procedures that restart the search after each new example. We present an active-learning framework for LTLf in which the teacher only labels traces and answers natural-language questions about the intended behaviour. The learner maintains an enumerated version space of candidate formulas, generates traces that distinguish candidates, and uses the teacher's hints to rank candidates or to restrict the search. We prove consistency with the observed examples, identification within bounded hypothesis classes with a bound on the number of queries, and a PAC guarantee for the final hypothesis. In experiments with a simulated teacher on 36 targets, including targets in four standard environments, the learner identifies every target when it compares all rivals, with fewer than seven queries beyond an initial sample of ten traces on average. Correct hints reduce the number of queries by up to 16% and the number of generated candidates by a fifth, and hints used for ranking never prevent identification, even when incorrect. Our enumeration-based version space is faster than the SAT-based approach of previous learners at every target size.

cs.LO · cs.AI

版本更新 · v3arXiv:2607.12753

RFMSR: Residual Flow Matching for Image Super-Resolution

Shuwei Huang, Tianyao Luo, Jicheng Liu

原文摘要

Generative image super-resolution (ISR) methods typically sample from a standard Gaussian prior and transport the sample to the data distribution, where the low-quality (LQ) input serves only as an external condition. However, the LQ image already carries rich structural information about the target high-quality (HQ) image, which makes a distribution approximating the LQ image a more suitable starting point, an idea that has been validated by a series of diffusion-based restoration methods. In contrast, recent flow-matching-based ISR methods still adopt the standard Gaussian prior and thereby discard such structural priors; moreover, existing single-step acceleration techniques, such as distillation and consistency training, either depend on an additional teacher or sacrifice the model's multi-step inference capability. In this paper, we propose Residual Flow Matching for Image Super-Resolution (RFMSR), which defines the source distribution as a Gaussian centered at the LQ latent, so that the flow starts from the LQ image rather than from pure noise and preserves the structural priors already present in the input. To achieve high-quality single-step generation, we further propose a simple yet effective training strategy that combines the supervision loss on the single-step output with the conditional flow matching (CFM) loss, enabling high-quality restoration with an arbitrary number of steps without resorting to distillation or other acceleration techniques. Extensive experiments show that RFMSR achieves competitive results against state-of-the-art methods. The source code is available at https://github.com/Faze-Hsw/RFMSR.

cs.CV

新论文 · v1arXiv:2611.17722

Federated Soft Poly-Level Learning Over a Distributed Network with Guaranteed Convergence

Yang Jiao, Kai Yang, Jianwei Huang

原文摘要

Multi-level learning/optimization, e.g., bilevel optimization, has been recognized for its versatile applicability across a broad array of domains, spanning from signal processing to machine learning. However, most existing works focus on bilevel and trilevel optimization. In contrast, multi-level optimization problems involving four or more hierarchical levels, which we term poly-level learning (PLL) problems, remain largely unexplored.In addition, in practical PLL, data may be distributed across multiple nodes over a distributed network. Nevertheless, extant studies on PLL predominantly focus on the non-federated setting, necessitating the collection of data to central servers and thereby posing potential privacy risks. To this end, we propose a Federated Poly-Level Learning (FPLL) framework over a distributed network to tackle the PLL problems with soft constraints in a federated manner. FPLL hinges on a novel non-linear cut, i.e., $L$-cut, for the level-wise relaxation to the PLL problems. Additionally, the proposed federated algorithm is designed with adjustable parameters that allow for a flexible trade-off between its computational complexity and performance efficiency, enabling users to tune it according to specific application requirements. We also carry out non-asymptotic analysis to derive the iteration complexity for the proposed FPLL to achieve the $ε$-Pareto stationary point. Extensive experiments have been undertaken to elucidate the superior efficacy of the proposed method.

cs.AI

新论文 · v1arXiv:2611.16188

PERA: Plug-in Experts for Robotic Actions in Continual Whole-Body Control

Shangchao Hu, Yadan Sun, Xibo Yu, Wei Huang

原文摘要

Motion imitation enables humanoid robots to acquire whole-body skills such as walking and dancing. However, fine-tuning an entire policy for a new skill can affect existing behaviors, while training a separate policy for each skill increases training and maintenance costs. We present PERA, a method for learning new skills by reusing existing motion capabilities. PERA freezes a pretrained mixture-of-experts policy and trains an additional task expert and its routing score using task rewards or teacher-action supervision. In Unitree G1 simulation, each added task module contains approximately 1.03% of the parameters of the base actor. Built on our pretrained policy, PERA successfully completes all ten new tasks. Disabling the expert restores the original computation path of the base policy, which still fully executes all 126 original motions. Enabling the expert also improves the execution of some dance motions not used to train that expert, indicating that its benefits extend beyond its training motions. Experiments with HoloMotion further demonstrate the applicability of PERA to different base policies.

cs.RO

版本更新 · v2arXiv:2611.13711

Hint, Not Hole: Localization-Robust Video Overlay Removal

Dongyang Zhang, Wei Zhang, Renjie Zou, Zhiwei Huang

原文摘要

Video overlay removal recovers the scene beneath burned-in subtitles, karaoke lyrics, titles, credits, logos and watermarks. Generative video models now fill a known region convincingly, but in practice the region comes from a detector or a segmenter, and it is wrong in both directions: it misses strokes, halos, whole frames and whole objects, and it covers background between characters, around boxes and on genuine scene text. Erasers that treat the mask as a hole, regenerating inside and copying outside, inherit every one of these errors. We present HintErase, which treats localization as a hint, not a hole. The model sees the full, unmasked video together with a hint channel; during training the hint is corrupted the way real localizers fail, while supervision follows the true overlay. The result is a single model that removes overlay the hint missed, keeps background the hint wrongly covered, and is trained to keep genuine scene text even when the hint lands on it. For full-length releases, a streaming pipeline handles interlaced sources, shot cuts, missed and jittering hints, paste-back and audio, with memory independent of the length of the video. This report describes the approach, the pipeline that turns it into full-length deliveries, and qualitative results; video results, with input, hint and output side by side, are on the project page.

cs.CV

版本更新 · v5arXiv:2607.04171

XS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning

Iok Tong Lei, Ying Jie Yap, Wei Huang, Qingchen Xie, Qianzhi Li, Yujie Zhang, Xiaolong Liu, Zhidong Deng

原文摘要

How can richer training supervision improve robot control while keeping the deployed policy compact? We present XS-VLA, a staged training framework using teacher-derived spatial labels and demonstration-conditioned action learning. Coarse-Grained Spatial Distillation (CSD) initializes the backbone through an auxiliary region-label task. Latent Flow Matching (LFM) then conditions an action-space velocity field on a demonstration latent, using KL regularization while jointly optimizing the backbone and action modules. The deployed policy contains 243.99M parameters and operates without the teacher or posterior encoder. XS-VLA achieves 90.25% average LIBERO success in each of two training seeds, compared with 86.00% for a SmolVLA-0.25B base trained under our settings. Ablations examine both training stages through matched image pretraining and Huber/MSE controls. On three Mobile ALOHA tasks, average strict success increases from 21.7% to 65.0%. These results demonstrate the control utility of auxiliary representation initialization and regularized demonstration-conditioned flow learning for compact VLA policies

cs.RO · cs.LG

版本更新 · v2arXiv:2606.29623

SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings

Yingjie Wang, Yi Dong, Edmund Lau, Jie Meng, Taylor T Johnson, Xiaowei Huang

原文摘要

Rare events govern the safety profile of modern AI systems, yet their probabilities are extremely difficult to estimate: direct Monte Carlo requires prohibitive sample budgets. Subset Simulation (SS) addresses this by decomposing a rare-event probability into moderate conditional probabilities over nested intermediate events. However, classical SS requires a handcrafted scalar performance function whose sublevel sets define those events, demanding detailed knowledge of the failure geometry and limiting transfer to new domains. We propose SCARCE (Scalable Cascade Analysis for Rare-event Characterisation via Embeddings), which replaces the performance function with learned latent representations and geometric rulers that score proximity to failure regions. Adaptive thresholding constructs nested intermediate events directly from data. We formalise SCARCE through a non-negative supermartingale, yielding a high-probability upper envelope that remains valid under early stopping. On MNIST misclassification, where dense Monte Carlo provides ground truth, SCARCE achieves approximately 400--500 times lower mean absolute error than grid-searched traditional SS while eliminating systematic over-counting. We then study PAIR-style LLM jailbreaks under a fleet-level threat model with adversarial fraction $η$. On Llama-Guard-3-8B hidden states, a PCA-based ruler attains 2.6% mean relative error for $η\geq 10^{-3}$ against finite-sample references whose average bootstrap relative half-width is 27.9%, and transfers to a GCG-style corpus with 2.93% relative error after recalibration. A directional criterion $\mathrm{KL}(p_{\mathrm{good}}\,\|\,p_{\mathrm{bad}})$ ranks rulers consistently with estimation error (Spearman $ρ=0.83$).

cs.AI · cs.LG

版本更新 · v4arXiv:2604.24357

DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Discrete Diffusion Models

Dake Bu, Wei Huang, Andi Han, Si Wu, Hau-San Wong, Qingfu Zhang, Taiji Suzuki, Atsushi Nitanda

原文摘要

Discrete diffusion models admit many token orders, yet most systems rely on confidence-based decoding. Confidence is a strong and efficient heuristic, but it can be myopic because local certainty does not measure a position's effect on terminal quality. We introduce DPRM (Doob h-transform Process Reward Model), a plug-in token-ordering module induced by a terminal-reward-tilted trajectory distribution. The Doob transform converts terminal reward into a process reward for each candidate position. A compact estimator indexed by generation progress, confidence, and optional positional or task state makes this correction reusable across partial states. DPRM changes only token order; the host architecture, denoising objective, supervision, and token sampler remain fixed. We derive the exact reward-tilted law and bound its shortlist and online approximations. Across nine recent open-source hosts spanning language, multimodal generation, and scientific sequences, DPRM improves reasoning, numeric VQA, visual-codebook ordering, and preference-conditioned generation. Relative to confidence, it improves PUMA GSM8K by 14.6%, Omni-Diffusion CLIP-L/14 by 13.2%, Prism voted accuracy from 82.41% to 83.85%, and RealWorldQA numeric/count accuracy by 8.97 points. Matched scientific gains include 8.3% in DCM nonzero recovery, 15.0% in GenMol QED, and 53.3% in SDPO-DNA total utility. Entropy and random-order controls show that the gains do not come from favoring uncertain tokens indiscriminately. Token-order traces and shared-state interventions instead show how terminal reward can correct a locally confident but globally poor choice. Code is available at: https://github.com/DakeBU/DPRM-DLLM.

cs.LG · cs.AI

新论文 · v1arXiv:2611.11977

MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing

Hang Yi, Ziwei Huang, Yining Ma, Zhiguang Cao

原文摘要

Neural Combinatorial Optimization (NCO) is a promising paradigm for solving routing problems, yet its generalization across diverse data distributions remains a critical bottleneck. Existing methods typically tackle cross-distribution generalization through complex multi-distribution training or intricate meta-learning schemes, implicitly presuming that single-distribution training yields a weak zero-shot baseline. In this paper, we demonstrate that the potential of single-distribution training has been substantially underestimated and can be unlocked by a simple architectural inductive bias: Mix Normalization. To approach this, we first construct a comprehensive benchmark spanning three representative routing problems and 179 fine-grained datasets, capturing diverse shifts in node coordinates, customer demands, capacity and time windows. Building on this benchmark, we propose MixRoute, a neural framework that adaptively combines normalization statistics at different granularities to mitigate varying distribution shifts. Trained exclusively on uniform distributions, MixRoute generalizes effectively to a wide range of unseen distributions without any distribution-specific adaptation. Extensive experiments demonstrate that MixRoute consistently achieves state-of-the-art zero-shot generalization. Our work revisits normalization as a parsimonious alternative for zero-shot generalization against complex training-adaptation schemes.

cs.LG · cs.AI

新论文 · v1arXiv:2611.11914

CRAFT-GBM: Selecting Best Features for Gradient-Boosted Machine Learning

Basil Kuok, Yi Zhou, Yao Xuan, Shuping Li, Ke-Wei Huang

原文摘要

Feature subsampling is used to accelerate gradient-boosted trees, yet standard approaches fix the feature count in advance and largely ignore the split-gain evidence accumulated during training. We introduce CRAFT-GBM (Confidence-Ranked Adaptive Feature Tracking), a native LightGBM extension that uses this evidence to adapt which---and, by default, how many---features are searched each boosting round. CRAFT-GBM transforms root-split gains into bounded observations and constructs joint time-uniform bounds valid under adaptive, non-stationary training histories. In its default endogenous mode, after initialization, CRAFT-GBM retains exactly the features that cannot yet be ruled out as best, letting the selected feature-set size $K_t$ emerge from training history rather than a pre-specified fraction. With probability at least $1-δ$, every feature with the largest expected gain is retained jointly across all rounds after initialization. When a feature fraction $f$ is specified instead, CRAFT-GBM ranks features by their interval point estimates and provides an approximate top-$K$ guarantee for feature budget $K_f$. We implement CRAFT-GBM within LightGBM while preserving its native feature-bundling representation, and evaluate it across 14 public and synthetic dataset families and four noise-augmented settings. In the fully endogenous setting, CRAFT-GBM reduces per-fit training time by 39.74\% with 1.04\% lower test loss in the geometric mean across all 18 RQ1 experiments. Under pre-specified feature fraction $f$, Exogenous CRAFT-GBM also yields aggregate training-time reductions up to 13.52 percentage points larger than random feature subsampling, with no increase in aggregate test loss relative to full-feature LightGBM. Accumulated training evidence can thus support adaptive feature search with statistical guarantees while retaining the practical advantages of native gradient boosting.

cs.LG · math.ST

版本更新 · v4arXiv:2510.12026

Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning

Junsoo Oh, Wei Huang, Taiji Suzuki

原文摘要

Mamba, a recently proposed linear-time sequence model, has attracted significant attention for its computational efficiency and strong empirical performance. However, a rigorous theoretical understanding of its underlying mechanisms remains limited. In this work, we provide a theoretical analysis of Mamba's in-context learning (ICL) capability by focusing on tasks defined by low-dimensional nonlinear target functions. Specifically, we study in-context learning of a single-index model $y \approx g_*(\langle \boldsymbolβ, \boldsymbol{x} \rangle)$, which depends on only a single relevant direction $\boldsymbolβ$, referred to as feature. We prove that Mamba, pretrained by gradient-based methods, can achieve efficient ICL via test-time feature learning, extracting the relevant direction directly from context examples. Consequently, we establish a test-time sample complexity that improves upon linear Transformers -- analyzed to behave like kernel methods -- and is comparable to nonlinear Transformers, which have been shown to surpass the Correlational Statistical Query (CSQ) lower bound and achieve near information-theoretically optimal rate in previous works. Our analysis reveals the crucial role of the nonlinear gating mechanism in Mamba for feature extraction, highlighting it as the fundamental driver behind Mamba's ability to achieve both computational efficiency and high performance.

cs.LG · stat.ML

新论文 · v1arXiv:2611.11210

DynOLAT: OLAT Video Prediction for Controllable Dynamic Full-Body Relighting

Taoming Liu, Yinji ShenTu, Guangzhao He, Yudong Jin, Yukang Ye, Siyu Zhang, Fan Jia, Wei Hua 等 10 位作者

原文摘要

Accurate lighting response is essential for realistic dynamic human relighting, because shadows, highlights, and color changes should follow the target illumination in both direction and relative strength. Current learning-based relighting methods can generate visually plausible videos, but they often exhibit imprecise lighting responses: shadows and highlights may drift away from the target direction, and the output brightness may not faithfully follow the relative intensities in the target environment, making the result closer to appearance harmonization than controllable relighting. To address this issue, we propose DynOLAT, a generalizable OLAT video prediction framework for dynamic full-body humans. Instead of directly synthesizing a single relit appearance, our method predicts temporally consistent One-Light-At-a-Time (OLAT) basis videos from flat-lit inputs, and then linearly combines the predicted bases according to the target environment map. This OLAT-based formulation makes the directional response explicit in the predicted bases, while the relative lighting strength is determined by the linear weights derived from the environment map. We further introduce a dynamic capture pipeline and the first large-scale dynamic full-body OLAT dataset, comprising over 24 million frames from 224 identity-outfit combinations, where different outfits of the same person define separate combinations. Experiments show that DynOLAT responds more faithfully to variations in target lighting direction and relative intensity than the tested baselines, enabling controllable video relighting while preserving fine appearance details and temporal coherence. The dataset and processing tools will be publicly released to foster future research.

cs.CV

新论文 · v1arXiv:2611.11125

LongCap: Hour-Scale Timestamped Audio Captioning via Chunk-wise Processing

Jinchuan Tian, Sen Chen, Wenbin Huang, Chao Weng, Zhengwei Huang, Jiatong Shi, Yichen Lu, Haoran Wang 等 10 位作者

原文摘要

Describing hours of audio requires accurate event timing and sustained descriptive detail throughout the recording. We present LongCap, a framework for timestamped audio captioning (TAC), with the human-annotated LongCapBench and three diarization-inspired metrics: Timeline Error Rate (TER), Granularity Error Rate (GER), and Caption Similarity (tcpCapSim). LongCap interleaves audio chunks with structured event captions, using relative timestamps and retained context to support length extrapolation within a 1M-token inference context window. Event-level reannotation restores caption detail, while systematic studies examine model scaling, dependency supervision, and self-distillation. LongCap-Diar achieves strong benchmark results and extrapolates to 16 hours of concatenated audio despite training on recordings no longer than 40 minutes. Our TAC models are competitive with Qwen3.5-Omni-Plus on short clips, outperform evaluated baselines in caption similarity and timeline accuracy in segment-level comparisons on LongCapBench-TAC-Long, and caption full recordings approaching two hours. On LongCapBench-TAC, 9B and 35B-A3B offer favorable size-performance tradeoffs, while 122B-A10B substantially improves event-dependency recovery. These findings support long-horizon general audio understanding and provide a foundation for always-on voice agents.

cs.CL · cs.SD

新论文 · v1arXiv:2611.11114

Compositional Conformal Risk Control for Multi-Stage LLM Cascades

Yuxia Sun, Jiahuang Wang, Haoting Liu, Zhiwei Huang, Tingrui Pei, Saiqin Long

原文摘要

Multi-stage large language model (LLM) cascades balance accuracy and inference cost, but reliable deployment also requires controlling error risk and identifying its sources across stages. We propose Compositional Conformal Risk Control (CompCRC), a risk-control framework for pre-specified multi-stage LLM cascades. We decompose the risk of accepting incorrect answers into additive stage-wise contributions over the full query population, linking local risk budgets to a system-level guarantee. CompCRC constructs and freezes candidate budget allocations and acceptance thresholds, selects one candidate on independent data, and certifies its stage-wise risk contributions on separate held-out data. Under conditional exchangeability, we establish a finite-sample guarantee: the marginal expected accepted-error risk of the complete deployment procedure does not exceed the global risk budget. At the reported comparison budget of $α=0.45$, all three stages of CompCRC pass their local checks on MMLU, GSM8K, and HellaSwag. Compared with Global-CRC, which passes system-level risk certification at the same budget, CompCRC reduces observed accepted-error risk by 1.33--2.00 percentage points, improves final accuracy by 0.67--2.00 percentage points, and reduces weighted inference cost by 30.37\% on HellaSwag. The selected cost-based budget allocation also improves accuracy per unit cost by 10.6\%--46.7\% over uniform allocation. Further experiments show that stage-wise statistics identify stages that fail local certification checks, providing diagnostic information alongside system-level risk control.

cs.LG

版本更新 · v2arXiv:2611.03523

DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?

Yuxuan Jiang, Chenglin Liu, John Rose, Mason Miller, Ruthesh Thavamani, Juntao Wu, Yinwei Huang, Jiahao Xu 等 9 位作者

原文摘要

LLM agents show strong potential in software engineering tasks such as competitive programming and code synthesis. Existing benchmarks, however, largely focus on small-scale settings such as self-contained Python modules, leaving distributed systems, an essential class of production software, under-examined. We introduce DistDebug-Bench, a benchmark for evaluating agents' ability to diagnose complex-system failures at the code level. It curates 120 high-quality real-world bugs from 11 widely used distributed systems, spanning 5 programming languages and 10 failure patterns. Through an extensive evaluation of state-of-the-art LLMs and agents, we identify substantial gaps between current agents and real-world debugging tasks. A recurring gap is tunnel vision due to a lack of explicit reasoning structure and nondeterminism from inconsistent tool-use scope. The benchmark and evaluator are available at https://github.com/OrderLab/distdebug-bench, with agent traces and a leaderboard at https://distdebug.com.

cs.SE · cs.DC · cs.LG

版本更新 · v3arXiv:2606.16881

SGM-SLAM: Scene Graph Matching for Data-Efficient Distributed SLAM

Yewei Huang, Tixiao Shan, Abhinav Rajvanshi, Niluthpol Chowdhury Mithun, Yaxuan Li, Brendan Englot, Han-Pang Chiu

原文摘要

We introduce a data-efficient distributed Simultaneous Localization and Mapping (SLAM) framework for multi-robot operation in GPS-denied and communication-constrained environments. The framework is designed for teams of robots equipped with LiDAR, cameras, and inertial sensors, where robots may operate from independently initialized local coordinate frames and share only limited spatial overlap. Our approach constructs a scene graph by using fused RGB-LiDAR point clouds to generate both a semantically segmented point cloud layer, and a layer of discrete bounded objects, to accompany estimated robot trajectories. Scene graph matching is performed collaboratively through exchanging and matching object data with neighboring robots. To maximize communication efficiency, we utilize a multi-step data exchange and optimization process. We demonstrate the effectiveness and communication efficiency of the proposed approach using real-world datasets containing limited trajectory overlap, viewpoint variation, repeated structures, and degraded visual conditions.

cs.RO

新论文 · v1arXiv:2611.10073

Noise-Regularized Training for Learned Image Compression

Renjie Zou, Zhiwei Huang, Dong Jiang

原文摘要

Learned image compression (LIC) is trained almost exclusively on clean images: the only stochastic perturbation in the loop is an additive uniform proxy injected in the latent domain to keep the entropy model differentiable. Outside compression, by contrast, a long line of work---from Tikhonov regularization and contractive autoencoders through denoising score matching and modern diffusion models---has established that Gaussian noise at the input of a network with a clean target acts as a structured probe of the data manifold rather than as data augmentation. Building on this view, we introduce noise-regularized training for LIC: at every training step we add Gaussian noise to the encoder input while keeping the distortion target, the latent uniform proxy, the hyperprior, and the entropy coding pipeline unchanged. The recipe is architecture-agnostic and adds essentially no training or inference overhead. Across backbones and operating regimes it yields consistent BD-Rate gains: -2.60% on a reproduced ELIC and -0.85% / -1.05% / -2.38% on the Base/Medium/Large scales of a variable-rate DMCI codec, with DMCI-Large reaching -22.02% against VTM-22.0. A second-order expansion of the noisy RD loss accounts for these gains: because the noise enters upstream of the analysis transform, it converts the clean RD objective into a structured $O(σ^{2})$ regularizer comprising an information-weighted encoder-Jacobian penalty (rate side) and a Frobenius contractive penalty on the end-to-end reconstruction map (distortion side). A finite-difference Lipschitz analysis shows corresponding sensitivity reductions of ~12% for the encoder and ~8% for the end-to-end codec, while an exact-JVP test further shows preferential contraction of high-information directions. Code and trained models are available at https://github.com/Googolxx/NoiseRegu-LIC.

eess.IV · cs.CV

新论文 · v1arXiv:2611.09138

Deep Learning Theory through the Lens of Statistical Physics: A Topical Review

Wei Huang, Youjin Deng

原文摘要

The recent success of foundation models and deep learning has far outpaced our theoretical understanding of how large-scale neural networks learn and generalize. Statistical physics provides a natural language for describing such high-dimensional, nonlinear, and strongly coupled systems, offering concepts such as mean-field theory, phase transitions, energy landscapes, and stochastic dynamics. In this topical review, we adopt a statistical-physics way of thinking -- from concepts including phases and criticality, and free-energy viewpoints, to methods such as kernel and Gaussian-process limits, mean-field and dynamical mean-field theories, random-matrix tools, and Fokker-Planck formalisms, and to a mindset emphasizing universality, scaling, and tractable limits with explicit validity regimes. We survey recent progress on understanding modern deep learning through this lens, including mean-field analyses of wide networks, spectral and geometric perspectives on loss landscapes, stochastic-gradient-based training viewed as a dynamical process, and phase-transition analogies that organize phenomena such as overparameterization, generalization, and representation change. Our goal is to synthesize these threads into a coherent framework that clarifies what each approximation explains, when it is expected to hold, and how apparently competing narratives relate or diverge. Together, these perspectives form a unified physical framework that views representation learning as a collective phenomenon in high-dimensional systems, bridging deterministic and stochastic regimes of gradient-based optimization.

cs.LG · cond-mat.stat-mech

版本更新 · v2arXiv:2605.20235

Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine

Wei Huang, Andi Han, Mingyuan Bai, Huanjian Zhou, Qixin Zhang, Taiji Suzuki, Kenji Fukumizu

原文摘要

Diffusion models generate high-dimensional data with remarkable quality, yet how training discovers and exploits low-dimensional manifold structure remains incompletely understood. We analyze a two-stage collapse-and-refine procedure motivated by the small-noise score: its singular normal component identifies manifold projection as the leading denoising target, while the remaining correction encodes density and geometry. Under suitable assumptions, we prove that annealed mean-field training asymptotically recovers the population denoiser and quantify the resulting geometric alignment error. With the learned representation fixed, residual score learning reduces to convex random-feature regression. We establish generalization bounds that separate residual learning error, propagated projection error, and geometric approximation bias, with statistical exponents governed by the intrinsic dimension. Under additional structural assumptions, we further derive an end-to-end sampling guarantee. Motivated by this analysis, we develop Score-induced Latent Diffusion (SiLD), a practical two-stage framework combining low-noise denoising representation learning with latent diffusion, without requiring KL regularization of the latent representation. Experiments on Stacked MNIST and molecular generation benchmarks demonstrate competitive generation quality relative to architecture-matched VAE-based latent diffusion baselines.

cs.LG · cs.AI

版本更新 · v2arXiv:2607.29586

TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning

Binnan Liu, Yechi Ma, Tian Xie, Wei Hua

原文摘要

The Abstraction and Reasoning Corpus (ARC) tests whether a model can infer an unseen transformation from a few input-output examples and apply it to a new grid. Looped visual reasoners refine predictions over multiple iterations, but conventional training constrains only the final output, leaving intermediate refinements unconstrained. We propose that these refinements should instead follow the transformation step by step. We introduce TraceViT, a looped visual reasoner trained with semantically monotonic transformation chains. We obtain these chains by rewriting and verifying programmatic task implementations, decomposing each solution into intermediate grid states. Each iteration is grounded by a task reference derived from the few-shot demonstrations and an object workspace representing the current grid state. Because these chains may differ in length from the loop, soft trace alignment enforces only their ordering, letting the model allocate iterations freely. TraceViT achieves 67.8% pass@2 on ARC-AGI-1 and 24.3% on ARC-AGI-2. Controlled ablations on ARC-AGI-1 show that trace supervision becomes beneficial only when paired with grounding. Code and data will be available at https://github.com/LiuBinnan/TraceViT.

cs.CV · cs.AI

新论文 · v1arXiv:2611.06627

Interactive World Simulation with Cosmos for Physical AI

NVIDIA, :, Anis Ahmad, Jon Allen, Malik Aqeel Anwar, Jesse Archer, Maciej Bala, Piotr Barejko 等 90 位作者

原文摘要

We present a shared framework that adapts Cosmos world foundation models for real-time interactive world simulation in Physical AI. By streaming visual observations in response to actions and scene controls, the framework enables users and embodied agents to interact with evolving virtual environments. It supports both predicting the visual consequences of actions and generating observations from physical state maintained by an external simulator. We demonstrate this approach across camera navigation and robot manipulation, controllable video transfer, and multi-view autonomous vehicle (AV) simulation. These examples provide a shared foundation for developing interactive virtual environments for Physical AI training and evaluation. Our code and model checkpoints are available at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3-examples. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos-simulation.

cs.AI · cs.CV · cs.LG · cs.RO