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

+1865新增论文
+1473其中 AI 相关
+176已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 17:12各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 17:23 — 2026-11-17 17:23(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:2026-11-17 04:58最近发现新增版本:2026-11-17 17:12库内论文最新更新时间:2026-11-17 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。

25,692 已收录论文21,414 AI 相关7,613 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 39 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.21570

Trustworthy Numerical Software in the Age of AI: What Would Turing Do?

Kimon Fountoulakis, Maksim Melnichenko, Muhammad Fetrat Qharabagh, Georgios Alexandros Georgantzas, George Spyrou, Oleg Balabanov, Vasileios Georgiou, Riley Murray 等 9 位作者

原文摘要

AI coding agents can now produce numerical software faster than human experts can review it, raising serious concerns about usability and reliability. These and other AI tools are already transforming mathematics and software, and they will soon transform mathematical software. These concerns motivated us to assess AI-generated numerical linear algebra (NLA) kernels, which we did through an audit of a recent public GPU QR competition. All five leading kernels passed the competition's accuracy tests, and the winning kernel achieved a 107-fold speedup over the competition's baseline, which calls NVIDIA's QR routine. Yet each failed at least once on new inputs, even those from the competition's generator, under the same checker, while the baseline passed them all. In light of this, we want to develop reusable formalizations of numerical analysis methods, which remain sparsely represented in existing formal libraries. We describe VSCL, our Lean library of mathematical foundations for numerical computing. We also propose VERNA to connect these tasks by using formalized results to guide kernel assessment against explicit specifications. Drawing on Turing's work on rounding-error analysis and program checking, we discuss design principles for developing trustworthy numerical software when direct human checking is impractical.

math.NA · cs.MS

新论文 · v1arXiv:2611.20714

MSAR: Next-Scale Autoregressive Forecasting for Time Series via Modular Multi-Scale Decoupling

Fanda Fan, Kuiye Ding, Liming Mao, Bingsong Wang, Yao Wang, Xiaorui Wang, Ruijie Jian, Zhipeng Liu 等 12 位作者

原文摘要

Time series forecasting underpins critical applications in finance, energy, healthcare, and transportation. Although deep models have achieved strong results, most adopt single-scale modeling or restrict multiscale processing to the input side, causing a misalignment between multiscale inputs and single-scale outputs and limiting predictive power. We introduce the Modular Scale-wise Autoregressive Framework (MSAR), a model-agnostic design that forecasts progressively across multiple temporal resolutions. MSAR offers three advantages: (1) scale-wise aligned modeling, which disentangles heterogeneous temporal patterns by aligning inputs and outputs at each scale; (2) scale-wise autoregression, where coarse-scale predictions guide finer-scale forecasting through hierarchical information flow; and (3) a modular architecture, enabling seamless integration with diverse backbones such as CNNs, MLPs, and Transformers. Extensive experiments across a broad set of datasets and forecasting models demonstrate that MSAR achieves consistent improvements in both accuracy and inference efficiency, validating the effectiveness of scale-aligned autoregression for multiscale time series forecasting. The code is available at: https://github.com/Oryxo/MSAR.

cs.LG

版本更新 · v2arXiv:2607.23753

On the post-hoc Evaluation of PDE Discovery: A Multifaceted Challenge of Scientific Advancement

Baptiste Mathevon, Farah Cherfaoui, Amaury Habrard, Marc Sebban

原文摘要

PDE discovery aims to identify from data the governing law of a physical system. Constituting a cornerstone of scientific advancement, it has become during the past decade a major line of research in the rapidly evolving field of Physics-informed Machine Learning (PiML). Among the open problems to address in this domain, the post-hoc evaluation of discovered PDEs raises the particular difficulty of being multifaceted. Indeed, it requires jointly considering predictive accuracy, physical consistency, interpretability, and out-of-distribution generalization capacity, some of these properties being conflicting. Drawing on an extensive body of literature spanning ML, numerical analysis and symbolic regression, we establish in this article that the overwhelming majority of papers address only certain aspects of the overall evaluation task. To better understand their limitations when used in isolation from the others, we propose the first taxonomy of PDE evaluation metrics. Through experiments conducted on several PDEs, we observe that limiting the scope of the evaluation can lead to overstated conclusions as well as changes in the ranking of the identified equations. For this reason, we provide recommendations with the aim of promoting standardized and reliable practices. This results in Pde-Check, a simple rules-based protocol to guide practitioners according to the scenario under consideration, including whether or not the ground truth equation is available (recovery or discovery), whether data is available beyond the training time frame and/or under varying initial conditions, or whether physical priors is available. We argue that this paper is intended both for ML experts who design new PDE discovery algorithms and for users of these methods aiming, in real applications, to discover and validate well-founded scientific laws.and validate well-founded scientific laws.

cs.LG

新论文 · v1arXiv:2611.17806

Can Agents Keep Up with Time? An Empirical Analysis of Temporal Adaptation After a Conversational Hiatus

Hongguan Su, Ming Wang, Shun Zhang, Yifan Wang, Rong Yin, Zhiming Ma, Mengzheng Yang, Peng Chen

原文摘要

Long-horizon agents increasingly serve as persistent personal assistants across modern web platforms, managing schedules, applications, and multi-step plans over weeks or months. Users often return to an ongoing conversation after a long conversational hiatus, while earlier bookings and preparation notes stay on record. During this hiatus, scheduled dates may pass even though the retained records remain unchanged and event outcomes go unrecorded. Existing evaluations of long-horizon agents focus on fact retention and explicit state updates. Whether agents perceive the passage of time and adapt their advice accordingly therefore remains unknown. We frame this ability as temporal state perception and use, which means perceiving the current time and applying it when interpreting dated records. To study it, we design session-rekindling tasks that keep the earlier conversation fixed and vary only the follow-up date and the way temporal information reaches the agent. Experiments across five model routes and five temporal-information conditions show that agents can obtain the current time but often fail to use it. They reliably query the clock and even note in their reasoning that the scheduled date has passed, yet many still tell users to prepare for the expired event. Supplying explicit temporal context reduces this error, and providing the computed date relation removes it entirely. Keeping up with time therefore depends on turning perceived time into updated plans. Based on these findings, we design a session-rekindling benchmark that provides temporal-awareness guidance for designing long-horizon agents. The code can be found at https://github.com/Adoreu2/session-rekindling-benchmark.

cs.AI

版本更新 · v2arXiv:2610.02665

大规模语言连续扩散模型

Large Language Continuous Diffusion Models

Zhihan Yang, Wei Guo, Jean-Marie Lemercier, Simon Welker, Mohammad Mahdi Kamani, Yonggan Fu, Sajad Norouzi, Julius Berner 等 17 位作者

AI 速读 基于摘要

提出首个大规模(3B/8B)连续扩散语言模型 Nemotron-Labs-Sigma,通过可操控的低维 ODE/SDE 潜轨迹实现高效推理与加速。

cs.CL · cs.AI · cs.LG

查看原文摘要

Despite the success of discrete diffusion language models (dLMs) for fast parallel decoding, their non-smooth, high-dimensional space hinders trajectory steering for reasoning and inference acceleration. To overcome this, we present Nemotron-Labs-Sigma, the first family of large-scale (3B/8B) continuous dLMs built on steerable, low-dimensional ODE/SDE latent trajectories. Trained blockwise via likelihood optimization, Nemotron-Labs-Sigma jointly denoises Gaussian-corrupted token embeddings while learning an optimal embedding geometry, and leverages pretrained autoregressive (AR) weights for warm-starting. At inference, we identify classifier-free guidance and score temperature as essential for high-fidelity reasoning and coding. Against state-of-the-art discrete counterparts (masked dLMs and AR baselines), Nemotron-Labs-Sigma outperforms them on standard benchmarks after pretraining (e.g., GSM8K, Minerva, HumanEval, MBPP) and on challenging reasoning tasks after supervised fine-tuning (e.g., MATH-500, AIME), with the largest consistent gains on coding. Beyond accuracy, we exploit two structural properties unique to continuous dLMs. First, smooth trajectories degrade gracefully at low NFEs and enable efficient few-step distillation: distribution matching proves strongest among the methods we study, giving roughly 8x acceleration on math and 4x on coding (8 and 4 tokens per forward pass) with negligible accuracy loss and preserved diversity. In addition, the one-step speculative decoding on the (pre-SFT) distilled 8B model yields a further ~3.5x throughput gain over the AR counterpart (on GB200), outperforming masked dLM baselines. Second, embedding-space steering controls the quality--diversity trade-off, yielding strong pass@$k$ that keeps improving as $k$ grows. Together, these results establish continuous dLMs as a promising paradigm for efficient language generation.

版本更新 · v3arXiv:2606.00727

知道何时行动:交通中人类行为的证据累积模型

Knowing When to Move: Evidence Accumulation Models of Human Behavior in Traffic

Floor Bontje, Felix van Waveren, Leendert van Maanen, Bhargav Nallapu, Gustav Markkula, Arkady Zgonnikov

AI 速读 基于摘要

一篇半系统综述,梳理28项(2014–2026)用证据累积模型(EAM)刻画交通决策与操控行为的研究,并按建模层级与实现方式组织文献。

cs.HC

查看原文摘要

Evidence accumulation models (EAMs) describe decisions as noisy evidence accumulating toward a decision boundary. Although widely studied in laboratory tasks, their application to dynamic, real-world behavior has received less attention. Traffic offers a setting where evidence changes as situations unfold, response timing matters, and decisions occur within ongoing control and interaction. This semi-systematic review synthesizes 28 publications (2014-2026) that model traffic decisions and control actions with EAMs. We organize the literature by modeling level (discrete decisions versus continuous action control) and implementation (stand-alone accumulators versus models embedded in broader perception-action or interaction frameworks). We examine how model components are implemented and evaluated across tasks. Overall, EAMs account for a range of dynamic road-user behaviors. Several comparisons suggest that response timing is better described by accumulating evidence as situations develop than by fixed delays or thresholds on momentary evidence, although accumulation models do not consistently outperform other kinds of models. Whether decreasing boundaries improve the fit differs between studies, and the models offer testable accounts of how decision-relevant information is processed. For cognitive scientists, traffic offers a testbed for studying how evidence from changing environments shapes decision-making. For applied modelers, the findings show how EAM components can be adapted to different traffic tasks, and why the choice of components needs to be evaluated for each task. However, most publications that estimated parameters pooled across participants, and most were not tested beyond the data they were fitted to, highlighting the value of participant-level or hierarchical estimation and of testing on new data.

版本更新 · v2arXiv:2609.33663

LieDiscover: Adaptive Symbolic Library Construction for Explicit Open-form Symmetry Discovery

Xinxin Li, Jianming Ma, Xingyu Cui, Da Li, Juan Zhang, Junping Yin

原文摘要

Discovering symmetries from observational data provides interpretable insights into dynamical systems and priors for scientific machine learning. However, existing symmetry discovery methods face two limitations. Many methods represent symmetries implicitly, making it difficult to obtain explicit infinitesimal generators that can serve as physical priors for learning dynamical systems. Meanwhile, methods that explicitly identify generators often rely on predefined function libraries, limiting their ability to capture complex symmetries involving high-order polynomials or transcendental functions. To address these limitations, we propose LieDiscover, a framework that explicitly identifies infinitesimal generators through an iterative symbolic search process that dynamically expands the symbolic function library to capture complex functional forms. Specifically, at each search step, we design an encoder-decoder architecture to generate a candidate symbolic expression. An adaptive singular value decomposition (SVD)-based evaluation is introduced to assess how each candidate contributes to the recoverable symmetry subspace. The resulting evaluations are incorporated into step-wise rewards to guide reinforcement learning toward discovering richer symmetry structures with concise symbolic representations. Experiments on eight partial differential equation (PDE) benchmarks demonstrate that LieDiscover recovers explicit generators involving higher-order polynomial, exponential, and trigonometric terms, while achieving more accurate symmetry subspace recovery and improved robustness to noise. Furthermore, the recovered generators enable effective symmetry-based data augmentation, improving the accuracy of downstream neural PDE solvers.

cs.SC · cs.LG

新论文 · v1arXiv:2611.15464

RSE-TTS: Compact Text-to-Speech through Shared Text-Aware Reference Encoding and Generation

Ming Ma, Mingjie Chen, Yuanzhong Zheng, Hengyao Bao, Hailin Yu, Shijing Yu, Hao Qiu, Gongfan Cao 等 11 位作者

原文摘要

Can a speech generator also serve as an effective voice encoder? We show that a pretrained autoregressive text-to-speech (TTS) backbone can be repurposed for reference compression, improving speaker similarity in subsequent synthesis. Jointly encoding reference speech and its transcript further strengthens this capability. Controlled ablations and activation interventions trace the text benefit through intermediate acoustic representations into the compressed vectors that condition generation. Building on these findings, we introduce RSE-TTS, whose Reconstructive Speaker Encoder (RSE) shares the generation backbone and compresses paired reference text and speech into eight continuous vectors. Sharing reduces encoder-generator parameters by 48% relative to independent pretrained encoding. Large-scale English training yields a 118M-parameter generator that improves both word error rate and speaker similarity over the corresponding official MOSS-TTS-Nano cloning modes on all three English benchmarks. Combined with acoustic continuation, RSE-TTS approaches the speaker similarity of substantially larger systems while achieving lower WER than the evaluated CosyVoice 3 and MOSS-TTS-Local models. Audio samples are available at https://voxnexusai.github.io/RSE-TTS/.

cs.SD · eess.AS

新论文 · v1arXiv:2611.15271

MoE Pretraining:Parallelism Layout Changes the Model, Not Quality

Esther Xin

原文摘要

Large Mixture-of-Experts (MoE) models are trained across many machines, and the way the work is split, the parallelism layout, often changes between runs: a job resumes on a different GPU count, a cluster is resized, or an ablation runs on a new setup. In exact arithmetic the layout should not matter, but in real arithmetic it changes the order in which numbers are added, and some MoE rules such as load balancing and expert capacity are often computed per machine. We ask whether the layout changes the trained MoE model. We pretrain the same small MoE language models (25M to 117M parameters, 20M FineWeb-Edu tokens) with the same seed, data and hyperparameters under 9 data-parallel and expert-parallel layouts, in fp32 on CPUs and fp16 on a GPU, and compare each run with the effect of a new random seed. Across 80 runs we find: (1) The layout does not change model quality, but it does change the model: final predictions differ about 80% as much as with a new seed, and over 90% of routing decisions differ. Any layout, a one-bit change to one weight, or a different CPU thread count has the same effect. (2) The cause is the router: decisions that flip are almost exactly those where two experts were nearly tied (AUC 0.97 to 1.00 in the first 16 steps). (3) More, smaller experts create more near-ties (2.7% with 8 experts, 23% with 64) and less reproducible routing (68% vs. 100% of decisions differ), but outputs do not drift further. (4) A dense model of the same active size is far more stable (0.12x the seed level in fp32, 0.58x in fp16), while the MoE reaches about 0.8x at both precisions and twice as fast. (5) When pretraining resumes on a new layout, timing matters: switching at 84% of pretraining barely changes the final model, while switching at 10%, just after warm-up, changes it substantially. We release code, run logs and data.

cs.DC

版本更新 · v2arXiv:2508.19363

LongReasonArena: A Long Reasoning Benchmark for Large Language Models

Jiayu Ding, Shuming Ma, Lei Cui, Nanning Zheng, Furu Wei

原文摘要

Existing long-context benchmarks for Large Language Models (LLMs) focus on evaluating comprehension of long inputs, while overlooking the evaluation of long reasoning abilities. To address this gap, we introduce LongReasonArena, a benchmark specifically designed to assess the long reasoning capabilities of LLMs. Our tasks require models to solve problems by executing multi-step algorithms that reflect key aspects of long reasoning, such as retrieval and backtracking. By controlling the inputs, the required reasoning length can be arbitrarily scaled, reaching up to 1 million tokens of reasoning for the most challenging tasks. Extensive evaluation results demonstrate that LongReasonArena presents a significant challenge for both open-source and proprietary LLMs. For instance, even GPT-5 achieves only 27.8% accuracy on Level 3. Further analysis also reveals that the accuracy exhibits a linear decline with respect to the logarithm of the expected number of reasoning steps. Our code and data are available at https://github.com/LongReasonArena/LongReasonArena.

cs.CL · cs.AI

新论文 · v1arXiv:2611.14728

SyntheIce: A Synthetic Radargram Annotation Benchmark for Englacial Layer Reconstruction

Muhammad Behroze Hassan, Bayu Adhi Tama, Sanjay Purushotham, Vandana P. Janeja

原文摘要

Englacial layers in radio-echo-sounding radargrams (subsurface ice images) encode the climate and flow history of ice sheets and glaciers. However, large-scale extraction is hindered by time-consuming manual annotation and semi-automated detectors that produce fragmented rather than continuous horizons. We address two challenges: reconstructing complete layers from partial detections across radargram profiles and validating layer continuity across adjacent tile boundaries. We introduce a slope-aware greedy fragment-linking algorithm that reconstructs full-width layers using row-similarity gating and an exponentially weighted moving average (EWMA) slope predictor. Each reconstruction receives a content-based hash ID for stable cross-radargram identification. For quantitative evaluation, we generate SyntheIce, a synthetic dataset of 600 radargrams spanning multiple complexity levels and realistic noise conditions, including 150 wide radargrams divided into four adjacent tiles. All samples include exact ground-truth annotations. We evaluate the dataset using XCheck, a consistency-based validation framework, extending its original two-image setting to four consecutive tiles and enforcing continuity at every boundary. This demonstrates the dataset's utility for developing and evaluating real-world annotation algorithms. Our findings extend beyond ice science: when spatial features are fragmented but retain consistent local geometry, trajectory-based linking is more reliable than appearance-based matching. Evaluation against expert-labeled real radargrams demonstrates high precision, recall, F1-score, and mean IoU, supporting the method's transfer to real-world data.

cs.CV

新论文 · v1arXiv:2611.11861

Scaling Adaptive Prompt Injection Attacks with Agent Swarms

Alexey Kurakin, Vishal Karande, Alex Bie, Chongyang Shi, Shuang Song, Saeed Mahloujifar, Abdullatif Köksal, Jamie Hayes 等 11 位作者

原文摘要

Prompt injections have emerged as one of the top security risks faced by AI agents today. Early work in prompt injection attacks looked at simple tool-call agents and static attack payloads, and were saturated since mid-2025. As of Fall 2026, human red-teaming may be nearing saturation, especially on the Gemini family of models. In this work, we argue that despite this apparent plateau, prompt injection attacks are still possible and continued effort into prompt injection defense is needed. We design a new synthetic evaluation dataset which uses random non-malicious actions as adversarial goals. Such dataset design helps us to evaluate prompt injection robustness as a model ability to respect instruction hierarchy, and disentangle this ability from model knowledge of security practices. We show that an agentic attacker of increased capabilities can reliably trick model to follow instructions in tool output in our evaluation, even for models previously considered robust on public prompt injection benchmarks such as GraySwan Arena. This shows that current frontier defenses may require proactive, automated red-teaming to remain resilient to increasingly capable adversaries.

cs.CR · cs.LG

新论文 · v1arXiv:2611.11509

Review the Episodes, Refine the Lessons: Simple Memory Evolution for Embodied Agents

Yifei Yao, Yude Zou, Xing Gao, Guanbo Jiao, Yukai Wang, Jianming Ma, Weinan Zhang, Chunhua Shen

原文摘要

Recent studies of embodied agents based on frontier multimodal large language models (MLLMs) develop harness engineering around the MLLM, such as harnesses with post-trained policies and recursive self-improvement loops. Yet whether these additions exceed the native capability of the MLLM remains unexplored. We introduce SimplEvo to explore how far an MLLM can improve under direct control when it retains its execution experience in self-written text memories. It requires no weight updates, post-trained policies, or privileged information. The MLLM writes a coordinate-free task memory once from a single demonstration. Under a strict train-test protocol, it then creates a bounded working memory on training episodes only and refines it after each episode with lessons on procedure, completion, and recovery. Both memories stay fixed at test time. On EBench, SimplEvo lifts the success rate (SR) of GPT-6-Astra under direct control from 46.7% to 81.7%, and tops the RoboDojo leaderboard with 69.63% SR and a score of 75.32. Compared with memories that also store past visual frames, SimplEvo reaches a similar SR with text memory alone while using fewer tokens. With its memories fixed, SimplEvo also generalizes to unseen layouts and randomized scene configurations. Moreover, the working memory transfers across models: written by GPT-6-Astra, it can be reused as is by weaker MLLMs and improve their performance without any adaptation of their own.

cs.RO · cs.AI · cs.LG

新论文 · v1arXiv:2611.11169

Map2SLAM: From Streaming Map Prediction to Real-Time SLAM

Jian Gao, Lin-Zhuo Chen, Yihang Chen, Jiagang Chen, Jiacheng Dong, Xun Cao, Nan Xue, Yinghao Xu 等 9 位作者

原文摘要

Streaming 3D foundation models (3DFMs) estimate camera poses and dense geometry online, but they fall short of SLAM: their predictions are fixed once emitted, so loop closures cannot correct accumulated drift. With such models already providing strong geometric capability, a central question for SLAM becomes how to schedule their inference and how to keep its results as revisable state. We present Map2SLAM, which keeps LingBot-Map frozen, trains only a lightweight retrieval head, and builds SLAM on the model's inference interface, turning its predictions into observations of an external persistent SLAM state. The front-end tracks every incoming frame with the model's causal streaming inference and decides which frames are written to the persistent state as keyframes. The back-end asynchronously decides when and which past frames to re-observe, re-running the model's joint inference over them with fresh context; verified loop observations correct the trajectory online, and segment observations refine dense geometry after the sequence. All invocations share a single frame encoder pass per image, whose cached features also drive loop retrieval, so frequent re-invocation incurs no additional encoding cost. Map2SLAM achieves state-of-the-art performance on KITTI, VBR, and Oxford Spires, reducing mean ATE by over 40% compared with the best uncalibrated baselines, while maintaining real-time tracking at over 28 FPS at a resolution of $518\times154$ on an NVIDIA RTX 5090D GPU. Please visit our project page at https://robbyant-research.github.io/Map2SLAM/.

cs.CV

新论文 · v1arXiv:2611.10846

Efficient SC-Flip Decoding for Polar Codes through Decision-Boundary Normalization

Gulinisha Yiming, Zhongjun Yang, Zhicheng Liu, Zhiming Ma, Xumin Ni, Yuting Liu

原文摘要

Accurate first erroneous position (FEP) identification is key to improving the error-correction performance of successive cancellation flip (SCF) decoding. However, FEP identification remains challenging with a limited number of re-decoding attempts. To address this issue, we propose decision-boundary normalization (DBN) to improve FEP identification and develop a novel DBN-SCF decoding algorithm. DBN normalizes the magnitude of each decision log-likelihood ratio (LLR) by the standard deviation predicted by the Gaussian approximation (GA) for the corresponding bit-channel. This allows a single normalized threshold to be shared across bit-channels within each code configuration, giving it a consistent statistical meaning and avoiding per-channel calibration. DBN-SCF decoding selects candidate flip positions from the information set in the natural successive cancellation (SC) decoding order using a threshold, without sorting. Moreover, DBN-SCF decoding achieves better error-correction performance with a limited number of re-decoding attempts. It also requires lower average decoding complexity than existing SCF decoding methods at a comparable level of error-correction performance.

cs.IT

新论文 · v1arXiv:2611.10600

InfoOrgBench: Can Agents Turn Scattered Information into Coherent Hierarchies?

Justice Ou, Lanming Ma, Zijian Zhang, Yilun Zhao

原文摘要

When agents organize records into folders, they may correctly group the excerpts of a design proposal yet place the proposal under the wrong owning group. Existing agent benchmarks do not directly measure such higher-level errors. We introduce InfoOrgBench, a benchmark of 150 tasks in which agents organize scattered records from meeting recaps, issue threads and design proposals into hierarchies. Integrity checks verify that every record is preserved, and a Structure Score measures agreement with the source hierarchy at every level, independent of folder names and order. We evaluate 45 systems that pair nine models with five agent harnesses. The best system scores 83.2 out of 100, but no system exceeds 78 on meeting recaps or issue threads. Model choice affects scores far more than harness choice: model means span about 27 points, whereas the average effect of each harness is below one point. More importantly, parent-level relations have higher error rates than leaf-level relations in all three domains. In design proposals, nearly half of the outputs analyzed by level make exactly this kind of error. These results show that evaluating information organization requires measuring higher-level relations separately from record preservation and local grouping.

cs.AI

新论文 · v1arXiv:2611.10219

Multi-GPU MoE Inference with Adaptive Expert Offloading

William X. Zheng, Zhongjie Chen, Shuo Yang, Ziming Mao, Xiaoze Fan, Yi Pan, Kunjun Li, Hanfei Yu 等 12 位作者

原文摘要

Modern Mixture-of-Experts (MoE) inference is constrained by GPU memory. This constraint is mitigated by expert offloading, which stores part of the model's weight in host memory and executes on demand. Though MoE architecture has computation sparsity, more GPUs are needed for serving increasingly larger frontier models. However, existing expert offloading systems overlook this need and fail to scale performance with additional GPUs. We present AdaOffload, a general and efficient multi-GPU hybrid expert execution framework that effectively handles heterogeneous hardware and workloads. We co-design GPU-CPU parallelism and GPU-CPU co-execution for decode and prefill with online workload observation that adapts to different hardware, workload, and batch size heterogeneity. We evaluated AdaOffload on five different platforms with varying GPU capability (L4, Pro6000, B200), number of GPUs, CPU capability, and NUMA topology on three different frontier open-weight models (284B to 753B). AdaOffload achieves $1.9\times$ to $15.5\times$ throughput speedups across different models over state-of-the-art systems.

cs.AI

新论文 · v1arXiv:2611.08993

When2What: A Timing-Conditioned Framework for Long-Horizon Forecasting of Continuous Cardiovascular Waveforms

Chaoqi Zhang, Shujie Yan, Zhao Zhang, Yanhua Sun, Yu Wang, Li Li, Lingzhong Meng, Xiaoyi Chen 等 9 位作者

原文摘要

Long-horizon forecasting of quasi-periodic cardiovascular waveforms, such as the electrocardiogram (ECG), arterial blood pressure (ABP), and photoplethysmogram (PPG), requires predicting both when future cardiac events will occur (beat timing) and what the local structural pattern looks like around each event (beat morphology). However, standard sequence forecasters trained with pointwise mean squared error (MSE) average across uncertain future heartbeat phases, flattening sharp R peaks and pulse upstrokes into featureless baselines. Our analysis of intraoperative ECG reveals a clear temporal asymmetry: beat-time predictability from history decays within seconds due to stochastic heart-rate variability, whereas local beat morphology aligned at true beat times remains stable over several minutes. Guided by this insight, we introduce When2What, a timing-conditioned framework comprising three stages: Predict, Commit, and Generate. Given a 120-s history, When2What predicts a dense 60-s timing map, selects and sharpens discrete beat events into unit-height Gaussian impulses, and conditions a neural waveform generator on both these committed events and the observed history. Across intraoperative ECG, When2What substantially outperforms existing time-series and physiological forecasters, achieving a near-term waveform event skill of 0.644 and reproducing 95.62% of its predicted heartbeats in the generated waveform where direct long-horizon forecasters collapse into flat baselines. Furthermore, When2What transfers zero-shot to external hospital and atrial fibrillation cohorts, extends effectively to ABP and PPG pulse waveforms, and is supported by ablations and synthetic analyses that establish explicit timing conditioning as an effective paradigm for quasi-periodic long-horizon waveform forecasting.

cs.LG

版本更新 · v2arXiv:2608.16543

Revisiting Shannon's Source Coding Theorem with Distributional Uncertainty under the Nonlinear Expectation Theory

Wen-Xuan Lang, Shaoshi Yang, Jianhua Zhang, Zhiming Ma

原文摘要

In classical information theory, a source is modeled by a single, precisely known probability distribution. However, in the increasingly complex communication networks full of unanticipated, nonstationary, and heterogeneous random events, the assumption of precise and well-defined probability distributions to describe random variables appears somewhat idealized. Therefore, it is important to characterize the uncertainty of distributions of source messages, subject to relaxing the assumption of deterministic probability models for analyzing information sources in information theory. Based on the nonlinear expectation theory, a novel axiomatical system that extends classical probability theory, this paper investigates the information sources whose distributions themselves are uncertain, and refers to them as uncertain-distribution sources. We generalize the fundamental concept information entropy to nonlinear information entropy, which describes the measurement of the amount of information contained in a uncertain-distribution source. By using the strong law of large numbers under sublinear expectation, we establish a nonlinear source coding theorem, which not only shows that the nonlinear information entropy is the upper bound for the infimum of achievable coding rate of uncertain-distribution sources under the maximum error probability criterion, but also determines a cluster point of the coding rate of uncertain-distribution sources under the minimum error probability criterion. Our findings reveal that the introduction of nonlinear expectation theory allows for a more comprehensive understanding of information sources.

cs.IT

新论文 · v1arXiv:2611.01430

Polynomial-Time Minimax Prediction for Stationary Renewal Processes

Xinyu Chen, Yiming Ma

原文摘要

The minimax next-symbol Kullback-Leibler risk for stationary binary renewal processes is known to have order n^(-1/2). We give a polynomial-time predictor attaining this order for an arbitrary unknown finite-mean interarrival law. The construction uses a classical type-uniform renewal code. Its contribution is an exact dynamic program for censored prefix marginals, avoiding enumeration of gap histograms or binary completions. Combined with an established prediction reduction, it gives risk at most [log M_(n+1)+log(n+2)]/n, where M_N counts renewal types. Shared suffix updates reduce the total computation to O(n^3) arithmetic work and polynomial bit complexity, without tail, mixing, known-mean, or bounded-support assumptions. The statistical rate and its lower bound are prior results; the proposed advance concerns computation.

cs.IT · cs.LG

新论文 · v1arXiv:2610.40075

Learning Safe Flow Matching Robot Policies from Binary Feasibility Oracles

Jianming Ma, Rongjun Jin, Yizhi Chen, Yue Gao

原文摘要

Robot foundation models increasingly rely on flow-based action generation for general-purpose manipulation, yet the generated actions are not guaranteed to satisfy physical constraints such as joint limits and collision avoidance. This problem is especially challenging when the feasible set cannot be described analytically and is accessible only through black-box feasibility oracles. We study this practical oracle-only setting and propose an oracle-guided differentiable safeguard for safe flow-matching robot policies. The safeguard uses binary feasibility queries to correct unsafe updates in the forward pass, while extracting local boundary information to provide constraint-aware learning signals in the backward pass. Combined with discrete-time flow matching, the same safeguard is used during training and inference, enabling forward--backward aligned policy learning without explicit or differentiable constraint models. Experiments on obstacle-aware robotic manipulation demonstrate 100% constraint satisfaction while preserving task performance.

cs.RO · cs.AI

新论文 · v1arXiv:2610.36848

Evolving Agent Teams

Shiyi Cao, Ziming Mao, Dacheng Li, Joseph E. Gonzalez, Ion Stoica

原文摘要

The rapid progress of software engineering agents drives interest in applying them to open-ended problems such as GPU kernel optimization. However, we find that existing coding agents converge to local optima on real-world, expert-written kernels (e.g., FlashInfer). We introduce Evolving Agent Teams, a multi-agent framework that escapes such local optima. It features (1) a central supervisor that diagnoses each local optimum and restructures a team of agents; and (2) a persistent file system that comprises a learning document, an evolution history, and per-team artifacts, grounding restructuring with accumulated experience. Under a matched token budget, Evolving Agent Teams consistently outperforms strong coding-agent baselines. With an extended token budget, Evolving Agent Teams generates a CUDA kernel that reaches 1.2x mean speedup over the production FlashInfer MLA paged decode kernel from scratch and wins on 36 of 47 production workloads from FlashInfer-Bench (0.86-0.99x on the remaining 11). It also demonstrates superior performance on tasks such as KDA prefill on AMD MI350X (3.01x over vLLM) and NVIDIA B200 (3.44x over FlashKDA), MoE expert-offload serving on Apple silicon (30.3 tokens/s decode for Qwen3.8-Flash-Next in MLX 4-bit on a 48 GB M4 Pro), and RoboDojo robot manipulation (62.1 on held-out seeds vs. 55.3 for the best leaderboard entry). Code is available at https://github.com/caoshiyi/EAT.

cs.AI

新论文 · v1arXiv:2610.36577

An Unconditional Space-Approximation Lower Bound for Semi-Streaming Matching

Yang P. Liu, Kheeran Naidu, Hoai-An Nguyen, Janani Sundaresan

原文摘要

We prove the first unconditional lower bound tradeoff between the number of passes and the approximation factor of maximum matchings in the semi-streaming model. Specifically, we show that any algorithm that outputs an $(1-\varepsilon)$-approximation to maximum matching requires $Ω(\log(1/\varepsilon))$ passes for constant $\varepsilon \in (0,1)$. Prior to our result, such tradeoffs were proven only conditioned on a certain combinatorial assumption about the density of Ruzsa-Szemerédi graphs. The state-of-the-art unconditional lower bound rules out any approximation factor better than $(8/9)$ in two passes but leaves open the possibility of a $(1-\varepsilon)$-approximation for any $\varepsilon > 0$ even in three passes. We provide two different proofs of our result: the first proof uses the recent hierarchical-embedding framework of Assadi, Konrad, Naidu, and Sundaresan (STOC 2024) along with combinatorial constructions using Ruzsa-Szemerédi graphs. The second extends the two-level Ruzsa-Szemerédi hierarchy of Konrad and Naidu (SODA 2024) beyond two levels and proves the corresponding communication lower bound directly by induction, rather than through a reduction to Index.

cs.DS

新论文 · v1arXiv:2610.36574

ADTGuard: Adaptive Depth-Time Safeguard for Streaming Inference in Large Language Models

Chuming Wei, Churui Yang, Zihan Zhang, Ruien Li, Wusheng Zhang, Yan Zhang, Guangwen Yang

原文摘要

Large Language Models (LLMs) can generate fluent responses to diverse user requests, yet streaming may expose users to harmful content before generation is complete. Existing guardrails face two limitations in this setting. First, post-hoc moderation at response or chunk boundaries delays intervention, risking harmful exposure when content is released before verification. Second, even with token-level detection, coarse response-level supervision does not specify when harmful content begins, while fixed-layer readouts may miss relevant safety signals at other depths. To address these limitations, we introduce ADTGuard, which checks each token before release, progressively refines token-level training targets, and adapts layer selection to the current prefix. ADTGuard models risk across depth and time through Depth-Time Safety Dynamics (DTSD), which integrates safety evidence across layers at each token and uses it to guide risk accumulation over successive tokens. To adapt the choice of observation layers to the current prefix, we propose the Causal Depth Router (CDR). With only response-level labels available, we further develop Risk-Onset Target Refinement (RTR) to progressively construct token-level training targets for both components. Through extensive experiments across multiple safety benchmarks, we demonstrate that ADTGuard consistently achieves strong streaming detection performance, matching or surpassing state-of-the-art safeguards while requiring only 16M trainable parameters and maintaining competitive per-token latency.

cs.AI

新论文 · v1arXiv:2610.36538

Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization

Zhiheng Qian, Junhao Du, Jing Peng, Hanqi Li, Kunyang Peng, Feng Xue, Lu Chen, Shuai Wang 等 9 位作者

原文摘要

Multilingual automatic speech recognition (ASR) has achieved rapid progress with large-scale pretrained models and multilingual speech corpora. Previous studies have proved the pivotal role of data sampling in multilingual ASR performance. However, existing sampling strategies largely rely on time-consuming manual, heuristic-based designs. To address this, we propose a linguistic-aware agentic data sampling framework that introduces a data sampling LLM agent into the multilingual ASR training loop. The agent is driven by a linguistically grounded rubric that analyzes ASR errors from phonological, morphological, and syntactic perspectives, and uses the resulting feedback together with training statistics, budget constraints, and algorithm profiles to select domain-level, sample-level, and token-level sampling strategies. This design turns evaluation results into adaptive data-selection decisions rather than treating WER/CER as final endpoints only. We conduct experiments on twelve Common Voice languages using Whisper-medium as the ASR backbone. The results show that our method achieves performance better than full-data training while using less training data and lower computational resources, and substantially accelerates training convergence compared to conventional sampling strategies.

cs.CL

新论文 · v1arXiv:2610.35832

Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy

Yifei Yao, Yude Zou, Guanbo Jiao, Xing Gao, Ning Gao, Yukai Wang, Jiantong Chen, Zihou Zhu 等 15 位作者

原文摘要

Frontier multimodal large language models (MLLMs) can control robots without robot-specific training, but how their capabilities compare and interact with post-trained vision-language-action (VLA) and world action model (WAM) policies across manipulation demands remains to be thoroughly evaluated. In this report, we evaluate GPT-6-Astra on EBench as the core of an agent that controls a robot through an agent harness under the same visual and proprioceptive observation protocol as post-trained policies. We study two agent configurations: direct control, in which the agent generates waypoint commands directly, and harness with policy, in which it can also invoke a post-trained VLA or WAM policy for action execution. Under direct control, the agent achieves competitive overall performance relative to post-trained policies. It leads on short-horizon tasks and exhibits the least performance variation across generalization dimensions, whereas it underperforms post-trained policies on long-horizon tasks, tabletop manipulation, and high-precision contact-rich tasks. In the harness with policy, invoking a post-trained VLA or WAM combines the complementary strengths of both components, raising overall task success to the level of the strongest compared post-trained policies while substantially reducing token cost. However, performance remains below the per-task upper bound of the standalone components due to suboptimal policy invocation, fixed-instruction execution without subgoals, and grasp disruption when the agent resumes control. Overall, our study characterizes the capability boundary of a frontier MLLM agent and suggests directions for improving future agent harness design. Project page: https://internrobotics.github.io/EBench-Astra-Tech-Report/

cs.RO · cs.AI

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.115ACL Anthology · ACL 2026

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning

Yanrui Du, Fenglei Fan City University of Hong Kong, Sendong Zhao, Jiawei Cao, Ming Ma, Danyang Zhao Harbin Institute of Technology, Shuren Qi City University of Hong Kong, Ting Liu Harbin Institute of Technology 等 9 位作者

原文摘要

Instruction Fine-Tuning (IFT) has emerged as a critical technique for customizing Large Language Models (LLMs) to meet diverse downstream applications. However, recent studies have revealed that IFT can compromise the built-in security mechanisms of LLMs, thereby posing significant security risks. Although defense methods targeting various training stages have been proposed, they either face challenges in practical deployment or exhibit instability and limited performance gains. In our study, we propose a novel SWAT method that introduces a key idea: shifting more of the learning burden onto security-robust parameters. To this end, our study investigates how module-level parameters affect LLMs’ internal security feature space, aiming to uncover robustness patterns in parameters. Guided by this analysis, we identify a robust module set (Mods_Rob) that exhibits minimal effects on LLMs’ security feature space. Leveraging this insight, SWAT proceeds in two phases: (1) a warm-up phase that preferentially trains Mods_Rob to learn low-level features with minimal security risk, followed by (2) standard tuning to achieve optimal task performance. Across diverse knowledge-intensive datasets, scenarios, and LLMs, SWAT substantially reduces security risks without sacrificing task performance gains.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1201ACL Anthology · ACL 2026

SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning

Peidong Wang, Zhiming Ma SmartFlowAI, Xin Dai, YongKang Liu Northeast University, Shi Feng Northeastern University, China, Xiaocui Yang Northeastern University, Wenxing Hu, Zhihao Wang Northeastern University 等 11 位作者

原文摘要

Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This limits their effectiveness against complex deceptive strategies. To address these challenges, we first propose SAFE-QAQ, an end-to-end comprehensive framework for audio-based slow-thinking fraud detection. First, the SAFE-QAQ framework eliminates the impact of transcription errors on detection performance. Secondly, we propose rule-based slow-thinking reward mechanisms that systematically guide the system to identify fraud-indicative patterns by accurately capturing fine-grained audio details, through hierarchical reasoning processes. Besides, our framework introduces a dynamic risk assessment framework during live calls, enabling early detection and prevention of fraud. Experiments on the TeleAntiFraud-Bench demonstrate that SAFE-QAQ achieves dramatic improvements over existing methods in multiple key dimensions, including accuracy, inference efficiency, and real-time processing capabilities. Currently deployed and analyzing over 70,000 calls daily, SAFE-QAQ effectively automates complex fraud detection, reducing human workload and financial losses. Code: https://anonymous.4open.science/r/SAFE-QAQ.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.158ACL Anthology · ACL 2026

OASIS: Online Sample Selection for Continual Instruction Tuning

Minjae Lee, Minhyuk Seo KU Leuven, Tingyu Qu KU Leuven, Tinne Tuytelaars, Jonghyun Choi Seoul National University

原文摘要

In continual instruction tuning (CIT) scenarios, where new instruction tuning data continuously arrive in an online streaming manner, training delays from large-scale data significantly hinder real-time adaptation. Data selection can mitigate this overhead, but existing strategies often rely on pre-trained reference models, which are impractical in CIT setups since future data are unknown. Recent reference model-free online sample selection methods address this, but typically select a fixed number of samples per batch (e.g., top-k), making them vulnerable to distribution shifts where informativeness varies across batches. To address these limitations, we propose OASIS, an adaptive online sample selection approach for CIT that (1) selects informative samples by estimating each sample’s informativeness relative to all previously seen data, beyond batch-level constraints, and (2) minimizes informative redundancy of selected samples through iterative selection score updates. Experiments on various large foundation models show that , using only 25% of the data, achieves comparable performance to full-data training and outperforms the state-of-the-art sampling methods.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.2174ACL Anthology · ACL 2026

Adaptive Instruction Composition for Automated LLM Red-Teaming

Jesse Zymet CapitalOne, Andy Luo CapitalOne, Swapnil Shinde CapitalOne, Sahil Wadhwa CapitalOne, Emily Chen CapitalOne

原文摘要

Many approaches to LLM red-teaming leverage an attacker LLM to discover jailbreaks against a target. Several of them task the attacker with identifying effective strategies through trial and error, resulting in a semantically limited range of successes. Another approach discovers diverse attacks by combining crowdsourced harmful queries and tactics into instructions for the attacker, but does so at random, limiting effectiveness. This article introduces a novel framework, Adaptive Instruction Composition, that combines crowdsourced texts according to an adaptive mechanism trained to jointly optimize effectiveness with diversity. We use reinforcement learning to balance exploration with exploitation in a combinatorial space of instructions to guide the attacker toward diverse generations tailored to target vulnerabilities. We demonstrate that our approach substantially outperforms random combination on a set of effectiveness and diversity metrics, even under model transfer. Further, we show that it surpasses a host of recent adaptive approaches on Harmbench. We employ a lightweight neural contextual bandit that adapts to contrastive embedding inputs, and provide ablations suggesting that the contrastive pretraining enables the network to rapidly generalize and scale to the massive space as it learns.

cs.CL

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