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

+0新增论文
+0其中 AI 相关
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-15 18:02 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-14 18:31 — 2026-11-15 18:31（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：2026-11-15 18:02最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

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

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 73 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-15 18:01（北京时间）
新论文 · v1arXiv:2611.16701

Sprint3D: Accelerating End-to-End 3D Asset Generation through Pipeline Optimization

Sho Kuno, Ruihan Yu, Yonghao Yu, Guixu Lin, Lian Fu, Muyao Niu, Yu-Ju Tsai, Zheng-Hui Huang 等 14 位作者

原文摘要

Image-to-3D generative models now produce asset-quality textured meshes, but at minutes per asset they remain slow to iterate with and costly to deploy. Prior work has mostly accelerated the sampling of the networks, and where it also optimizes the mesh processing, it trains its own generators. We instead start from a publicly released pipeline and ask how much of its end-to-end time can be saved. Profiling the public Pixal3D pipeline shows that its latency is dominated by what happens after the networks: the four rectified flows take 14% of the wall-clock time and mesh post-processing takes 85%, most of it in CPU-based UV unwrapping. We therefore first rebuild the mesh post-processing on the GPU and take it off the critical path, then cut the per-evaluation overhead of the flows and distill them from 76 to 8 network evaluations. The resulting pipeline, Sprint3D, reduces the median time per asset from 133 s to 4.05 s on one H200 GPU at the same export settings (33$\times$). At the same time, on 2,653 held-out Toys4K objects it improves every input-view normal metric of the Pixal3D protocol, with a slightly lower mean silhouette IoU, lower point-cloud alignment scores and less fine texture detail. The rebuilt post-processing alone also speeds up TRELLIS.2, which uses the same export code, by 6.7$\times$ without a detectable change in the evaluated metrics.

cs.CV · cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16498

How many LLM-labelled rows does a decision encoder need, and how wrong can the labels be?

Mohammed Nayeem Khan, Aliyas Ahmad Misri

原文摘要

A decision encoder such as Laya reads a question with named options (for example, which department should handle a ticket) and a text, and picks an option. It reads both in one forward pass and returns a probability for every option, without writing any text. We ask how many LLM-written training rows such an encoder needs and how wrong those labels may be. We ran 19 fine-tunes of Laya (ModernBERT-large) on nested subsets of a 2,818-row pool and scored them on 1,065 held-out items from the same generator, so every test item is in-distribution and no out-of-family test was run. Accuracy rises from 69.4% before fine-tuning to 74.3% with 5% of the rows, 84.8% with 50% and 86.9% with all rows. The curve flattens, and a saturating fit with bootstrap intervals cannot pin down its plateau. Seed spread at 20% of the rows (s.d. 1.6 points) exceeds some of the steps between sizes. Giving small subsets as many updates as the full pool gains 1.9 points at 5% and 1.9 points at 20% of the rows (one seed; p=0.14 and 0.13), and at 20% that is below the 2.3-point difference between two ordinary seeds. A single run with 10% symmetric label noise shows no detectable change (-0.2 points, 95% interval -1.7 to +1.4); 20% costs 3.4 points and 40% costs 8.7 points. Confusable-pair noise at 20% costs 7.4 points, and under noise the model moves from over-confident to under-confident. An independent labeller disagrees with the gold labels on 3.5% of held-out items, and about half of its choice disagreements (16 of 33, leaving each item out of the partner map) name the partner option that the confusable-pair noise uses. Laya is +0.9 points ahead of a TF-IDF classifier trained on the same rows at full size (the interval includes zero) and +21.1 points ahead at 5% of the rows. Everything is synthetic, LLM-labelled and from one backbone, one trainer and mostly one seed.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16447

A $Θ(n)$-Multiplicative Improvement of the Gilbert-Varshamov Bound for Linear and Quantum Codes

Chen Yuan, Ruiqi Zhu

原文摘要

The Gilbert-Varshamov (GV) bound is a fundamental benchmark for the existence of error-correcting codes. For non-linear $q$-ary codes of code length $n$, its finite length form is known to admit a multiplicative improvement of order $Θ(n)$. In contrast, for $q$-ary linear codes of arbitrary rates, the best previously known general improvement was only of order $Θ(\sqrt n)$. This leaves open whether the algebraic constraint of linearity inherently prevents a linear-order refinement. We show that it does not. For every fixed prime power $q$ and relative distance $0<δ<1-1/q$, we obtain a $Θ(n)$-multiplicative improvement of the GV bound for $q$-ary linear codes of arbitrary rate, matching the corresponding result for nonlinear codes. Our proof is based on a simple change of viewpoint. Rather than requiring the initial random linear construction to contain no low-weight vectors, we allow $O(n)$ low-weight points, show that they are independent in the underlying projective space, and then eliminate all of them simultaneously at the cost of a single dimension. The key probabilistic ingredient is an exponential bound on nontrivial linear dependencies among low-weight vectors. We further show that this approach can be extended to quantum codes despite the symplectic self-orthogonality constraint. We obtain a $Θ(n)$-multiplicative improvement of the quantum GV bound for every fixed $0<δ<1-1/q^2$ satisfying $H_{q^2}(δ)<1/2$. Thus, the same $Θ(n)$ finite length improvement is applicable to both general linear structure and symplectic self-orthogonality.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36777

S3-S2ST: Semantically Supervised Streaming Speech-to-Speech Translation

Yuxiang Zhao, Zhiyun Fan, Yu Pu, Yanjie An, Yushen Chen, Wenrui Liang, Baiji Liu, Yunchong Xiao 等 14 位作者

原文摘要

Streaming speech-to-speech translation requires timely decisions about when partial input is sufficient for accurate translation. We present S3-S2ST, a model that learns to translate and speak from semantically aligned streaming supervision. By converting utterance-level speech pairs into incremental training examples, we teach a learned policy when to commit translations. Its adjustable threshold controls the quality--latency tradeoff on a fixed 640\,ms input grid. S3-S2ST delivers competitive English--Chinese translation on FLEURS and leads the evaluated streaming systems in translation quality on the internal 9-pair test set. On RealSI, adapting the threshold to buffered speech further improves quality over a low fixed threshold with little change in first-audio latency. We have released the training and inference code and 4B model weights at https://github.com/QwenAudio/S3-S2ST

cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16114

ADAPT: Agentic Diff-Aware Patch Testing for Pull Requests

Vahid Haratian, Atakan Akar, Eray Tüzün

原文摘要

Modern software development relies on pull requests (PRs) that introduce small, targeted code changes. Once merged, these changes should be protected by focused tests that exercise the behavior the PR introduces, yet developers often submit PRs without such tests, leaving the new behavior unguarded against future regressions. Most test generation techniques target entire software units and optimize objectives such as code coverage rather than the behavior a change introduces, and prior diff-aware approaches have had limited success in capturing it. We propose ADAPT (Agentic Diff-Aware Patch Testing), a regression test generation approach that uses an autonomous coding agent to produce change-focused tests for PRs. Given a PR, the agent analyzes the diff between the base and head versions to identify the modified functions and their context, then plans and generates candidate unit tests. A dedicated fail-to-pass (F2P) verification tool runs each candidate on both versions and, after F2P success, reports which executable changed lines remain uncovered; guided by this feedback, the agent iteratively refines its tests. We evaluate ADAPT on the same 426 real-world PRs used by the prior state-of-the-art baseline, with GPT-4o and GPT-5-mini. ADAPT+GPT-4o reaches an F2P rate of 62.0% (264/426), compared with BLAST's reported 35.4% (151/426), while ADAPT+GPT-5-mini reaches 89.9% (383/426). On 137 PRs shared with Change And Cover (ChaCo), ADAPT achieves full patch coverage on 83.9% of PRs, compared with 79.6% for ChaCo, at considerably lower time and cost. A manual evaluation confirms that the F2P-valid tests target each PR's intended change, with mean scores of up to 4.54/5 for importance, 4.35/5 for assertion strength, and 4.49/5 for readability, often covering behavior beyond the developer-written tests.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15829

Training Calibrated Conditional Generative Models with a Sample-Only Coverage Loss

Benjamin Remy, Raphael Rossellini, Chihway Chang, Rebecca Willett

原文摘要

Conditional generative models have become the tool of choice for sampling posteriors in scientific inverse problems, where we seek to sample images or signals conditioned on a set of indirect and noisy measurements. Yet they are often overconfident, which is a critical failure in scientific applications where accurate uncertainty quantification is essential. Existing regularizers fall short in complementary ways: differentiable coverage objectives require the model's density and do not identify the posterior, while strictly proper scoring rules such as the energy score need only samples but do not directly enforce coverage. We close this gap by introducing a differentiable loss function based on the expected coverage probability, estimated from samples alone. It applies to any conditional generative model, with no need for tractable densities or architectural changes. We prove that it is a strict divergence, vanishing if and only if the model equals the true posterior. On simulation-based inference benchmarks, it matches a density-based coverage loss without evaluating the density. On high-dimensional imaging inverse problems, it yields better-calibrated posteriors than scoring-rule regularizers, with little change in the reconstruction quality of point estimates.

cs.LG · stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15102

One Fabrication Is Enough: A Fake News Article Changes the Forecasts of LLM Forecasting Systems

Zeyu Zhang, Bradly C. Stadie

原文摘要

LLMs are increasingly used for forecasting, and the best forecasting systems retrieve news as evidence to strengthen their predictions. This also opens them to attack. We study the weakest attacker of this kind, who knows only the forecasting question and publishes fabricated news articles, with no access to the model, the retriever or its queries. We evaluate how far this attack reaches on stock questions and real prediction-market questions. Once the article is in the model's context, it reverses 74% to 82% of the forecasts that opposed it, on every frontier model we tested. The model cannot verify the fabrication and follows it anyway. Retrieval is the attack's entry point, and the systems built to retrieve well are the most exposed: the architectures of two leading deployed forecasting systems, whose agents search for every related article, retrieve the fabricated one in about 90% of runs. Accuracy cannot reveal this harm: the attacked forecaster is right when the attacker's direction turns out right and wrong otherwise, so its average accuracy barely changes while its forecasts follow the attacker's guess. We also propose a second attacker, who publishes two articles that argue opposite directions to make the forecaster unsure. The model does not hedge; it returns a confident forecast in a direction the attacker no longer controls. We then evaluate the two strongest published retrieval-time defenses, passage filtering and partitioned retrieval. Each stops the one-article attack but is bypassed by a one-prompt change to the attack. Together they stop both bypasses at four articles, but sixteen distorted copies beat them, and they change 29% of clean decisions and discard 39% of the genuine news. Partitioned retrieval also requires control of the retrieval index. Systems that search the open web have no such control and are left with the filter alone. For them, the attack still works.

cs.CR · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14974

Who Moved the Frontier? Paying Open Frontier Challenges with Free Identities

Luca Zanolini, Duc V. Le

原文摘要

In an open frontier challenge, anyone, person or AI agent, submits changes to a shared problem, and a change that beats the best measured score becomes the public baseline. How should it pay when identities are free? Rank prizes can be gamed: on a replay of one track of a recent challenge, one solver's steps under two identities would have taken first and second prize. We consider a prediction-market rule, proposed for machine-learning contests, that pays each accepted step for the progress it adds; with exact scores, among rules that see only a step's start and end, only these resist splitting and merging, and extra identities gain nothing. With noisy scores and independent normal runs, we prove that any payment that never takes money back and pays real improvements also pays something, on average, to a change that does nothing. We propose a fee per submission, at least what luck pays per attempt, that removes each attempt's expected profit if verifiers are honest and no submission is noisier than planned; nothing enforces that bound, and under noise the rule does not cap the total paid. If crediting another and faking credit to one's second account look the same, a rule that neither rewards fakes nor punishes honesty pays for credit at most what lying costs. We introduce a royalty on how much a later gain falls without the earlier change, which needs no claims but needs removable changes. For five public challenges, we name the rule our results would support.

cs.GT · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.23966

自适应人工智能实现可泛化的胎儿脑生物测量

Generalizable fetal brain biometry via adaptive artificial intelligence

Yijin Li, Mingxuan Liu, Yi Liao, Le Chang, Hongjia Yang, Kasidit Anmahapong, Xiaotian Hu, Ziang Wang 等 27 位作者

AI 速读 基于摘要

提出解剖引导的测试时自适应框架 BioTTA，从三维胎儿脑 MRI 自动测量 11 项生物指标，并在多中心异质数据上提升测量精度与异常检测能力。

cs.CV

arXiv ↗PDF ↗
查看原文摘要

Fetal brain biometry provides a quantitative basis for assessing prenatal growth and identifying congenital brain abnormalities. However, comprehensive assessment remains limited by labor-intensive manual measurements and automated models that lose accuracy across imaging sequences and institutions. We introduce BioTTA, an anatomically guided test-time adaptation framework that measures 11 fetal brain biometrics from reconstructed three-dimensional magnetic resonance images. BioTTA adapts pretrained models to individual unlabeled volumes using geometric consistency and atlas priors, without access to source images. In a retrospective study across five centers in China and Switzerland, BioTTA improved measurement accuracy across three out-of-distribution datasets and two network architectures. It reduced mean absolute measurement errors by 46-82% relative to the corresponding models without adaptation, achieving errors similar to those of supervised fine-tuning. Its measurements were mapped onto normative growth trajectories derived from expert annotations, enabling gestational-age-specific assessment through a web-based reporting platform. Across four disease cohorts, the platform achieved 82.1-95.0% accuracy in binary detection of ventriculomegaly or cerebellar abnormalities, with performance similar to that of a senior radiologist. BioTTA provides a practical foundation for standardized fetal brain biometry across heterogeneous imaging settings, supporting scalable prenatal growth assessment and quantitative evaluation of brain abnormalities.

新论文 · v1arXiv:2611.14267

通过设计训练数据实现抗多普勒效应的鲁棒信道估计神经网络

Achieving Robust Channel Estimation Neural Networks on Doppler effects by Designed Training Data

Dianxin Luan, John Thompson

AI 速读 基于摘要

作者提出一套合成训练数据的设计准则，使离线训练的神经网络无需先验信息或在线训练，即可在不同多普勒频移和功率延迟谱（PDP）的无线信道上稳健地估计信道。

eess.SP · cs.AI

arXiv ↗PDF ↗
查看原文摘要

Channel estimation is crucial in wireless communication systems. Many existing works train and test their models using the same or similar channel. However, practical channels are infinitely diverse and time-variant while data-driven algorithms often degrade on new and previously unseen channels. This prohibits the practical implementation of neural networks for channel estimation, particularly in high speed scenarios characterized by rapidly channel profile changes and very high Doppler shifts. Online training can fine-tune models to adapt to new channels, but requires high computation resource and incurs significant latency for physical-layer devices. Moreover, online training cannot exhaustively cover all possible channels because there are infinitely many possible channels. Therefore, we investigate the ability of neural networks to generalize to wireless channels. This paper proposes design criteria to generate synthetic training data, which guaranty that the resulting networks perform robustly across wireless channels, especially for very high Doppler shifts and different Doppler spectra. It ensures that offline-trained neural networks require no prior information or online training to precisely estimate the new channels. To demonstrate general applicability, we use neural networks with different levels of complexity to show that the generalization achieved appears to be independent of architecture. From simulation results, neural networks achieve a certain performance across wireless channels with different unseen power delay profiles (PDP) and Doppler shifts.

新论文 · v1arXiv:2611.14026

Energy-Proportional Serverless Computing on SBC Clusters

Yuliya Sasinskaya, Natalie Carl, Niklas Kowallik, David Bermbach

原文摘要

Serverless computing promises to run code only on demand, yet the servers beneath it draw most of their power while idle, so energy consumption does not scale to zero with the workload. We show that the statelessness of serverless functions makes it possible to extend scale-to-zero from function instances to physical nodes, enabling energy proportionality. Our platform, built on tinyFaaS for clusters of single-board computers, treats node power state as part of worker selection, powering workers off when idle and back on under load. On a physical cluster, our approach reduces mean power draw by 39.6 % on a bursty, trace-based workload and by 46.7 % on a sparse one, without a detectable change in median latency on the bursty workload. The cost lands in the tail, where invocations that arrive while all workers are off wait about a minute for a node to boot. Under continuous load, the platform behaves like an always-on cluster.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13295

Time Series Change Point Detection with Gaussian Processes

Olga Isupova, Danil Kuzin, Fredrik Gustafsson, Lyudmila Mihaylova

原文摘要

This paper proposes a novel general Gaussian process framework for change point detection in time series. A change is defined as an alteration of the hyperparameters of the Gaussian process prior. We formulate the problem in the context of statistical hypothesis testing and demonstrate its performance over both offline and online multiple change points detection. The approach provides theoretical guaranties of its performance. An important advantage of the developed framework is that it does not need a detailed specification of the time series function before and after a change. The hyperparameter values are learned from the data. Comprehensive evaluation of the proposed framework is provided both on synthetic and real data and its efficiency is demonstrated.

stat.ML · cs.LG · math.ST · stat.ME

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12871

Vendi 异常分数：高效准确的异常检测

Vendi Anomaly Scores for Efficient and Accurate Anomaly Detection

Amey Pasarkar, Adji Bousso Dieng

AI 速读 基于摘要

作者提出从多样性视角定义异常检测的 Vendi 异常分数（VAS），通过移除样本后数据集多样性的变化来识别异常，并在多组基准嵌入数据集与 ImageNet 实验上报告了有竞争力的结果。

cs.LG

arXiv ↗PDF ↗
查看原文摘要

Anomaly detection (AD) is a critical for trustworthy machine learning and scientific discovery. Existing methods typically define anomalies through local density, isolation heuristics, or distance from a fitted distribution, making them sensitive to neighborhood scale, partitioning choices, or restrictive distributional assumptions. In this work, we introduce a new paradigm by formulating anomaly detection from a diversity perspective. We propose the $\textit{Vendi Anomaly Score}$ (VAS), which detects anomalies by quantifying how much a sample changes the diversity of the dataset, as measured by the Vendi score, when removed. VAS captures both local redundancy and global data structure without relying on density estimation or partitioning heuristics. Moreover, VAS requires no hyperparameter tuning, instead adapting automatically to the spectral structure of the data. VAS is non-parametric and scales linearly with dataset size. Across 148 benchmark embedding datasets derived from 10 source datasets and 4 embedding architectures, VAS achieves state-of-the-art AD performance. We further validate VAS on large-scale ImageNet experiments, where it remains robust as both contamination rate and dataset scale increase.

新论文 · v1arXiv:2611.12738

Quantum Robustness via Sandwiched Rényi Divergences

Luc Rey-Bellet

原文摘要

If a quantum state is known only approximately, how much can the expectation of an observable change? We answer with the worst-case expectation over all states within a sandwiched Rényi divergence budget of a reference state, for every order $α\in [1/2,\infty]$. Convex duality gives this value as a one-dimensional optimization over a sandwiched Schatten norm, running from a fidelity risk at $α= 1/2$, through the entropic risk at $α= 1$, to a quantum conditional value-at-risk at $α= \infty$. The main result is a classicalization theorem: the quantum problem coincides with the classical one for a probability measure $ω_α$ on the spectral interval of the observable, constructed from Heinävaara's tracial joint spectral measure and given by Stahl's theorem at $α= 1$. The Hoeffding, Bernstein and Markov--Krein bounds of classical probability thereby apply to the quantum problem, and yield Pinsker-type inequalities with Bernstein-type refinements. The measure $ω_α$ is the Born measure only at $α= 1/2$; for $α> 1/2$, noncommutativity of the observable with the state strictly lowers its variance below the Born variance, and with it every variance-sensitive bound: a quantum deflation.

quant-ph · cs.IT · math-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12634

How Far Does Second-Order Linear Response Predict Quantization Mismatch? Pre-Registered Measurements on Five Language Models

Dezhen Lu, Zixiang Ni

原文摘要

Serving systems choose a weight format for each model and deployment. A low-cost screen predicts the resulting KL divergence from the unquantized model's Fisher information using $\tfrac12Δ^\top FΔ$, the expansion underlying Hessian-aware and second-order post-training quantizers. We assess the reliability of this screen in GPU batches with channel-wise int8, per-tensor fp8 and group-wise int4 on Qwen3-8B, Qwen3-4B, OLMo-2-7B, Qwen3-32B and Qwen3-30B-A3B. Relative predictions hold across a 16-fold range of perturbation scales, int4 group sizes and rounding modes, while absolute predictions are heavy-tailed. A trimmed average brings 10 of 12 cells on Qwen3-4B and OLMo-2 within 15% of measured KL. The MoE model exhibits nonquadratic response at small perturbations, with int8 KL scaling as $α^{0.63}$. Computing per-sequence gradients in bf16 can cause fourfold prediction errors. We trace these errors to arithmetic in the lower half of the backward pass and eliminate them by using fp32 there. Batch-invariant kernels run at 0.55 times the throughput, while changes in reduction order introduce a floor of 0.17-0.22 nats per sequence. We build a screener with one streamed fp32 Fisher pass, trimmed tensor-block predictions with a band, a flag for aligned tensors and per-layer format allocation. On the unseen Mistral-7B-v0.3 family, all six predictions fall within the band, all three KL budgets are met, and vLLM throughput is predicted within 0.4%.

cs.CL · cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12225

A Cost That Practice Accuracy Hides: Worked Solutions in Self-Generated Training Data and the Compositional Use of New Rules

Jiantong Xu

原文摘要

A worked solution can make self-generated training targets shorter and cheaper, but accuracy on the practiced operation may hide how well a model can reuse newly learned rules. We study this choice in a 2B-parameter reasoning model learning two invented quantitative rules. The model generates targets from a rule sheet alone or from the sheet plus a program-written worked solution; targets are accepted for final-answer correctness, and the support is removed for fine-tuning and evaluation. Training questions request forward use in one segment; composition requires sequential reuse of the same rule across two segments. After six passes, using a program-checked numerical signature, sheet-only targets lead by 24.3 percentage points (95% item-bootstrap CI 14.6-34.0) on composition in a prospective test. On unseen argument values, observed forward accuracy is identical (87.5% each), but composition accuracy is 58.3% versus 23.6%, a 34.7-point gap (25.7-43.8). An independently sampled second target-bank pair repeats the direction (+14.6 points, 2.1-26.0). Ten passes on the shorter worked-solution targets, approximately matching the domain tokens of six sheet-only passes while changing other training quantities, narrow the gap to 16.3 points (6.3-26.7) in the first bank pair and 6.2 points (-6.3 to 18.8) in the second, where the pre-specified test does not hold. At six passes each, the worked-solution policy uses fewer capture tokens and less update time, yet the trained models use 2.6 times as many generated tokens per composition success under the numerical signature (2.1 times in the second bank pair). Choosing a capture context therefore requires testing how the new rules are reused, alongside the inference cost of those uses, rather than relying on forward accuracy alone.

cs.SE · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.19861

PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents

Seongjae Kang, Taehyung Yu, Sung Ju Hwang

原文摘要

Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation. Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure. Workflow-following systems support prescribed process execution, but primarily target workflow completion rather than safeguarding agent behavior. PolicyGuide instead compiles each domain policy into a workflow graph and invokes a proactive verifier at user-turn boundaries. From persisted graph state, the verifier reconciles open requests and returns step-specific remediation along a policy-compliant path. Across the $τ^2$-bench airline, retail, and telecom domains with a GPT 5.4 agent and verifier, PolicyGuide raises mean $\mathrm{Pass}^4$ from $0.42$ to $0.62$, with the largest gain on telecom ($0.19$ to $0.61$), the most workflow-structured domain. The same workflows transfer to Claude Sonnet 4.6 and Gemini 2.5 Pro agents. Complementary evaluations find the lowest observed attack-success rate under adversarial users and the strongest procedural compliance in an independently validated workflow-level audit.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2611.06918

From Pixels to Actions--Towards Native Vision-Language-Action Policies

Weichen Fan, Haiwen Diao, Penghao Wu, Siyuan Hu, Ziqi Huang, Tianqi Liu, Mingze Sun, Ziyi Wang 等 17 位作者

原文摘要

Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only afterwards. Yet manipulation often hinges on precisely the visual signals most vulnerable to this abstraction, e.g., local geometry, boundaries, depth, and subtle state changes. This raises a fundamental question: should action policies inherit a fixed visual endpoint, or directly access evolving visual computation? We introduce NEO-VLA, a structurally encoder-free vision-language-action framework. Images are tokenized by lightweight patch convolutional layers and evolve jointly with language throughout the backbone, allowing a flow-matching action expert to draw from instruction-conditioned visual representations at different depths. This simple change reveals a consistent pattern. Native architectures outperform encoder-based counterparts under controlled comparisons; full fine-tuning reduces but does not erase the gap, and additional scale alone cannot recover it. More strikingly, layer-wise probing shows that the action-critical signals often peak well before the final visual representation. Across diverse manipulation settings and distribution shifts, NEO-VLA consequently achieves stronger and more robust control. Together, these results suggest that embodied control benefits from access to visual representations across the computational hierarchy, rather than a fixed encoder output.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.16933

A Unified Taxonomy and Evaluation Framework for Distributional Shifts in Reinforcement Learning

Ardianto Wibowo, Paulo E Santos, Amer Baghdadi, Matthew Stephenson, Karl Sammut, Jean-Philippe Diguet

原文摘要

Distributional shift in reinforcement learning (RL) is defined inconsistently across the literature, and it is studied alongside out-of-distribution (OOD) generalization and non-stationarity without a clear account of how the three terms are related. Methods are also often described as robust after evaluation under only a few particular changes, leaving the scope of such claims unclear. We develop a unified taxonomy that brings the three terms under one definition of distributional shift. We factorize the joint distribution of a one-step interaction into five components, each produced by its own generating function: initial-state distribution, observation mechanism, policy implementation (distinct from the policy being optimized), transition dynamics, and reward mechanism. A shift is specified by what changes (the changed components) and when it changes (the interaction regime: OOD, non-stationary, or combined), while changes in interaction data and performance are treated as observed effects. We complement the taxonomy with an evaluation framework that measures immediate generalization and subsequent adaptation, summarizing adaptation in a shift adaptation score (SAS). Published benchmark results, controlled Gridworld experiments with DQN, A2C, and PPO, and a mapping of selected studies show that method responses and rankings vary with the shifted component, and that existing evaluations cover only some components. Robustness claims should therefore be bounded by the components and regimes evaluated, since strong performance under one shift does not establish robustness under others. Identifying an unknown component-level source from observed interaction data remains a direction for future research.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10601

AI in the Clinical Documentation Loop: Effects of LLM-Induced Note Bloat and Diagnostic Overcall on Downstream LLMs

Jinghui Liu, Anthony Nguyen, Taylan Gurgenci

原文摘要

Large language models (LLMs) are increasingly used to process medical records for healthcare tasks such as clinical documentation. Because these tools also generate documentation, the relationship is now bidirectional: models both read from and write to the record. Understanding how LLMs behave when reading records that already contain LLM-authored content is therefore critical for their safe deployment. In this study, we examine how LLM-authored content in the medical record affects downstream LLMs that read the same record. We consider two types of LLM-induced artifacts: bloat, in which LLM-generated summaries accumulate in the record and change the length and provenance of its content over time; and distortion, in which LLMs subtly alter clinical findings rather than fabricating facts outright. As a case of distortion, we study diagnostic overcall (documenting an unconfirmed differential diagnosis in the record) and test whether it propagates to the reader LLM's output. Across seven reader models from four families, we find evidence of both effects. First, LLM-generated summary notes modestly but consistently degraded downstream hospital-course generation compared with copy-forward and templated text of matched length. Second, injected overcalls reappeared in downstream outputs at rates that varied by reader model, without detectable changes in standard quality metrics. These findings show the need to monitor AI-generated content in medical records and to account for it when those records are later processed by AI.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10400

Detecting and Explaining Robot Policy Failures from Sparse Internal Features

Riad Ahmed, Sujosh Nag, Moniruzzaman Akash, Momotaz Begum

原文摘要

Visuomotor policies can handle many robot manipulation tasks, but understanding their failures remains difficult. Unfamiliar conditions and small action errors can lead to failure, yet watching the robot alone tells us little about what went wrong inside the policy. We introduce MIND (Mechanistic Interpretability for Neural Diagnosis), a method that looks inside a trained policy to detect failures during execution and identify the internal concepts involved. MIND uses a sparse autoencoder to break down the policy's internal activations into features that can be studied individually. We give meaning to these features by linking their activity to the robot's position, movement, and surroundings, and by steering their activations to examine how they affect the robot's actions. From successful and failed executions, we learn how the features behave on the way to a failure. During execution, MIND flags deviations from these patterns and uses the meaningful features contributing most to the change to describe the problem. Experiments in simulation and on a physical robot show that changes in these internal features help detect and explain failures. By using the same features for detection and diagnosis, MIND connects failure signals to understandable changes inside the policy.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.24184

Multi-author style detection with stylistic embeddings

Man-Ling Sung, Chak Fai Li, Damianos Karakos, Fred Bernardin, Brian Ulicny

原文摘要

We investigate the use of Large Language Models (LLMs) in multi-author style change detection. Using off-the-shelf LLMs or supervised fine-tuning solely within the target domain fails to yield effective features; for this reason, we propose cross-domain transfer learning with LLM-based embeddings fine-tuned for authorship verification. We fine-tune Mistral-7B embedding model and compare it with DeBERTa, used in the state-of-the-art (SOTA) systems in PAN-25 multi-author writing style analysis challenge. Results show that DeBERTa and Mistral excel in different user-generated text scenarios. We exploit this diversity by combining both embeddings, leading to more effective style change detection.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10279

Restoring General and Improving Domain-Specific Safety in Fine-Tuned LLMs Without Retraining

Vishnu Kabir Chhabra, Ding Zhu, Zhihui Zhu, Xueru Zhang, Mohammad Mahdi Khalili

原文摘要

Safety-aligned language models are known to suffer degradation in refusal behavior following domain-specific fine-tuning, even when the fine-tuning data is entirely benign. The predominant mitigation strategy, preference optimization on the fine-tuned model, is computationally expensive and requires domain-specific preference data that is often unavailable in practice. We propose SPECTRA, a training-free, weight-level method that restores refusal behavior by transferring the base model's refusal direction into the fine-tuned model's weights via an activation-aware, low-rank update, requiring no gradient-based optimization or domain-specific safety data. The low-rank design restricts the intervention to the subspace most causally active on harmful inputs, leaving benign behavior largely undisturbed by construction. Empirically, SPECTRA substantially improves refusal behavior across a comprehensive safety evaluation, while preserving general coherence, domain-specific knowledge, and producing negligible change in false refusal rates.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.18127

Predictive Representation Learning for Manipulation via Streaming Egocentric 3D Hand Forecasting

Ruicong Liu, Yifei Huang, Liangyang Ouyang, Caixin Kang, Yoichi Sato

原文摘要

Learning embodied manipulation from egocentric human data offers a scalable path, reducing the cost of collecting robot-specific demonstrations. However, existing representation learning methods largely stop at perceptual understanding, such as extracting what a scene contains or what an action is. A capable embodied agent is more than understanding: it predicts the next motion. We propose that forecasting 3D human hand motion is one suitable pretraining task, as the representation jointly learns how to manipulate objects and how the motion will unfold next. Building on this hypothesis, we introduce SFHand, the first representation learning method via streaming egocentric 3D hand forecasting. SFHand learns by autoregressively predicting future 3D hand states, including hand type, 2D bounding box, 3D pose, and trajectory, from a continuous stream of video and language instructions. Its autoregressive architecture is equipped with an ROI-enhanced memory layer, capturing temporal context while focusing on salient hand-centric regions. To enable this research, we also introduce SFHand, the first open-source large-scale dataset pairing synchronized 3D hand poses with fine-grained language instructions (247K clips, 3.95M frames). Transferred to downstream embodied control, the learned representation shows state-of-the-art performance on both simulation and real-world manipulation benchmarks, improving success rate by up to 13.4%. Our method also achieves leading 3D hand forecasting accuracy, with 35.8% lower ADE than baseline methods. These results suggest that forecasting hand motion is a better pretraining task for representation learning in embodied manipulation. Projec page: https://ruicongliu.github.io/sfhand/.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:1303.7276

The effect of limb kinematics on the speed of a legged robot on granular media

Chen Li, Paul B. Umbanhowar, Haldun Komsuoglu, Daniel I. Goldman

原文摘要

Achieving effective locomotion on diverse terrestrial substrates can require subtle changes of limb kinematics. Biologically inspired legged robots (physical models of organisms) have shown impressive mobility on hard ground but suffer performance loss on unconsolidated granular materials like sand. Because comprehensive limb-ground interaction models are lacking, optimal gaits on complex yielding terrain have been determined empirically. To develop predictive models for legged devices and to provide hypotheses for biological locomotors, we systematically study the performance of SandBot, a small legged robot, on granular media as a function of gait parameters. High performance occurs only in a small region of parameter space. A previously introduced kinematic model of the robot combined with a new anisotropic granular penetration force law predicts the speed. Performance on granular media is maximized when gait parameters minimize body acceleration and limb interference, and utilize solidification features of granular media.

physics.bio-ph · cond-mat.soft · cs.RO · physics.flu-dyn · q-bio.QM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.05278

Beyond Accuracy: What Language-Subspace Interventions Capture, Remove, and Improve

Shaanil Punglia, Dadhichi Telwadkar, Vaibhav Rathore, Siddharth Sureka, Neha Bhargava

原文摘要

Language-subspace interventions aim to improve multilingual reasoning by suppressing language-related components in mid-layer activations. Using MATH and MGSM across four open-weight LLMs, we ask three questions: do estimated language subspaces capture translation-associated variation? Does projecting them out remove language information? And do they improve accuracy without compromising response language? For the first question, we build subspaces using the existing Mean-SVD construction and our DiffPCA. Both capture substantial translation-associated variation and show similar patterns across model depth. For the second, we project out each subspace and train linear probes to classify language from the projected activations. The probes still identify language almost perfectly, showing that neither subspace exhaustively captures language information. For the third, we evaluate several intervention configurations on Qwen2.5-7B, by varying subspace creation methods and intervention operators. We find that the intervention that most improves MGSM accuracy sacrifices response-language fidelity, with only one intervention improving joint accuracy$\unicode{x2014}$answers that are correct and in the target language$\unicode{x2014}$slightly, by 1.60 points. Interestingly, subtle changes in the prompt alone can reproduce the accuracy gains albeit with significant damage to language fidelity. We argue that causal interventions must be judged on more than accuracy, to fully account for language substitution trade-offs.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08936

Ordered Policy Optimization

Dongkyu Derek Cho, Pan Xu

原文摘要

Proximal Policy Optimization (PPO) stabilizes policy updates by clipping the importance ratio between the new policy and the data-collecting policy. The standard rule uses one fixed clipping range for all samples. While this choice offers simplicity and effectiveness, it fails to distinguish statistically harmful extreme ratio values from large, yet tolerable changes. We study how to adapt the clipping radius to the reliability of the induced importance ratio distribution. Our case study demonstrates that reliable updates require controlling these extreme ratios, rather than merely verifying that individual ratios fall within a fixed interval. Motivated by this observation, we propose Ordered Policy Optimization (\textsc{OPO}). In each minibatch, \textsc{OPO} sorts the importance ratios, selects the extreme ratios that potentially have the largest effect on the update, and assigns them adaptive sample-wise radii instead of using the fixed clipping radius. These radii are derived from a prescribed tail profile, which specifies desired target values for the selected extreme ratios. The resulting objective remains first-order and requires only minibatch sorting and a modified policy loss. Experiments conducted on MuJoCo and Atari benchmarks demonstrate that this simple modification achieves strong performance relative to established baselines.

cs.LG · cs.AI · cs.RO · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.26289

Augmentation with Dilution? A Large-Scale Empirical Study of Human Contributor Ecosystems After AI Coding Agent Adoption

Weixing Zhang, Bowen Jiang, Tianhai Liu, Jialong Li, Anne Koziolek

原文摘要

AI coding agents are rapidly proliferating in open-source software development, and the long-term sustainability of open-source projects is closely tied to the health of their human contributor ecosystems. Yet most existing studies treat human contributors as a static backdrop, and the available evidence on human participation after agent adoption mainly concerns newcomer outcomes. This paper takes the human contributor ecosystem as its dependent variable. To the best of our knowledge, it is the first study to estimate how agent adoption changes the number of distinct humans behind each pull request, and to relate this change to agent pull requests recorded under developer accounts. Using the AIDev dataset, GitHub API scanning, agent-trace screening, and two-stage propensity score matching, we construct a balanced panel of 2,246 treated and 3,798 control repositories from January 2023 to May 2026, and estimate effects with the Sun-Abraham estimator for staggered difference-in-differences, event studies, and HonestDiD sensitivity analysis. AI agent adoption is associated with a decline in human contributor density of 0.019 to 0.048, about 4-10% of its pre-adoption level, depending on the reference month (both p < 0.01); because this estimate tolerates only small violations of parallel trends, we regard it as suggestive evidence. The share of newcomers shows no detectable change (ATT = -0.009, p = 0.28), with the 95% confidence interval ruling out a decrease of more than 2.4 percentage points. Whether the decline in density is associated with agent pull requests recorded under developer accounts remains inconclusive (high minus low share: -0.013, 95% CI [-0.083, 0.057]). These findings are consistent with a pattern of augmentation with dilution: we detect no decrease in the share of newcomers, but each human contributor appears to correspond to more pull requests.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08721

Remembering Is Not Enough: Evaluating Timing and Omission in Longitudinal AI Mental Health Support

Eli Min, Mohit Chandra, Aamogh Sawant, Mengting Tu, Freya Lin, Ridwan Shams Khan, Reigna El-Yashruti, Christopher L. Smith 等 11 位作者

原文摘要

Evaluations of large language models (LLMs) for mental health support commonly focus on the clinical appropriateness of individual responses, potentially overlooking failures that emerge across extended interactions. As AI assistants accumulate memory of users' circumstances and prior disclosures, this raises an accountability question: Do AI chatbots provide appropriate support as users' needs evolve? We investigate by analyzing 14,256 longitudinal simulations grounded in donated chatbot histories from 22 users, examining how a memory-equipped assistant responds to suicidal ideation, self-harm, and anxiety crises across recovery trajectories and communication styles. We introduce the Context-Aware and Readiness-Evaluative (CARE) framework, developed with mental health professionals, to assess the timing and quality of advice, including omissions. Advice was less aligned with users' readiness after a crisis than in matched control stretches of the same conversation, largely because of premature recommendations, which were most common when recovery stalled. Revisiting a crisis reduced premature advice but not lagging advice, and users' communication style changed how often and when the assistant gave recommendations. Although explicitly unproductive advice was rare, the assistant frequently omitted clinician-expected support such as follow-up and planning for next steps. These findings show the limits of single response-level safety evaluation and the need to assess timing, omission, and consistency across users when holding AI systems accountable for longitudinal support.

cs.CY · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08428

元访问的力量：面向未来软件的演示——以LLM聊天界面与Chat AI为例

The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI

Julian Kunkel, Ali Doosthosseini

AI 速读 基于摘要

提出“元访问”概念，让LLM助手获得对界面自身结构化、受权限约束的访问能力，并以Meta Chat原型演示聊天客户端如何成为整个工作区的控制层。

cs.AI

arXiv ↗PDF ↗
查看原文摘要

Chat remains the default surface for many large language model (LLM) tasks, even as agentic tools such as OpenCode excel at coding and automation. Yet the model sees the current dialogue but not the workspace around it. We explore meta access---giving the assistant a structured, permissioned view of the interface itself and propose a ladder of levels: feature tutoring; metadata, settings, and preference access; retrieval over summaries and messages, confirmed mutation, and full orchestration. Meta access can turn a chat client from many screens into one entry point for finding, navigating, organising, and operating it, while raising risks around grounding, privacy, prompt injection, and trust. General-purpose agentic harnesses are runtimes; because they can change their own settings, meta access becomes reflexive and needs a separate control-plane boundary. We ground this in the Meta Chat prototype of the Chat AI client. It builds bounded context from, e.g., summaries, settings, and relevant messages; links references to conversations, topics, and personas; supports confirmed, reversible changes; offers a browsable tutorial library; and recommends personas as user-started conversations. By exposing application state in structured form, meta access can extend screen readers from widget descriptions to semantic workspace operations. Meta access thus turns chat from a window onto one conversation into a control layer for the whole workspace, extending chat toward agentic capability without surrendering user control. As assistants become embedded in IDEs, dashboards, office suites, and operating systems, AI-era interfaces should expose a structured, permissioned model of their state and capabilities, ideally by opening their existing metamodels through a debugger-like interface.