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

+1111新增论文
+874其中 AI 相关
+133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:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 09:27 — 2026-11-20 09:27(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:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 23,249 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)
新论文 · v1arXiv:2611.23403

Tracking Representations in LLM Reasoning Traces for Iterated Games

Chaipat Tirapongprasert, Rajarshi Das, Parijat Dube

原文摘要

Large language model (LLM) agents achieve state-of-the-art performance across domains through chain-of-thought (CoT) reasoning. Despite their ubiquitous use, little is understood about the relationship between the externalized trace and the model's actual computation. We address this by investigating how LLM agents make decisions in iterative games with incomplete information. Using a series of mechanistic interpretability techniques, we find that the model forms and iteratively revises an internal representation of the game throughout the CoT. Once the model prematurely commits to an incorrect belief, it rarely recovers. This failure is manifested in both the literal trace and the layer activations. Ultimately, as multi-agent systems are more prevalent, our work opens the door to a more focused diagnosis of their strategic reasoning errors. For illustrative purposes, we offer an interactive visualizer of our methodology on selected sample traces at https://interp-self.github.io/gametrace/

cs.CL · cs.AI · cs.GT

新论文 · v1arXiv:2611.23398

HardwareDx: A Foundational Graph Model System for Datacenter Machine Repairs

Yuanlin Wen, Elan Markowitz, Zubo Gu, Sami Abu-El-Haija, Bryan Perozzi, Mikhail Galkin, Ali Parviz, Aayush Gupta 等 14 位作者

原文摘要

The rapid scale-up of AI infrastructure has made datacenter reliability a cornerstone of the cloud business economy. Since hardware failures in hyper-scale AI clusters can stall multi-million dollar training workloads, the downtime of individual machines can cause outsized economic losses. Minimizing machine downtime, therefore, is more important than ever. To address this, we present Hardware Diagnoser (HardwareDx), an AI-driven hardware diagnosis system that applies a graph foundation model approach to automated datacenter maintenance. It allows a single model to diagnose many platforms and accelerate onboarding of new hardware products. Deployed at production scale at Google, HardwareDx yields substantial efficiency gains across diverse compute architectures. Real-world evaluations demonstrate that it reduces production downtime by 18.3% on GPU platforms and 16.1% on TPUs. Furthermore, it significantly accelerates hardware deployment, cutting quality assurance (QA) time by 28.3% for GPUs and 25.1% for TPUs. These results establish HardwareDx as a field-tested solution for maximizing the reliability and cost efficiency of next generation AI fleets.

cs.AI · cs.AR

新论文 · v1arXiv:2611.23397

Which Tokens, in What Order, and How Fast? A Theoretical Analysis of On-Policy Distillation Objectives

Hubert Strauss, Liam Fowl, Noam Razin

原文摘要

On-policy distillation (OPD) trains a student language model to match a teacher model based on its own generations. When using OPD, one must choose whether to apply it at the sequence or token level and which divergence to minimize. However, despite the wide adoption of OPD in practice, the formal understanding of which OPD objective is appropriate for a given setting is limited. Toward addressing this gap, we theoretically analyze how the choice of OPD objective governs which tokens are prioritized, in what order, and how efficiently. Our analysis reveals that sequence-level OPD exhibits a future agreement bias, which myopic token-level objectives avoid. This bias induces a reverse learning order, in which sequence-level OPD first matches the teacher at later token positions, while at earlier positions it can favor tokens that are improbable under the teacher, and thus often undesirable. As for the choice of divergence, we prove that it strongly influences the amenability of OPD to gradient-based optimization. In particular, while the forward KL divergence enjoys a well-behaved objective landscape, other $f$-divergences, such as reverse KL, can suffer from vanishing gradients even when the student and teacher are far apart. Across language model post-training settings, we demonstrate the implications of these theoretical findings for which OPD objective is preferable, highlighting the importance of accounting for the interplay between the student, teacher, and task at hand.

cs.LG · cs.AI · stat.ML

新论文 · v1arXiv:2611.23395

Lossless Reversible Watermarking for AIGC with Applications in Authentication

Yupeng Qiu, Han Fang, Ee-Chien Chang

原文摘要

AIGC watermarking is commonly used for tracing, but it can also support applications such as authentication and tampering detection. We study lossless reversible watermarking, which enables exact recovery of the original watermarked image after permissible distortions. By exploiting the relatively low entropy of the information required for image generation, together with robust latent-space watermarking, we design a framework that preserves sufficient information for lossless recovery. We then apply the framework to AIGC authentication, which generally faces two key challenges. First, the authentication mechanism must resist adaptive adversaries. Second, the content relevant to authentication, such as visual designs or expressed messages, may depend on application requirements that are not known at generation time. To solve these difficulties, we incorporate cryptographic message authentication to provide unforgeability against adaptive attacks. Lossless recovery provides the original image as reference evidence, after which a suitable analyzer can be selected to make the authentication decision. Experiments on Stable Diffusion demonstrate exact recovery under a wide range of distortions.

cs.CR · cs.CV

新论文 · v1arXiv:2611.23388

QDA: Closed-Loop LLM Quantization Design with Agents

Xingyang Li, Tianlang Zhao, Song Han, Ligeng Zhu

原文摘要

Post-training quantization is the standard way to serve large language models at low cost. However, the best quantization recipe differs across models and precisions. As a result, experts must redesign it for every new model, which is time-consuming and often sub-optimal. Fortunately, an LLM agent can take over this design by refining the recipe over rounds of building and evaluating candidates, so that more rounds lead to better recipes. However, evaluating one quantized reasoning model takes tens of GPU-hours, and combining methods from different codebases means porting each to the new architecture by hand. We present QDA, a system in which an agent designs the recipe for each model and precision. To make evaluation fast, QDA scores each candidate in minutes by its output KL divergence from the original model on reasoning traces that the agent never sees, and checks promising ones with long generations to catch failures such as repetition loops. To make building fast, QDA provides a library of public PTQ methods that are compatible with one another and with new model architectures. Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search. On the 320B-parameter MoE model GLM-5.3-Flash at NVFP4 W4A4, it recovers 98.3% of the FP8 model's accuracy, against 96.9% for the best vendor checkpoint. Every QDA checkpoint also runs on existing serving kernels with no inference overhead. We will release the library, the evaluator and the harness.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.23386

Chorus: Shared N-gram Embeddings with Layer-wise Adaptation

Stephen Chung, Wenyu Du

原文摘要

Language models can gain capacity at little computational cost from n-gram embedding tables: large tables of learned vectors for short sequences of consecutive tokens, which are looked up and added to the model's input or to its intermediate layers. Recent designs commonly use a separate n-gram embedding table for each layer, which makes the tables costly in memory and prevents layers from sharing what they learn. Sharing a single table, however, gives every layer the same embedding and leaves no room for layer-wise preferences, and it performs poorly in practice. We propose Chorus, in which one set of n-gram embedding tables serves the whole network and every layer reads it in its own way. Each layer maps the refined embedding through its own projection layer, after rescaling its components by factors computed from its current hidden state. Chorus matches the quality of existing n-gram methods with 87% smaller tables: with 1.2B table parameters it predicts text better than FactorEngram and DeepSeek's Engram do with 9.6B. It outperforms Engram, TN-gram and FactorEngram in every setting where we compared them, across table sizes from 20M to 9.6B parameters. We also show that the recently proposed memory-efficient optimizer Ember works well with Chorus, saving 99.2% of table-optimizer memory compared with AdamW without degrading training performance. These results enable further scaling of n-gram embedding tables along the table-size axis by reducing memory use and allowing shared knowledge to be reused across layers.

cs.CL

新论文 · v1arXiv:2611.23375

Where the Tokens Go: Heat, Entropy and Error in Agentic Coding

Alán Aspuru-Guzik, Varinia Bernales

原文摘要

Coding agents are billed by the token, yet software engineering says nothing about what a token actually buys. Here we introduce a theory of software thermodynamics. The theory draws analogues from classical and stochastic thermodynamics, extends them, and applies them to modern agentic coding. We count the tokens an agent generates as its cost and divide that cost into work and heat. The test suite acts as a software Maxwell's daemon that judges every coding change. We test the theory with an analogue of the experiments in which a single molecule is pulled open and let fold again: an agent makes a change to a repository (coding) and then undoes it (uncoding), many times over, and we count the tokens of every model call. The cycle returns the requested edits to where they began, with each direction started from a stored reference tree, and the spread of its cost over repeated cycles defines a software temperature, which rose with the sampling temperature of the model. About 80 per cent of the tokens of a successful run are generated in model calls that leave the requested change where it was, and we call these tokens heat. The free energy of a change, which we estimate by analogy with the equality of Jarzynski, is 14 to 22 per cent of the mean cost of a successful coding run. Coding costs 1.1 to 1.5 times as much as uncoding. The daemon is imperfect: the verdict of a test suite varies with its environment, and a suite that accepts a broken change has a cost in tokens. The practical implication of the proposed theory could be new tools for analysing and optimising coding agents through the lens of thermodynamics.

cs.AI · cond-mat.stat-mech · cs.SE

新论文 · v1arXiv:2611.23229

环境LLM:通过温度匹配实现数据高效监督微调

Ambient LLMs: Data-Efficient Supervised Fine-tuning via Temperature Matching

Giannis Daras, Marios Papachristou, Adam Klivans, Antonio Torralba, Constantinos Daskalakis

AI 速读 基于摘要

提出Ambient SFT框架,利用预训练模型作为噪声教师,通过匹配高温条件分布来增强微调数据,缓解小数据SFT中的过拟合和灾难性遗忘。

cs.LG · cs.AI · cs.CL

查看原文摘要

Collecting large-scale, diverse, and high-quality post-training datasets for autoregressive language models is challenging. Consequently, Supervised Fine-Tuning (SFT) is typically applied to datasets significantly smaller than those used for pre-training, which leads to overfitting and the catastrophic forgetting of the tails of the data distribution. To prevent this collapse, we introduce Ambient SFT, a principled framework for leveraging imperfect predictions to augment the fine-tuning set. In our method, a "frozen" version of the pre-trained model serves as a noisy teacher that the fine-tuned model must match at a coarse level. In particular, we require that the high-temperature versions of the conditional distributions produced by the post-training model should match the high-temperature versions of the pre-training ones. The temperature hyperparameter controls the level of trust in the pre-trained model, with the limit $T\to \infty$ reverting back to regular SFT and $T=1$ to knowledge distillation. We demonstrate that our approach outperforms standard SFT across domain adaptation, instruction-tuning, and reasoning, leading for up to $21\%$ average relative improvement to standard SFT.

新论文 · v1arXiv:2611.23228

Spool:面向混合视觉语言模型的低延迟流式推理

Spool: Low-Latency Streaming Inference for Hybrid Vision-Language Models

Rui Ning, Om Chabra, Hari Balakrishnan

AI 速读 基于摘要

Spool 是一种免训练框架,通过缓存并组合逐帧的循环状态变换,让混合视觉语言模型在滑动窗口视频推理中无需重放旧帧即可剔除过期帧,从而降低首 token 延迟。

cs.CV · cs.LG

查看原文摘要

Applications such as visual accessibility agents and robotics require answering questions about recent video content promptly, over a bounded window of past frames (e.g., the last two minutes). Hybrid vision-language models (VLMs), which interleave attention with linear recurrent layers such as Gated DeltaNet (GDN), are attractive for this setting, but maintaining a sliding window is expensive. The reason is that recurrent layers combine all past frames into a shared state, so expiring old frames normally requires re-running the entire window through the model. We observe that the recurrent update is affine in the state with input-dependent coefficients, so the effect of each frame can be captured as a transformation that composes associatively. We present Spool, a training-free framework that caches per-frame state transformations and composes them efficiently as the window advances, removing expired frames from each recurrent layer's state without replaying frames through the backbone. Removal is exact within each layer; as with key-value eviction in attention, expired frames can retain residual influence through the cached inputs computed by earlier layers. We design a dedicated data structure and GPU kernels to achieve low caching and composition overhead. Across five open-source hybrid VLMs and four video reasoning benchmarks, Spool achieves the lowest p95 time-to-first-token in all 20 model-benchmark tests, reducing it by a geometric mean of $6.6\times$ over the faster of two recent vLLM baselines, while improving accuracy by 2.3 percentage points on average.

新论文 · v1arXiv:2611.23226

FastFrames:交互延迟下的视频生成

FastFrames: Video Generation at Interactive Latency

Gene Chou, Guandao Yang, Fujun Luan, Lars Mescheder, Wei Dong, Stephan Richter, Vladlen Koltun

AI 速读 基于摘要

FastFrames 通过剖析并替换自回归视频扩散推理流程中的 VAE 解码与 KV cache 更新等耗时组件,在保持生成质量的同时把逐帧延迟降到交互级。

cs.CV

查看原文摘要

Autoregressive video diffusion models generate frames based on new observations and inputs, making them a promising medium for interactive visual experiences. However, existing models are orders of magnitude too slow for fluid interaction. This paper introduces FastFrames, a family of fast autoregressive video diffusion models that achieves interactive latency without compromising quality. We profile the inference pipeline of state-of-the-art models and find that operations often treated as fixed implementation details, such as VAE decoding and KV cache updates, in fact account for over half of end-to-end inference latency. We challenge the assumption that these components are indispensable and replace them with lightweight alternatives. Our 1.3B variant runs at 36 ms per frame, or 28 responses per second (RPS), on a single B200 GPU while matching the generation quality of a state-of-the-art model that is nearly 8x slower. Our 14B variant runs at 45 ms per frame, or 22 RPS, on an 8x B200 GPU node and yields significantly better visual quality and realism. We show that FastFrames enables real-time interaction in applications such as camera-conditioned and physics-conditioned video generation.

新论文 · v1arXiv:2611.23365

Training Language Models for Introspective Oversight

Alex Lin Wang, Linus Yifeng Tang, Dami Choi, Neil Chowdhury

原文摘要

Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy. Asking the assistant follow-up questions about its actions is unreliable, since models are generally not trained to report their own misbehavior. As a result, approaches to oversight typically involve querying external models. These face limitations: external transcript monitoring operates only on visible model outputs, and activation decoders lack full context and are prone to confabulation. We introduce introspective oversight, which trains a new role in the model to answer arbitrary questions about the assistant, rewarding answers that are verified against the assistant's actual behavior. We implement this by adding a separate, third-person observer role that answers these queries, which we can train solely for accuracy and separately from the assistant. On five held-out oversight evaluations, an observer trained on Qwen3.6-27B obtains a mean AUROC of 0.907, outperforming honesty training (0.864), transcript monitoring (0.828), and activation oracles (0.796). We further find that training an observer makes the assistant itself easier to monitor, with every baseline method improving on average when applied to the fine-tuned assistant. These results suggest that training models to answer verifiable questions about themselves is a tractable approach to overseeing unintended behavior.

cs.AI

新论文 · v1arXiv:2611.23225

StringQFT:面向AI辅助理论物理的多用途教科书资源

StringQFT: A Multiuse Textbook Resource for AI-Assisted Theoretical Physics

Xingyang Yu

AI 速读 基于摘要

StringQFT 是一套18卷的弦论量子场论教科书集合,同时提供基准题库、检索记录、训练数据示例和计算工具,以支持AI辅助理论物理研究。

hep-th · cs.AI

查看原文摘要

We present StringQFT as a textbook collection for string constructions of quantum field theory and as infrastructure for AI-assisted theoretical physics. The collection comprises 18 volumes, 190 chapters and 3,795 pages, covering brane probes, brane webs, geometric engineering, F-theory constructions, wrapped M5-branes and exact worldsheet constructions. Its open-book benchmark inventory contains 1,073 items, including 499 with automatic finite-answer checking. For retrieval-augmented generation, it provides 1,371 section records linked to textbook sources and PDF locations, together with a local lexical retriever. Training-data preparation is illustrated by 21 private, source-linked examples. For agents, it exposes 19 calculation tools with specified inputs and finite domains, connecting tool use to textbook derivations. We illustrate these uses through specific questions, retrieved passages and finite calculations. The textbook collection and accompanying resources are available at https://github.com/xingyang-yu/StringQFT.

新论文 · v1arXiv:2611.23364

Neural Circuit Architectural Priors for Rat Locomotion

Nikhil X. Bhattasali, Jaron Cui, Lerrel Pinto, Grace W. Lindsay

原文摘要

Animals generate behavior through continuous interactions between their neural circuits, bodies, and environment. Embodied simulations study these interactions by testing neural circuit models in biologically realistic settings. Recent efforts have simulated diverse animals, and emerging work on biologically grounded neural architectures has begun to integrate circuit connectivity and single-unit dynamics from experimental data into artificial neural networks, introducing stronger inductive biases and closer mechanistic alignment with biology. How can we develop embodied simulations that enable the study of increasingly complex bodies and neural circuits? In this work, we address the challenge through coordinated advances in the simulated body, neural architecture, and training infrastructure. We introduce Rat v2, an efficient and flexible biomechanical body for simulating rat behavior. To control this body, we develop Rat NCAP, a biologically grounded neural architecture for locomotion based on mammalian spinal circuits that incorporates cell-type-specific connectivity and a novel flexor-extensor neuromechanical interface. To optimize circuit parameters, we develop GPU-accelerated simulation and training infrastructure. The model learns to locomote at different speeds and transition between gaits without imitation learning, producing locomotion statistics, kinematics, and cell-type-specific neural activity consistent with experimental data. Analyses reveal that the neuromechanical interface substantially affects trainability and gait quality, and in silico cell-type ablations reproduce known gait phenotypes and predict gait changes under graded perturbations. Together, these findings support the view that embodied simulations at an intermediate level of abstraction can simultaneously reproduce complex behavior and yield mechanistic insights into the neural circuits that generate it.

q-bio.NC · cs.AI · cs.LG · cs.NE · cs.RO

新论文 · v1arXiv:2611.23221

约束凸有限和优化的非精确随机方差缩减梯度法

An inexact stochastic variance-reduced gradient method for constrained convex finite-sum optimization

Zhaosong Lu, Yifeng Xiao

AI 速读 基于摘要

提出一种非精确SVRG方法,显著改进约束凸有限和优化中计算ε-SFSO解的一阶预言机复杂度,并给出确定性锥优化的新方法。

math.OC · cs.LG

查看原文摘要

In this paper, we study a class of constrained convex finite-sum optimization problems. In many practical applications, all or some of the constraints are hard constraints that represent imperative requirements. Consequently, any desirable approximate solution must (nearly) satisfy these constraints. Motivated by this, we focus on computing an $ε$-$surely\ feasible\ stochastic\ optimal$ ($ε$-SFSO) solution, in which the constraint violation is deterministically bounded by $ε$, and the expected optimality gap is at most $ε$. While a recently proposed stochastic variance-reduced first-order penalty method can compute an $ε$-SFSO solution, there remains a significant gap between its first-order oracle complexity for computing an $ε$-SFSO solution and that for computing an $ε$-$expected\ feasible\ stochastic\ optimal$ solution, where both the expected constraint violation and the expected optimality gap are bounded by $ε$. To narrow this gap, we propose an inexact stochastic variance-reduced gradient (SVRG) method that significantly improves the previously best-known first-order oracle complexity for computing an $ε$-SFSO solution. Furthermore, when the objective consists of a single function, the proposed method reduces to a novel deterministic first-order method for solving standard convex conic optimization. It achieves a significantly lower gradient evaluation complexity with respect to the objective function compared to existing methods, and can outperform them when computing constraint gradients and projections onto the associated cone is cheaper than evaluating the objective gradient. Preliminary numerical results are presented to illustrate the performance of the proposed method.

新论文 · v1arXiv:2611.23219

LLM智能体还需要被告知如何自我改进吗?

Do LLM Agents Still Need to Be Told How to Self-Improve?

Shobhita Sundaram, Cansu Sancaktar, Phillip Isola

AI 速读 基于摘要

作者让冻结的LLM智能体在仅给定基本原语、资源和总体目标的情况下自行设计基于上下文的自我学习算法,发现能力足够强的模型能够自我改进,且学到的文本产物可迁移到外部基准。

cs.LG · cs.AI

查看原文摘要

LLM agents increasingly drive their own learning. Self-improvement methods delegate various components of model optimization to the models themselves. As models become more capable, this motivates a basic question: do these increasingly capable models still need us to specify how they should self-improve? In this paper we study an autonomous paradigm in which, given basic primitives, resources, and a general goal for self-improvement, agents construct their own self-learning algorithm for context-based optimization. Using the setting of gameplay as a testbed, a frozen LLM agent is given a compute budget and tools for collecting experience and updating text documents, and allowed to freely experiment without an externally imposed loop or access to real-world data. We find that sufficiently capable models do self-improve under these conditions, demonstrating strategies that align with classic cognitive frameworks for self-regulated learning and constructs from machine learning literature on self-generated curricula. Furthermore, we study the extent to which the learned text artifacts transfer to external benchmarks, observing improvement across different game horizons, mechanics, and 3D navigation.

新论文 · v1arXiv:2611.23218

偏见头测量的是什么?头级偏见归因中的不可识别性

What Does a Bias Head Measure? Non-Identifiability in Head-Level Bias Attribution

S. M Seefat Alam

AI 速读 基于摘要

作者审计头级偏见归因方法,发现其统计量主要由提示身份驱动,且无法区分标签、长度与受保护群体标记,同时偏见选择性并非晚层集中,消融头集也未降低不公平率。

cs.CL · cs.LG

查看原文摘要

Methods that localise social bias in large language models to individual attention heads and remove it by ablation are validated by their effect on a fairness metric, never by evidence that the statistic selecting the heads measures bias. We audit this on Qwen-2.5-7B-Instruct and Llama-3.1-8B-Instruct. The head map correlates at $ρ= -0.950$ and $-0.768$ with a label-blind response-length map, apparently identifying a surface confound. An intervention that breaks the length-label coupling rejects this reading: with the prompt held fixed, response length explains 1% of the statistic's variance. What does explain it is prompt identity, at 64% of variance, in an ordering that is not monotonic in length. Within any fixed prompt the fairness label, response length and the presence of a protected-group token are collinear at $φ= 0.95$, partly by definition of the labelling rule, so no observational analysis can attribute the map to any of them, and no method in this family performs an experiment that could. The substantive claims fail independently: bias selectivity is not late-layer-concentrated on either model under either reference reading, and no head set we tested reduces the unfairness rate when ablated. Its complement, scored on the opposite label, reliably destroys refusal behaviour ($p = 2.7\times10^{-5}$), demonstrating that the pipeline detects effects at this scale.

版本更新 · v2arXiv:2606.10377

双向随机投影

Bidirectional Random Projections

Chao Lan, Luyuan Yang

AI 速读 基于摘要

在固定设计下分析普通最小二乘回归的双向随机投影,给出基于(WXR, WY)的OLS估计器的期望超额损失上界,并说明其与单向投影上界的差距约以O(1/n1)衰减。

math.ST · cs.LG

查看原文摘要

This paper analyzes bidirectional random projections for ordinary least squares (OLS) regression under the fixed design setting. Let $(X, Y) \in \mathbb{R}^{n\times p}\times\mathbb{R}^{n}$ be a sample and $W \in \mathbb{R}^{n_1\times n}$, $R \in \mathbb{R}^{p\times p_1}$ be two random projections. We develop an expected excess loss bound for the OLS estimator built on $(WXR, WY)$, extending an established bound for the OLS estimator built on $(XR, Y)$. Our analysis shows that our bound is larger and the gap between the two bounds decays at a rate of approximately $O(1/n_1)$. These findings are confirmed by numerical results.

新论文 · v1arXiv:2611.23216

Higher-Scoring Coding Models Did Not Get More Work Done

Yining Hua

原文摘要

New coding models advertise themselves on score improvements of coding benchmarks. Yet no study has tested if a model that scores higher on these benchmarks gets more real work done. On June 12, 2026, a U.S. export control directive banned access to Claude Fable 5 for 19 days, which forced users to switch to other models. During this time, most former Fable 5 users switched to Opus 4.8 (11 points lower on SWE-Bench Pro compared to Fable 5). We treat this suspension as a natural experiment, where the people and projects stayed the same and only the model changed, so we could isolate the effect of Fable 5 on user productivity. We tracked GitHub pull requests of 297 Fable 5 users before, during, and after the suspension. We used 8,908 developers who stayed on Opus 4.8 all the time as the control group. We also repeated the comparison across five model upgrades before and after the suspension in 2026 (1,208 developers, 15,442 pull requests). Fitting a difference-in-differences model with developer and date fixed effects, we found that having access to Fable 5 increased the 7-day merge rate of pull requests by only 1.4 percentage points [-1.4; +4.3], which was not statistically significant. Similarly, no significant increases of merge rates were found with the upgrades (weighted mean: -0.9 percentage points [-1.9; +0.2]); all five estimates were negative (95% intervals included 0, did not differ from each other). We also did not observe a significant increase in the number of pull requests merged per week (+2.4% [-4.9%; +10.2%]).

cs.SE · cs.AI · cs.LG

新论文 · v1arXiv:2611.23215

基于模型信息鲁棒几何DDPC的反馈线性化轨迹跟踪

Feedback-Linearised Trajectory Tracking via Model-Informed Robust Geometric DDPC

Pranav Gupta, Deepan Muthirayan, Ravi Banavar

AI 速读 基于摘要

该文提出一种结合模型反馈线性化与几何鲁棒数据驱动预测控制的方法,用于全驱动机械臂的轨迹跟踪,并在平面2R机械臂仿真中与双积分MPC和DeePC进行比较。

cs.RO · eess.SY

查看原文摘要

Data-driven predictive control (DDPC) predicts system responses from recorded trajectories, but nonlinear dynamics can limit the accuracy of fixed linear predictors. This paper studies geometric robust DDPC for trajectory tracking of a fully actuated manipulator using model-based feedback linearisation. A mechanical model maps virtual acceleration commands into joint torques, while recorded data capture residual dynamics arising from imperfect model parameters. The controller minimises worst-case prediction error over an open Grassmannian ball centred at the fitted trajectory subspace. Simulations on a planar 2R manipulator under gravity compare the proposed method with double-integrator model predictive control (MPC) and direct regularised data-enabled predictive control (DeePC). Results show improved tracking over double-integrator MPC despite increased torque effort, while performance relative to DeePC depends on the reference trajectory.

版本更新 · v2arXiv:2611.21479

LynnReal-Hand:用手部控制解锁世界交互

LynnReal-Hand: Unlocking World Interaction with Hand Control

Shaohao Rui, Chaoyang Zhang, Xiaofeng Mao, Weijie Ma

AI 速读 基于摘要

提出一种手控视频世界模型,通过大规模数据、手部感知监督和高效流式生成,实现精确的手部交互与实时视频生成。

cs.CV · cs.AI

查看原文摘要

Interactive video world models enable exploration through text and camera controls, yet direct object interaction requires finer control. Hands provide a natural interface, but translating continuous hand movements into coherent visual responses remains challenging because of complex hand-object dynamics and demanding real-time computation. To address these challenges, we introduce LynnReal-Hand, a hand-controlled video world model that unifies precise interaction modeling with efficient streaming generation. We curate 100K interaction clips spanning diverse real and synthetic environments and develop hand-aware supervision to improve fine-grained hand motions and object interactions. Building on this foundation, we learn a causal flow map for few-step generation and introduce region-aware score distillation that combines complementary video and image priors to refine interaction dynamics and visual appearance. To further reduce inference latency, we propose Ultra-Fast-VAE, a compact video decoder that preserves high reconstruction fidelity with substantially lower computational cost. Extensive evaluations on HandBench demonstrate superior hand-following accuracy and visual quality compared with existing approaches. Our full-sequence model achieves an FVD of 181.67 and a MANO Dice score of 93.02, while the three-step causal model maintains a MANO Dice score of 92.49. For real-time interaction, 540p streaming on a single H200 reaches 18.03 FPS with 741ms latency and an optimized peak GPU memory footprint of only 34.89GB. We will release the datasets, model weights, and the full training and inference code to support research on hand-controlled video world models.

版本更新 · v2arXiv:2506.20630

带确定性约束的随机与有限和凸优化的一阶方法

First-order methods for stochastic and finite-sum convex optimization with deterministic constraints

Zhaosong Lu, Yifeng Xiao

AI 速读 基于摘要

针对带确定性约束的随机与有限和凸优化,提出以加速随机梯度方案求解二次罚子问题、从而获得约束违反确定有界且期望最优间隙受控的ε-SFSO解的一阶方法。

math.OC · cs.LG · math.NA

查看原文摘要

In this paper, we study a class of stochastic and finite-sum convex optimization problems with deterministic constraints. Existing methods typically aim to find an $ε$-$expected\ feasible\ stochastic\ optimal$ solution, in which both the expected constraint violation and the expected optimality gap are within a prescribed tolerance $ε$. However, in many practical applications, constraints must be nearly satisfied with certainty, rendering such solutions potentially unsuitable due to the risk of substantial violations. To address this issue, we propose stochastic first-order methods for finding an $ε$-$surely\ feasible\ stochastic\ optimal$ ($ε$-SFSO) solution, where the constraint violation is deterministically bounded by $ε$ and the expected optimality gap is at most $ε$. Our methods apply an accelerated stochastic gradient (ASG) scheme or a modified variance-reduced ASG scheme $only\ once$ to a sequence of quadratic penalty subproblems with appropriately chosen penalty parameters. We establish first-order oracle complexity bounds for the proposed methods in computing an $ε$-SFSO solution. Preliminary numerical results are presented to illustrate the performance of the proposed methods.

新论文 · v1arXiv:2611.23212

EviSlide-MIL:用于类增量全切片图像分类的多查询池化与共享预测

EviSlide-MIL: Multi-Query Pooling and Shared Prediction for Class-Incremental Whole-Slide Image Classification

Zhouhan Qian, Sicheng Chen, Chad Wong, Tianyi Zhang, Enhui Chai, Zeyu Liu, Fei Xia

AI 速读 基于摘要

EviSlide-MIL 通过每类多查询池化与共享预测模块,结合经验回放和知识蒸馏,缓解全切片图像类增量分类中的遗忘问题。

cs.CV

查看原文摘要

Histopathological analysis of whole-slide images (WSIs) plays a critical role in cancer diagnosis, and multiple instance learning (MIL) is widely adopted for WSI analysis under weak supervision. As new tumor subtypes are introduced, extending existing MIL models requires learning new classes while retaining knowledge of previously learned ones. This presents a class-incremental learning challenge, where models must acquire new classes with limited access to historical training data and recognize all learned classes without task identifiers at inference. A major obstacle is forgetting, as updates to feature aggregation and prediction modules can degrade performance on previously learned classes. To address this challenge, we propose \textbf{EviSlide-MIL}, a class-incremental WSI framework that integrates multiple learnable queries per class with a shared prediction module. The queries aggregate frozen patch features into class-specific representations, while the shared prediction module limits parameter growth across incremental stages. By freezing queries associated with previously learned classes, EviSlide-MIL preserves their attention patterns for identical inputs, while experience replay and knowledge distillation further mitigate forgetting as shared parameters are updated. Experiments on eight tumor subtypes from The Cancer Genome Atlas demonstrate that EviSlide-MIL achieves improved performance and reduced forgetting compared with competing methods across most learning settings, demonstrating its potential for scalable and knowledge-preserving WSI classification. Code and pretrained models will be released.

新论文 · v1arXiv:2611.23209

从人类注视中学习有依据的推理

Learning Grounded Reasoning from Human Gaze

Gabriel Sarch, Declan Campbell, Nicholas Budny, Kia Ghods, Katerina Fragkiadaki, Jonathan D. Cohen, Brenden M. Lake, Taylor W. Webb

AI 速读 基于摘要

利用人类注视作为先验引导视觉语言模型进行有依据的推理,在保持与人类行为对齐的同时提升视觉推理表现。

cs.CV

查看原文摘要

Human visual reasoning is driven by systematic exploration and extraction of task-relevant visual evidence. Human gaze provides a window into this process, making gaze a useful source of guidance for visually-grounded reasoning in vision-language models (VLMs). However, human gaze also includes noise and redundancies that may transfer poorly to VLMs. In this work, we investigate how human gaze data can be effectively leveraged to improve visual reasoning in VLMs, while maintaining alignment with human behavior. We collect 7,109 human gaze trials from a diverse and challenging set of visual reasoning tasks, and train grounded reasoning models with different forms of gaze guidance. Across evaluations in chart understanding, visual search, and counting, we find that using human gaze as a prior for grounded reasoning consistently outperforms supervision using the full gaze sequence. Based on these findings, we introduce GGR (Gaze-Guided Reasoner), which achieves greater human alignment and more reliable visual grounding while matching or outperforming leading grounded-reasoning baselines in accuracy. Reinforcement learning further improves task accuracy, gaze alignment, and grounding quality despite using no gaze supervision. Behavioral analyses show that gaze supervised models exhibit more visual exploration before arriving at an answer. Our results suggest that the value of human gaze lies in guiding spatial exploration and shaping reasoning behavior without requiring complete imitation of human behavior.

新论文 · v1arXiv:2611.23208

面向黑盒生成模型的无失真语义水印

Distortion-Free Semantic Watermarks for Black-Box Generative Models

Aviv Yossef, Or Patashnik, Or Zamir

AI 速读 基于摘要

提出一种仅需黑盒采样与语义嵌入查询的无失真语义水印算法,并训练图像编码器平衡变换稳定性与生成区分度。

cs.LG · cs.CR · cs.CV

查看原文摘要

We present a provably distortion-free semantic watermarking algorithm that requires only black-box sampling access to a generative model and black-box access to a semantic embedding. A watermark is called distortion-free if, averaged over its secret detection key, it leaves the generator's output distribution unchanged; this provides a formal guarantee that watermarking does not reduce output quality. Conventional such watermarks are often brittle to transformations. This is especially problematic for images, where benign operations such as compression, cropping, or resizing change the entire pixel representation. Semantic watermarks therefore require detection to be robust to content-preserving transformations. Previous methods combining these properties rely heavily on specific white-box properties of the underlying model: either to autoregressive text generation or to diffusion-specific access, such as control of the initial noise or diffusion inversion. In contrast, our construction is fully generic: It only interacts with the generative model and the semantic embedding, a function that determines the notion of "preserving content" under which detection should be robust, via sample and query access. We then instantiate this framework for image generation. We characterize the two competing properties required of the semantic embedding: it should remain stable under transformations that preserve an image's content, but should distinguish independent generations from the same prompt. We train an image encoder directly for this tradeoff. The resulting encoder improves separation while maintaining stability over off-the-shelf alternatives and enables strong aggregate detection while remaining robust to various transformations. We demonstrate the effectiveness of our watermark scheme on both open-source and closed models, which is possible only due to restriction to black-box access.

新论文 · v1arXiv:2611.23206

阅读场景状态:揭示视觉语言模型中的安全失效

Reading Scene States: Uncovering Safety Failures in Vision-Language Models

Tongxi Wu, Yuyang Cheng, Jiacheng Xian, Menglin Yang, Kai Chen, Jian Zhang, Yang Gao

AI 速读 基于摘要

论文识别出视觉语言模型的“场景状态安全漏洞”,并构建基准与攻击方法 S3TA,作者报告其攻击成功率显著高于基线。

cs.CV · cs.AI

查看原文摘要

Vision-language models (VLMs) can provide harmful assistance by interpreting visual events, even without an explicit request for the underlying harmful objective. We identify this \textbf{scene-state safety vulnerability} and introduce \textbf{SceneSafetyBench}, comprising 375 image--question pairs spanning Initial, Medium, and Ultimate scene states and five visual presentations. Across eight VLMs, scene-state inputs elicit harmful assistance with attack success rates (ASRs) of 45.6--72.3\%. Comparative analysis across three VLMs shows that scene-state inputs most closely resemble QR-related images in their layer-wise safety-related signal profiles, while exhibiting lower average late-layer readouts and distinct signal dynamics during generation. To turn this vulnerability into a systematic attack, we propose \textbf{S3TA}, which translates harmful objectives into scene states, queries image--question pairs independently, and assembles the responses. On seven MM-SafetyBench categories across eight open-weight and commercial VLMs, S3TA achieves a model-average ASR of \textbf{71.2\%, exceeding the strongest baseline by 6.1 percentage points}. Text-side filters and visual moderation provide limited protection. These findings highlight the need to safeguard the assistance models infer through scene-grounded reasoning, beyond screening input content.

版本更新 · v2arXiv:2607.05114

局部化LoRA-MoE:自适应路由的低秩专家混合

Localized LoRA-MoE: Mixture of Low-Rank Experts With Adaptive Routing

Babak Barazandeh, Subhabrata Majumdar, Vinay Prithyani, George Michailidis

AI 速读 基于摘要

提出Localized LoRA-MoE框架,结合局部空间分块与上下文条件专家路由,以缓解LoRA在交错多上下文训练中的梯度干扰问题。

cs.LG · cs.AI · cs.CL

查看原文摘要

Parameter-efficient fine-tuning (PEFT) methods such as LoRA adapt large models through a single low-rank update. Such updates are susceptible to gradient interference: when a training stream interleaves multiple operational contexts, conflicting updates to shared adapter weights collapse the adapter into an unspecialized average. While recent methods introduce block-wise isolation to remedy this issue, their topologies are static and cannot adapt to context switching or localized sensor degradation. In this work, we introduce Localized LoRA-MoE, a framework that combines localized spatial blocking with context-conditioned expert routing. We propose and evaluate two architectural variants: Block-Wise LoRA-MoE (centralized routing), which modulates the entire structural grid through a single context-conditioned gate, and Cell-Wise LoRA-MoE (decentralized routing), which assigns an independent gate to every coordinate cell of the matrix grid. Across three structured transformation benchmarks--a high-dimensional SVD matrix simulation, context-switched transformations over real tabular data, and spatial reconstruction under simulated sensor occlusion--both variants outperform static baselines under comparable adapter budgets. Both variants perform similarly when context shifts the grid uniformly, while cell-wise routing is strictly better when contexts are spatially heterogeneous. When fine-tuning a language model on six interleaved GLUE tasks, task-conditioned routing at a fixed adapter budget outperforms LoRA and static localized adapters, matching per-task adapters with 6x budgets. At decoder scale on Qwen2.5-1.5B, both routed variants outperform static baselines across eight commonsense benchmarks, with cell-wise routing achieving +3.9 points over LoRA at matched active capacity.

新论文 · v1arXiv:2611.23205

Fine-Tuning Gemma 4 Edge Models for MATLAB Signal-Processing Code with SFT and QLoRA on a Laptop iGPU

Mehmet Altan Toksöz

原文摘要

Small language models that run on a laptop are attractive for writing signal-processing code offline, but they make systematic errors on digital signal processing (DSP) conventions. We apply supervised fine-tuning (SFT) to the Gemma 4 edge models E2B and E4B with 66 checked examples covering 11 signal-processing MATLAB subtasks, using low-rank adaptation (LoRA) and quantized LoRA (QLoRA) on the integrated GPU (iGPU) of a laptop, and deploy the 8-bit integer (int8) models with the adapters through OpenVINO. On held-out variants scored by deterministic checkers, the pass rate rises from 18/66 to 37/66 (LoRA) and 37/66 (QLoRA) for E2B and from 32/66 to 47/66 for E4B (QLoRA). Reading all 159 failing programs shows that the adapters remove most errors of convention, such as the sign of a lag, units and array shapes, but few errors in building signals and noise. Applied at run time, the adapter costs 17-19% of the generation speed.

cs.LG · cs.AI · cs.SE · eess.SP

新论文 · v1arXiv:2611.23202

Agent Trust Infrastructure(ATI):面向跨组织自主AI智能体的联邦身份、信任、证明与问责架构

Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attestation, and Accountability Architecture for Cross-Organization Autonomous AI Agents

Viet K. Nguyen, Mohammad I. Husain

AI 速读 基于摘要

作者提出并实现ATI——一种基于PKI、零信任架构与远程证明的框架无关安全层,用于跨组织AI智能体的身份验证、配置完整性核验与授权,并在模拟联邦环境中报告了攻击遏制率提升与微秒级开销。

cs.AI

查看原文摘要

AI agents increasingly collaborate across organizational boundaries, invoking tools and interacting with agents operated by independent entities. Although existing agent frameworks support planning and coordination, they lack a common mechanism for verifying cross-organizational agent identity, execution integrity, and authorization. We propose the Agent Trust Infrastructure (ATI), a framework-independent security architecture built on Public Key Infrastructure (PKI), Zero Trust Architecture (ZTA), and remote attestation. ATI establishes federated trust through peer organizational certificate authorities (AgentCAs), eliminating the need for a shared root authority. Before executing requests, ATI validates agent certificates, verifies approved model, tool, and system-prompt configurations, and enforces authorization through three policy checks. We implement ATI as an external security enforcement layer that integrates with existing agent frameworks without modifying their underlying models. We evaluate ATI in a simulated federation of eight organizations using six agent frameworks, each deploying a five-agent team. Security experiments involve two organizations and assess 14 attack scenarios and six benign tasks across five agent models, using five attack variations and three repetitions per variation. A panel of judge models evaluates the experimental outcomes. With all enforcement mechanisms enabled, attack containment increases from 43% to 84% (40% to 80% for the 11 attack scenarios evaluated consistently across all configurations), while enforcement introduces approximately 174 microseconds of overhead per request. ATI is released as an open-source, framework-independent package that uses IETF WIMSE workload token formats for identity and request verification and Entity Attestation Tokens for model, tool, and system-prompt integrity verification.

版本更新 · v2arXiv:2610.02001

Mingbird:一个本地优先的智能体框架,使小型开放模型能够完成真实任务

Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks

Hao Wang, Ting Huang

AI 速读 基于摘要

Mingbird 是一个面向十亿参数级小型开放模型的本地智能体框架,通过完成控制等机制提升多步任务完成率。

cs.AI · cs.CL

查看原文摘要

Small open-weight language models now run on a laptop, but they fail at multi-step work in ways a large model does not: they stop with the files missing, repeat one action until the budget ends, and report success without checking. At the one-to-nine-billion-parameter tier the harness supplies almost all of the procedural control that a large model supplies for itself.We present Mingbird, an open-source harness for that tier on a consumer graphics card: 12k lines of Python, a 628-test suite, and eighteen mechanisms for context economy, completion, time budget and the host boundary, plus a crawl guard outside those four groups. Its design point is completion control: the harness runs executable checks on the working directory and refuses a claim of completion when they fail.Five evaluations accompany it. A configuration-surface audit finds four defects that the 625-test suite of v3.1.1 missed, each because a test checked a property adjacent to the one that broke. A ten-task probe suite gives each mechanism a reason to fire and reports where the change reaches the artifact, including one mechanism that cuts the signal it protects. Disabling five of six completion-time checks costs 0.152 of the artifact score on eighteen held-out tasks, three replications per cell (95% CI [+0.064, +0.246], Holm p = 0.014). On a 288-cell matrix the harness reaches 0.886 against 0.631, 0.479 and 0.405 for three open scaffolds, and on τ 2 -bench it ranks first or tied first in all three domains against the arms evaluated.Tasks, scorer, source and every per-cell result are public.

新论文 · v1arXiv:2611.23198

降采样观测频率下学习型与运动学轨迹预测的对比

Learned versus Kinematic Trajectory Prediction under Reduced Observation Frequency

Nukhbala Gadzhiev, Alexander Morochko

AI 速读 基于摘要

在Argoverse 2上把历史观测从10 Hz降采样到5/2/1 Hz后,作者报告频率专用LSTM RNN相对常速度/常加速度模型的优势并未消失,但行人场景下常速度模型更准。

cs.LG · cs.RO

查看原文摘要

Trajectory prediction models for automated driving are usually trained on data with a fixed sampling frequency, while positions received via vehicle-to-everything (V2X) communication arrive at 1-10 Hz. We study whether a learned predictor that uses only the observation history keeps its advantage over constant velocity (CV) and constant acceleration (CA) models when the history frequency drops. On the Argoverse 2 motion forecasting dataset, the 5 s history of the focal agent was downsampled from 10 Hz to 5, 2, and 1 Hz, and the 6 s future was predicted without maps or neighboring agents. An LSTM-based recurrent neural network (RNN) trained for each frequency was compared with the same network trained at 10 Hz and applied to sparse histories after linear interpolation. Hypotheses and thresholds were fixed before training, the main RNNs were trained with ten seeds each, and results on 24,984 test scenarios have bootstrap confidence intervals over scenarios and seeds. The average displacement error of the frequency-specific RNN grew by 3.1% at 5 Hz, 10.1% at 2 Hz, and 20.3% at 1 Hz. Contrary to our hypothesis, its advantage over the better kinematic model did not vanish on straight motion and was 24-30% on both straight motion and turns at every frequency, while for pedestrians CV was more accurate. The 10 Hz model with interpolation was at most 1.3% less accurate than the frequency-specific model down to 2 Hz but 11.5% less accurate at 1 Hz. Each hypothesis was only partly supported.