跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 06:08 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 07:07 — 2026-11-08 07:07（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：2026-11-08 06:08最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 06:06（北京时间）
版本更新 · v2arXiv:2610.29455

Omnilingual-MsASR: Benchmarking Multimodal, Multilingual, Long-Form Multi-Speaker ASR of Omni Large Language Models

Yuan Ge, Pei Zhang, Xize Cheng, Lingzhou Mu, Mingyang Wang, Jin Xu, Baosong Yang, Shengxiang Gao 等 11 位作者

原文摘要

Omni-modal large language models (LLMs) have achieved remarkable progress in audio and video understanding. However, existing models struggle with long-form, multi-speaker videos, especially in understanding the entire video and recognizing who says what and when. To characterize the capability limit of current omni LLMs and guide future model development, we introduce Omnilingual-MsASR, a multilingual, multimodal benchmark for long-form Multi-speaker Automatic Speech Recognition (MsASR) covering six languages, recordings up to 30 minutes, and scenarios with up to 20 speakers. Omnilingual-MsASR provides parallel audio and video inputs to evaluate models' cross-modal consistency and their ability to exploit complementary cues across modalities. Extensive evaluations of leading omni-modal LLMs reveal substantial performance bottlenecks, while their tcpWERs frequently exceed 100%. These findings highlight fine-grained temporal localization, speaker disambiguation, and cross-modal synergy as key challenges for future omni-modal foundation models. Our work is available at https://github.com/QwenLM/Omnilingua-Bench/tree/main/Omnilingua-MSpeaker.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04354

Large Language Models for Forecasting of Electricity Price Spikes

Liang Lin, Jianguo Zhu, Gang Lei, Allen Wang, Xin Lu

原文摘要

Can market notices read by a large language model (LLM) improve short-horizon electricity price spike forecasts? We study five regions of Australia's National Electricity Market. A local LLM extracted features once per notice, only notices visible at the forecast origin were used, and a gradient-boosting model produced onset probabilities. In an out-of-sample development back-test (July 2022 to July 2024), notice features did not lower the 60-minute Brier score of a numeric model including the market operator's next-hour forecasts. At 24 hours they did, but rule-based features did so almost equally and attribution to notice content was not established. A locally frozen protocol, not publicly deposited, governed a retrospective single-use holdout from 15 August to 17 October 2026. At 60 minutes, the hypothesis that LLM features lower the numeric model's Brier score was not established (H1; relative Brier skill -0.09%), so the planned comparison with rule-based features was not tested (H2). At 24 hours, the hypothesis that LLM features lower the score against a text-free control was not established (H3; +0.37%, 95% CI [-9.74, 1.39], inconclusive). By the frozen wording rule the non-significant 24-hour improvement comes mainly from recalibration and cannot be attributed to notice content, although post hoc the decomposition could not separate recalibration from resolution. The 24-hour base rate was 1.56% on the holdout against 14.0% in development. With 5 onsets on 3 days and 24-hour positives in 2 of 22 three-day blocks, the holdout neither established nor excluded a 24-hour effect.

eess.SY · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04353

XOR-Functions and Beyond in the Random Query Model

Sumegha Garg, Janani Sundaresan, Santhoshini Velusamy

原文摘要

We study time--space tradeoffs for computing Boolean functions $f:\{0,1\}^n \to \{0,1\}$ in the random query model. On input $x$, a branching program receives independent samples $(i,x(i))$, where $i$ is uniform in $[n]$. We want to evaluate $f(x)$ while minimizing the width $2^S$ and the length $T$ of the branching program. There is a simple upper bound of $T = \tilde{O}(n)$, $S = O(n)$: coupon-collector shows that $\tilde{O}(n)$ samples suffice, and they can be stored in $O(n)$ space. Raz and Zhan (ITCS 2020) introduced this model and studied the zero-error setting. In the bounded-error setting, Dinur (SODA 2024) proved $TS = \tildeΩ(n \cdot inf[f])$, where $inf[f]$ is the total influence of $f$. For many functions with low influence such as Equality and Tribes, this lower bound can leave a substantial gap from the best known upper bounds. Our main result is a stronger lower bound of $T(S+\log T) = Ω(n \cdot sens[g])$ for any XOR-function $g(x,y)= f(x \oplus y)$, where $sens[g]$ is the sensitivity of $g$. Through simple corollaries, we get tight nearly-quadratic time--space lower bounds for Tribes and Equality, despite their low influence. Our proof introduces a new notion of information complexity tailored to the random query model along with a corresponding direct-sum argument which may be of independent interest. Dinur also proved a tight bound of $TS = Ω(n^2)$ for Majority, whose influence is only $Θ(\sqrt{n})$, and asked whether an alternative characterization of Boolean functions could give a unified proof of tight results for a broader class of functions, including Majority. We answer this open question by proving $TS = \tildeΩ(n \cdot dgn[f])$, where $dgn[f]$ is the degeneracy of the sensitivity graph of $f$ (for Majority, this is $Θ(n)$). We also prove that this bound is tight for all symmetric functions up to logarithmic factors.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04352

ReSMap: Recasting Satellite Priors for Robust and Accurate Online HD Map Construction

Kyungmin Kim, Sumin Lee, Sungoh Jeong, DoHyun Lim, Seonghyun Park, Soonmin Hwang

原文摘要

Despite recent advances in camera-based online HD map construction, these systems remain susceptible to sensor failures due to their reliance on onboard cameras. In contrast, satellite images remain available independently of real-time sensing conditions as they are cached offline. Existing methods utilizing satellite images, however, primarily leverage them under nominal conditions, without explicitly addressing them as redundancy when a sensor degrades. To address this gap, we propose ReSMap, a redundancy-aware camera-satellite fusion framework for robust online HD map construction. Our framework explicitly leverages satellite images as a complementary source to improve robustness against camera failures. A Predict-then-Fuse (PTF) module fuses camera and satellite BEV features by using each branch's own prediction confidence as a per-pixel reliability weight, with no learned router. An Object-Centric Cooperative Multi-modal Query (OCMQ) decoder then extends this per-modality separation to the query level: each modality cross-attends only to its own BEV, and per-modality updates are merged through a learned per-token gate. Our model achieves state-of-the-art performance on nuScenes across all splits and range settings. More importantly, it also sets the new state-of-the-art under camera-failure scenarios, demonstrating that satellite images serve not only as a strong prior but as practical redundancy for robust online HD mapping.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.17895

TabPFN-3.5: Technical Report

Benjamin Jäger, Nick Erickson, Léo Grinsztajn, Felix Birkel, Klemens Flöge, Oscar Key, Kürşat Kaya, Jonas Kübler 等 47 位作者

原文摘要

We introduce TabPFN-3.5, our new flagship Tabular Foundation Model. It significantly outperforms its predecessor, TabPFN-3, and all existing baselines across a broad range of tabular problems. TabPFN-3.5 sets a new state of the art on standard tabular prediction in TabArena, and extends it to the data practitioners encounter in practice: non-i.i.d. data with temporal or grouped splits, tables with strings, text and images, high-cardinality categorical features, and wide tables with many features. These gains carry over to our task-specific harnesses: state of the art on relational data and stronger time-series forecasting. For faster inference, our variant TabPFN-3.5-Fast runs up to 3x faster than TabPFN-3 while keeping most of the accuracy gains. In addition, we upgrade TabPFN-3.5-Plus, expanding our multimodal capabilities with advanced text and date handling alongside proprietary inference optimizations. Finally, we release a new version of our Thinking mode, TabPFN-3.5-Thinking, which scales inference-time computation to push the state of the art further. It benefits from our stronger base model and from inference-time improvements that make it up to 12x faster than TabPFN-3-Thinking.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.21079

Repository and Issue Characteristics of Early GenAI Adopters on GitHub

Rikuto Tsuchida, Youmei Fan, Kazumasa Shimari, Raula Gaikovina Kula, Gema Rodríguez-Pérez, Kenichi Matsumoto

原文摘要

Generative artificial intelligence (GenAI) has introduced new forms of AI assistance into software development, but less is known about the repositories and issues of early adopters of GenAI tools. We study the repository and issue characteristics of early adopters who state interest in GenAI on their public profiles on GitHub by analyzing 531 early adopters, 100 of their repositories with AI-tool configuration files (ACFs), 100 matched control repositories without ACFs, and 370 issues from the two repository groups. Repositories with ACFs show modest distributional differences in selected README structural characteristics. They contain longer README files with more code blocks and include a license more often, while repositories without ACFs contain more external URLs. The category distributions of the two repository groups show weak evidence of a difference. Once GenAI relatedness is held fixed, we detect no difference in issue Type or Outcome between the two repository groups. Our data, collected from May to August 2025, record how early adopters developed software in Software Engineering 2.0, the stage in which developers use both AI assistants and autonomous AI agents. When these agents become the norm, later studies can compare their data with ours.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.05953

Fast mixing of the SYK model at high temperatures

Yiyi Cai, Yongtao Zhan, Alexander Zlokapa

原文摘要

The Sachdev-Ye-Kitaev (SYK) model is a strongly interacting fermionic system. Its dynamics are difficult to analyze with Lieb-Robinson bounds and cluster expansions due to its all-to-all disordered interactions. We prove that, with high probability over the disorder, the SYK model admits a quantum Gibbs sampler with a system-size-independent spectral gap at sufficiently high constant temperatures. This yields polynomial-time preparation of SYK Gibbs states on a quantum computer. While prior non-rigorous computations that suggested SYK thermalization were limited to studying local correlators, we emphasize that our result holds up to arbitrary inverse polynomial trace distance. Our proof introduces the pseudo-Lindbladian approach to fermions then applies two key new ideas: a Bochner inequality for quantum dynamics, and an especially simple SYK analysis based on a comparison to classical dynamics.

quant-ph · cond-mat.dis-nn · cs.DS · math-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.23120

Does Source-Free Time-Series Adaptation Really Require Updating the Encoder?

Shichang Meng, Linquan Wu, Xuan Ai, Yi Wu, Mingyang Liu, Linqi Song

原文摘要

Source-free domain adaptation (SFDA) adapts a pretrained model to an unlabeled target domain without accessing source data, enabling the reuse of time-series predictors across sensing systems. Existing methods commonly update the encoder using unlabeled target objectives. Yet changes in users, equipment, and operating conditions also alter the spectral characteristics of input signals, raising a fundamental question: does adaptation require changing the encoder, or can we instead adapt the signal it receives? We propose Source Free Frequency-Prototype Alignment (SF-FPA), which learns a spectral input transformation while freezing the source encoder and classifier parameters. First, a frequency adaptation layer applies amplitude and phase corrections to target signals. Separate branches adjust spectral magnitudes and phase relationships, with circular phase encoding avoiding discontinuities at the angular boundary. Second, confidence-filtered prototype alignment guides target representations toward source class prototypes. Combined with information maximization, this objective propagates gradients through the source predictor to learn spectral corrections that support class discrimination. Extensive experiments on three real-world time series benchmarks demonstrate state-of-the-art average Macro-F1 performance. Component ablations and controlled comparisons with encoder adaptation and a parameter-matched time-domain adapter further support spectral input adaptation as an effective approach to reusing source-trained predictors. The implementation is available at https://github.com/ShichangMeng/SF_FPA.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04349

Sparse Internal Control of Language Models

Xizhe Zhang

原文摘要

Language models are increasingly used in text generation, decision support, and automated interaction, creating a need for localized, reversible, and selective control of their behavior. Activation steering demonstrates that internal interventions can alter the behavior of frozen models, but how to select and evaluate compact, multi-site control interfaces remains an open question. I introduce sparse internal control, a framework for steering target behavior by applying inference-time interventions to a small set of internal model nodes. A local target-controllability formulation characterizes candidate site--direction pairs by their behavioral effects and specifies constraints on target recovery, off-target preservation, and intervention energy. Two complementary selectors instantiate this formulation: Driver-OMP selects nodes for sparse reconstruction of a desired behavioral displacement, while Coverage-Driver favors stable coverage across prompts. I propose a six-axis control-evaluation protocol measuring reachability, signed reversal, dose response, feedback controllability, off-target preservation, and held-out reuse. Exploratory experiments on indirect object identification, MMLU multiple-choice question answering, sentiment steering, and refusal steering provide evidence for the feasibility of steering task-defined behavior through sparse internal interventions. The six-axis evaluation characterizes these interventions beyond target movement, revealing distinct control properties that depend on the task and available direction information. Together, the formulation, reference algorithms, and evaluation protocol provide a foundation for the systematic study and development of internal control methods for language models.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.09017

Multicultural Spyfall: Assessing LLMs through a Dynamic Multilingual Social Deduction Game

Haryo Akbarianto Wibowo, Alaa Elsetohy, Qinrong Cui, Alham Fikri Aji

原文摘要

The rapid advancement of Large Language Models (LLMs) has necessitated more robust evaluation methods that go beyond static benchmarks, which are increasingly prone to data saturation and leakage. In this paper, we propose a dynamic benchmarking framework for evaluating multilingual and multicultural capabilities through the social deduction game Spyfall. In our setup, models must engage in strategic dialogue to either identify a secret agent or avoid detection, utilizing culturally relevant locations or local foods. Our results show that our game-based rankings are consistent with Chatbot Arena rankings on the overlapping models. However, we find a significant performance gap in non-English contexts: models are generally less proficient when handling locally specific entities and often struggle with rule-following or strategic integrity in non-English languages. We demonstrate that this game-based approach provides a scalable, leakage-resistant, and culturally nuanced alternative to traditional NLP benchmarks. The dataset (game history) and source code can be accessed here: https://huggingface.co/datasets/haryoaw/cultural-spyfall and https://github.com/haryoa/cultural-spyfall.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04344

Proper Agnostic Learning of Affine Halfspaces under Log-Concave Marginals

Zhijie Zheng

原文摘要

We give a proper constant-factor agnostic learner for affine halfspaces under full-dimensional log-concave marginals. For arbitrary binary labels, the algorithm uses independent labeled samples and returns a single affine halfspace with error at most $C\mathrm{OPT}+\varepsilon$. Its sample and real-arithmetic complexity are polynomial in dimension, inverse accuracy, and the logarithm of the reciprocal failure probability. The mean and covariance of the marginal need not be known, and the sample complexity can be made linear in this logarithmic confidence factor. The main geometric result compares global disagreement with disagreement on a balanced restriction: for a minority halfspace of mass $p$, global disagreement is within universal constant factors of $p$ times conditional disagreement, provided the latter is sufficiently small. To construct the restriction from noisy labels, we estimate the minority cap's mean and covariance robustly, approximately minimize the classical zonoid-depth dual objective, and expand a superlevel set to a marginal quantile. The disagreement comparison cancels the noise amplification caused by conditioning and allows the learned halfspace to be used on the entire space. The analysis combines degree-four sum-of-squares moment bounds for log-concave laws with a translation-based reduction from balanced affine learning to homogeneous halfspace learning.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04343

Do Retrieval Ranking Models Capture Event Order? A Study of Timeline-Constrained Retrieval

Alon Eirew, Lidan Avisar, Kfir Bar, Ido Dagan

原文摘要

Semantic retrieval models aim to match documents to a query's "meaning", yet it remains unclear whether they successfully encode temporal relations between events in their ranking mechanisms. We investigate this question by studying timeline-constrained document retrieval, where a query is an ordered sequence of natural-language event statements while a relevant document should match those events in a compatible temporal progression. We then test whether widely used dense retrievers and neural rerankers capture such constraints, and whether explicitly preserving temporal order improves ranking, using a controlled setting over a novel focused evaluation collection. Experiments show that state-of-the-art semantic retrievers and rerankers provide only limited improvements over lexical retrieval, suggesting that their semantic matching capabilities do not reliably capture temporal constraints. We then compare a timeline-aware method with both semantic matching and standard rerankers and find that it yields substantial improvements. This demonstrates that considering temporal order can provide a strong ranking signal in this setting, suggesting future research on improving temporal modeling in semantic retrievers.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04342

Beyond Fine-Tuning: Evaluating Prompt Engineering and Prompt Tuning for Roman Urdu Hate Speech Detection

Toneema Zubair, Muhammad Junaid Asif, Faisal Kamiran, Hafiz Hassan Saeed, Rana Fayyaz Ahmad

原文摘要

Low Resource Languages (LRLs) pose significant challenges for hate speech detection because of a scarcity of readily available annotated data, language variation, non-standard spelling, and context-dependent ambiguity. Beyond the problem of informal conventions of writing in Roman Urdu, there is also the issue of code-mixing. After working on the previous project about zero-shot learning and parameter-efficient fine-tuning (PEFT), this research systematically compares prompt engineering and prompt tuning for Roman Urdu hate speech detection. To study the effect of in-context examples, we will compare the zero-shot and few-shot prompting approaches. To understand the advantage of structured prompting and learnable prompt representations, we will conduct studies of manual vs. mixed prompt-based adaptation strategies. Experimentations are carried out on the PURUT dataset (~72,771 social media comments) with GPT-3.5, LLaMA-3, Mistral-7B, and multilingual BERT in several settings. Experimental results show that few-shot prompting always outperforms zero-shot prompting, with the Mistral-7B model scoring 0.67 F1 compared to 0.56 of the zero-shot models. Based on this observation, prompt-based adaptation is proposed to introduce additional improvements, with the proposed mixed prompt configuration able to yield a F1-score up to 0.87 which further surpasses the performance of regular manual prompts. Despite the larger size of the model, its performance trade-off between inference-based prompting, prompt optimization, and parameter-efficient model adaptation is compared to the previously reported PEFT-based F1-score, which is ~0.93.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04341

Pairwise Distortion Distribution with Graph-Based Importance Sampling for Quantization Error and Intrinsic Dimension Estimation

Xi Chen, Carl Nuzman, Shirin Jalali

原文摘要

Quantifying the dimensionality of data is a fundamental need in machine learning and signal processing applications such as representation learning, data compression, and inverse problems, where the extrinsic dimension in which the data is presented can be very different from the intrinsic dimension that determines the operational performance. Various concepts, such as Rényi information dimension, rate-distortion dimension, and quantization dimension are useful here. Despite their theoretical significance, estimating these measures are challenging given their asymptotic definitions. Recent research has shown that analyzing the pairwise distortion distribution (PDD) of a data source can provide a tractable lower bound on the distortion of random codebook quantization, from which a tractable notion of intrinsic dimension can be derived. In this paper we extend this line of research in three main ways. First, we develop a related upper bound on distortion of random codebook quantization. Second, we improve the computability of both the lower and upper bounds, using a graph-based adaptive importance sampling approach. Third, we leverage the bounds to define new notions of intrinsic dimension which form upper and lower bounds on the Rényi information dimension, rate-distortion dimension, and quantization dimension, and which can be empirically estimated from unknown data sources. We illustrate the concepts by analyzing several artificial and empirical distributions.

cs.IT · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.39009

Improved Tristate Multiplication With Formalization in Rocq

Nandakumar Edamana, Piyush P Kurur, Unnikrishnan Cheramangalath

原文摘要

We give a new multiplication algorithm for tristate numbers improving upon the state-of-the-art implementation from the Linux kernel in terms of precision. Our algorithm is significantly more precise as shown by experimental evaluation (at the peak, giving better results in 95.59% cases compared to the previous work for 31-bit samples). Importantly, we achieve this additional precision with performance comparable to the previous algorithm, as demonstrated by benchmarks. Our algorithm is now part of the upstream Linux kernel. We also provide the first machine-checked proofs for tnum arithmetic operations that work for all bit widths. Our proofs include the soundness of the new multiplication algorithm and the soundness and optimality of supporting operations.

cs.LO

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

DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation

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

原文摘要

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

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04338

Patching the Protocol: A Taxonomy of Pre-Registration Repairs in LLM-Proposer Experiments

Peter Chen, Ni Zhang, Siyuan Zhang

原文摘要

Pre-registration is increasingly proposed as a trust mechanism for machine-learning research involving LLM-generated content, but its canonical form assumes a frozen protocol can be executed unchanged. Software-intensive studies violate this assumption: the protocol is partly implemented, and implementations carry defects. We report a three-case study of protocol repairs ("patches") from a program where an LLM proposes executable rules that a programmatic verifier gates, across production scheduling, incentive design, and task assignment. Each protocol required exactly one defect-repair patch: three events in total. None modified a numbered judgment criterion, its threshold, or the scoring rule, and none altered already collected data; two changed pre-registered design parameters before any data were collected, each with a recorded rationale. We propose a two-axis taxonomy of patches (defect class: environmental / feasibility / correctness, x timing: pre-data / post-data), introduce a verifiable non-impact claim for post-data repairs, and distill a nine-item checklist; all nine items were exercised by at least one patch event -- an observation of use, not a validation of sufficiency. The credibility of verifier-bound, LLM-proposer studies depends less on whether patches occur than on whether they are auditable.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2410.07839

Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting

Tim Knappe, Ryan Li, Ayush Chauhan, Kaylee Chhua, Kevin Zhu, Sean O'Brien

原文摘要

While large language models (LLMs) have rapidly improved their performance on a broad number of tasks, they still often fall short on reasoning tasks. As LLMs become more integrated in diverse real-world tasks, advancing their reasoning capabilities is crucial to their effectiveness in nuanced, complex problems. Wang et al.'s self-consistency framework reveals that sampling multiple rationales before taking a majority vote reliably improves model performance across various closed-answer reasoning tasks. Standard methods based on this framework aggregate the final decisions of these rationales but fail to utilize the semantic information detailed in the step-by-step reasoning paths. Our work introduces semantic self-consistency, enhancing this approach by incorporating and analyzing both the reasoning paths of these rationales in addition to their final decisions before taking a majority vote. These methods not only improve the reliability of reasoning paths but also cause more robust performance on complex reasoning tasks.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04337

Mitigating Spatial Blindness in Multiple Instance Learning for Whole-Slide Image Analysis

Xiangyu Li, Jincheng Li, Xing Xie, Bin Guan, Shaohua Kevin Zhou, Rui Yan, Ran Su

原文摘要

Whole-slide multiple instance learning can predict diagnostic and prognostic labels from tissue composition while making limited use of spatial organization. Providing coordinates or a graph does not establish that a trained predictor uses tissue neighborhoods. We examine this gap as spatial blindness and hypothesize that early composition learning can weaken supervision of a spatial pathway. We introduce ResTopoMIL, which freezes a learned composition predictor before training a graph residual with a coordinate-reassignment separation loss. Permutation and information analyses distinguish architectural symmetry, available spatial information and the proposed optimization mechanism. On a controlled spatial task, staged training achieved an AUC of 0.987, compared with 0.684 for the same jointly trained architecture. Performance remained high on a composition-only task. Across four WSI classification and five survival benchmarks, ResTopoMIL improved mean primary performance on eight tasks; four improvements remained significant after Holm-adjusted patient-cluster tests. Coordinate-free residual controls recovered some of the gains, while neighborhood destruction reduced performance close to the composition anchor. Neighborhood-preserving transformations and anatomy-stratified perturbations further characterized this dependence. These results support fixing a composition reference as a practical intervention for learning spatial corrections, while retaining additional appearance capacity as a contributing explanation.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02044

Unified Loss-Aware Density Control for 3D Gaussian Splatting

Tae-Young Kim, Jiwoo Chung, Jae-Pil Heo

原文摘要

The efficiency and fidelity of 3D Gaussian Splatting critically depend on adaptive density control, which grows and suppresses Gaussian primitives throughout optimization. However, the standard pipeline still relies on heuristic view-space gradients, scale thresholds, and global opacity resets, rather than explicitly assessing the loss-reducing effect of each split, clone, or opacity update. This mismatch can allocate primitives to already-sufficient regions, miss under-reconstructed structures, and destabilize training through blanket opacity changes. In this work, we recast adaptive density control as a collection of local loss-reduction decisions. We derive efficient Taylor-based per-Gaussian surrogates that predict the objective change caused by three primitive-level operations: splitting, cloning, and opacity decay. This yields a unified loss-aware framework with three components. First, we extend second-order splitting to a normalized joint position-scale space, enabling children to adapt not only their locations but also their anisotropic extents. Second, we formulate duplicate cloning as a surrogate minimization problem, selecting only Gaussians whose duplicated contribution is predicted to improve reconstruction and assigning each child a principled opacity. Third, we replace global opacity reset with selective soft opacity decay that weakens harmful primitives while preserving useful ones. Across standard 3DGS benchmarks, our method produces more targeted primitive allocation and achieves improved rendering quality with comparable or smaller Gaussian budgets compared to baselines.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04336

Gaussian Difference Dynamics: Breaking the $2^{n/2}$ Barrier for the Shortest Vector Problem and Discrete Gaussian Sampling

Yiming Gao, Xuyuan Han, Honggang Hu

原文摘要

We give classical randomized algorithms in a word RAM model that break the $2^{n/2}$ barrier for both discrete Gaussian sampling (DGS) and the Shortest Vector Problem (SVP). For every fixed $α>1$, shifted DGS on arbitrary lattices at width $σ\geαη_{1/2}(L)$ takes $$ (3/2)^{n/2+o(n)}\text{ time} \qquad\text{and}\qquad (4/3)^{n/2+o(n)}\text{ space}. $$ These bounds match the Becker--Ducas--Gama--Laarhoven (BDGL) heuristic sieving exponents. At widths at least $3η_{1/2}(L)/2$, the same total cost suffices for an entire batch of $\lfloor(4/3)^{n/2}\rfloor$ samples jointly close to independent target Gaussians. For SVP on arbitrary lattices, our algorithm returns a shortest nonzero vector with high probability in $$ 2^{0.4130n+o(n)}\text{ time} \qquad\text{and}\qquad 2^{0.3138n+o(n)}\text{ space}. $$ As a corollary, we obtain centered DGS at every width with the same exponents, answering a question of Stephens-Davidowitz (SODA 2016). We introduce Gaussian difference dynamics (GDD), a framework for tracking expected counts and pairwise clustering of vectors through repeated differencing. A closed recursion for the first two counting moments controls these quantities relative to a Gaussian reference, without requiring independence within intermediate lists. Accurate moment bounds let us extract a Gaussian sample by weighted selection, while the weaker bounds needed to establish a shortest vector representation allow us to retain more differences. We perform these transitions on thin spherical shells, where the Gaussian rejection weights can be renormalized at subexponential cost. For batch sampling, we combine this geometry with the double rejection technique of Doulgerakis and Laarhoven to control the joint distribution of outputs while reusing vectors.

cs.DS · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28229

TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization

Chengtao Jian, Kai Yang

原文摘要

Direct Preference Optimization (DPO) minimizes empirical risk over observed preference comparisons, implicitly assuming that the training preference distribution matches the deployment preference distribution. In practice, this distributional assumption often fails, as preference distribution shifts can arise at three levels: group-level shift, prompt-level shift, and preference-level shift. Such multi-level distributional mismatch poses a critical challenge for safe LLM deployment, yet existing robust DPO methods typically either model uncertainty over the joint preference distribution or focus on individual sources of shift, leaving the hierarchical structure of OOD preference shifts underexplored. We propose TPO, a tri-level distributionally robust framework for OOD preference alignment, which jointly models all three levels of distributional uncertainty through a hierarchically structured rectangular ambiguity set. By instantiating it with Wasserstein distance, we derive a tractable and interpretable objective that combines a preference-level margin penalty, prompt-level adversarial embedding perturbation, and worst-case group reweighting, each governed by an independent radius. We establish finite-sample convergence guarantees and empirically validate the effectiveness of TPO across diverse OOD environments.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.25491

A Spectral Local-to-Global Principle for Spin Systems on Graphs with Girth At Least Five

Xiaoyu Chen, Kuikui Liu

原文摘要

It is proved that, for every $δ\in (0,1)$, the Glauber dynamics for the uniform distribution on proper $q$-colorings is rapidly mixing when $q \geq (1+δ)Δ$ and the underlying graph has girth at least $5$ and maximum degree $Δ= Ω_δ(1)$. This result also extends to general multi-spin systems satisfying a $\textit{local spectral contraction}$ condition, including the anti-ferromagnetic Potts model with $q\geq (1+δ)(1-β)Δ$. These results are achieved by a new spectral local-to-global principle on graphs with girth at least five for general multi-spin systems, and a novel Fourier analysis for Glauber dynamics on a star. The main ideas behind all the proofs were developed through several rounds of interaction with GPT-5.6 Sol Ultra.

cs.DS · cs.DM · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04334

RAIPAL: A Powerful and Agile Humanoid Arm for Human Tasks

Donggeon Kim, Hyungho Chris Choi, Donghyuk Choi, Jeongsoo Park, Choongin Lee, Chan Park, Jemin Hwangbo

原文摘要

This paper presents humanoid manipulator hardware designed specifically for human-level performance throughout its broad domain of tasks, from heavy payloads to highly dynamic motions. Unlike conventional designs targeting uniform workspace capability, the proposed approach derives force, speed, and endurance targets from published measurements of task-relevant human upper-limb performance. These targets guide the actuator, mechanism, and thermal design toward torque transparency and sustained operation. The platform integrates force-oriented upper-arm components, speed-oriented forearm components, and a posture-dependent elbow mechanism that shifts its torque-speed behavior. These components are driven by planetary actuators and compact actuator-embedded electronics. Experimental results validate broad task capability, demonstrating a peak payload of 20 kg (2.25x its own mass), an endpoint speed of 20.6 m/s, and continued operation under repeated hammering impacts. Thermal analysis further confirms that the robot's sustained operation capability exceeds the published human load--duration boundary across nearly the entire load spectrum. These findings show that hardware targets derived from human-task measurements narrow the human-to-humanoid capability gap. A supplementary video is available at https://youtu.be/xVUWFICD5G0

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.13986

TabPFN-3: Technical Report

Léo Grinsztajn, Klemens Flöge, Oscar Key, Felix Birkel, Philipp Jund, Brendan Roof, Mihir Manium, Shi Bin Hoo 等 41 位作者

原文摘要

Tabular data underpins most high-value prediction problems in science and industry, and TabPFN has driven the foundation model revolution for this modality. Designed with feedback from our users, TabPFN-3 builds on this foundation to scale state-of-the-art performance to datasets with 1M training rows and substantially reduce training and inference time. Pretrained exclusively on synthetic data from our prior, TabPFN-3 dramatically pushes the frontier of tabular prediction and brings substantial gains on time series, relational, and tabular-text data. On the standard tabular benchmark TabArena, a forward pass of TabPFN-3 outperforms all other models, including tuned and ensembled baselines, by a significant margin, and pareto-dominates the speed/performance frontier. On more diverse datasets, TabPFN-3 ranks first on datasets with many classes, and beats 8-hour-tuned gradient-boosted-tree baselines on datasets up to 1M training rows and 200 features. TabPFN-3 introduces test-time compute scaling to tabular foundation models. Our API offering TabPFN-3-Plus (Thinking) exploits this to beat all non-TabPFN models by over 200 Elo on TabArena, rising to 420 Elo on the largest data subset, and outperforms AutoGluon 1.5 extreme while being 10x faster, without using LLMs, real data, internet search or any other model besides TabPFN. TabPFN-3 extends the capabilities of our models, enabling SOTA prediction on relational data (new SOTA foundation model on RelBenchV1) and tabular-text data (SOTA on TabSTAR via TabPFN-3-Plus); and improves existing integrations: a specialized checkpoint, TabPFN-TS-3, ranks 2nd on the time-series benchmark fev-bench, and SHAP-value computation is up to 120x faster. TabPFN-3 achieves this performance while being up to 20x faster than TabPFN-2.5. In addition, a reduced KV cache and row-chunking scale to 1M rows on one H100 with fast inference speed.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04331

Warpline: Binary-Level Tracing and Unified Evidence for Agentic GPU Kernel Optimization

Junyu Yin, Vinod Grover, Keren Zhou

原文摘要

LLM agents are becoming GPU kernel engineers, but they still tune kernels without seeing where the time goes. Hardware profilers report how busy each unit was, not where each warp's time went; intra-kernel tracers can show it, but only with hand-placed probes and a recompilation that alters the very kernel being measured. We present Warpline, which gives agents this view automatically while leaving the kernel essentially unchanged. Warpline analyzes the binary to decide which events to record and inserts probes into the binary itself without recompilation or any manual step. It then aligns the trace with hardware profiling data on one unified timeline. Because it needs only the binary, it can regenerate this evidence for every new version of the kernel at whatever level the agent edits it (source, IR, or PTX), closing the optimization loop without human intervention. On NVIDIA B200, across 35 kernels in Triton, CuTe DSL, and CUDA C++, Warpline adds a median overhead of 1.2% and leaves a median 99.9% of executed instructions unchanged, whereas existing tracers have median overheads of 1.6% to 13.2% and leave only 4.6% to 32.7% unchanged. Warpline also traces closed-source kernels, which these tracers cannot. On 10 SOL-ExecBench problems, agents using Warpline spend less time and fewer model requests than a bare coding agent and NVIDIA's Kernel Design Agents (KDA), yet lead both after every round in geometric mean and reach a 7.69$\times$ geometric-mean speedup, against 6.94$\times$ and 6.13$\times$. Two case studies further demonstrate that Warpline reveals hidden bottlenecks and provides actionable optimization insights.

cs.PF · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04330

CORA: Teacher-Guided Causal O-RAN Adaptation for Jamming Detection

Sneihil Gopal, Richard A. Rouil

原文摘要

In mission-critical networks, a missed jamming event is costlier than a false alarm, so detectors should favor recall, operate causally, and work without labeled attack data. Retrospective Key Performance Indicator (KPI) detectors meet the label-free requirement but rely on future context and cannot run in streaming operation. We present CORA, a teacher-guided reinforcement learning (RL) framework that transfers the hindsight of a retrospective detector to a causal one without labels during training or deployment. Offline, a retrospective KPI detector evaluated on unlabeled historical logs defines a recall-weighted reward for a masked controller that adapts the sensitivity, persistence, and grace of a causal KPI detector. At deployment, the teacher is removed and the frozen controller acts causally, with no ground-truth labels and no target-specific calibration. The design maps onto offline training in the Non-Real-Time RIC and causal control in the Near-Real-Time RIC of an Open Radio Access Network (O-RAN). Under leave-one-out transfer across ten 5G O-RAN testbed configurations, CORA reaches recall-oriented operating points on the deployable frontier that none of the evaluated baselines covers. A Proximal Policy Optimization (PPO) controller raises mean recall from 0.687 to 0.771 over a fixed default detector on all ten configurations, while a Deep Q-Network (DQN) achieves a comparable F2-score to the best teacher-selected static configuration, with 61% fewer false alarms. Removing the teacher lowers recall on every configuration.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.17691

A Mimamsa Inspired Framework For Instruction Sequencing In AI Agents

Bama Srinivasan

原文摘要

This paper presents a formal framework for sequencing instructions in AI agents, inspired by the Indian philosophical system of Mimamsa. The framework formalizes sequencing mechanisms through action object pairs in three distinct ways: direct assertion (Srutikrama) for temporal precedence, purpose driven sequencing (Arthakrama) for functional dependencies, and iterative procedures (Pravrittikrama) for distinguishing between parallel and sequential execution in repetitive tasks. It introduces the syntax and semantics of an action object imperative logic, extending the MIRA formalism (Srinivasan and Parthasarathi, 2021) with explicit deduction rules for sequencing. The correctness of instruction sequencing is established through a validated theorem, which is based on object dependencies across successive instructions. This is further supported by proofs of soundness and completeness. This formal verification enables reliable instruction sequencing, impacting AI applications across areas like task planning and robotics by addressing temporal reasoning and dependency modeling.

cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02253

Calibration-Constrained Diagnostics for Evaluating LLM Self-Evaluation

Jae Oh Woo, Mengdie Flora Wang, Rahul Ghosh, Baishali Chaudhury, Mun Young Kim

原文摘要

We introduce a reusable evaluation artifact for diagnosing whether LLM self-reported confidence can support confidence-gated act-or-defer decisions. The artifact is designed for evaluation rather than safety certification: it provides a black-box protocol, prompts, judge-reference labels, model outputs, reproduction scripts, and calibration-constrained diagnostic metrics for auditing LLM self-evaluation across math, factual, and commonsense reasoning tasks. Our central finding is that aggregate uncertainty summaries can produce deployment-misleading rankings: a model that appears strongest under standard aggregate calibration metrics can fail under category-level calibration constraints, while a model with worse aggregate calibration can exhibit stronger calibration-constrained behavior in the positive-margin region where high self-selection accuracy and tight calibration coexist. To expose this failure mode, we define PVC and C-PVC as category-level diagnostics over an accuracy-by-calibration surface: PVC counts categories whose self-evaluation accuracy exceeds a threshold, while C-PVC additionally requires category-level calibration error below a tolerance. We aggregate these diagnostics using Volume Under Surface (VUS) and a positive-margin restriction; they are VC/fat-shattering motivated but are empirical evaluation proxies, not literal VC-dimension estimates. Across 13 models and four benchmarks, the artifact shows weak confidence-correctness separation, stable diagnostic rankings under alternative categorizations and judge-label perturbations, and persistent positive-margin failures not captured by ECE or Brier score. Confidence-gated self-evaluation therefore requires calibration-constrained, category-level diagnostics, and we provide a reusable artifact for applying them under black-box access.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04327

Anchor: Augmented Cross-Layer Recurrent State for Long-Context Retrieval in Test-Time Training

Vimal William, Yuanzhe Li, Danella Zhao, Huanrui Yang

原文摘要

Parameter-efficient linearization turns a pretrained autoregressive Transformer into an efficient model by hybridizing sliding-window attention (SWA) with a constant-size recurrent memory. But does every layer's recurrent state contribute to long-context retrieval? Investigating an SWA and Test-Time Training (TTT) hybrid, we find that retrieval is sparse across depth, concentrated in a few anchor layers, and that the remaining states hold similar information expressed through layer-specific transformations. We exploit both observations in Anchor: TTT memory placed only at the anchor layers, and a cross-layer recurrent state written once and read by many layers, each through its own learned read map that realizes a layer-specific stretch and rotation, along with demonstrated generalization to other hybrid attentions. On Llama-3.1-8B and Mistral-7B, Anchor delivers 2.3-3.1x higher recall and 6.7-8.9 points higher MMLU accuracy than LoLCATs with a 10x smaller recurrent state, retains 91-95% of the teacher's MMLU accuracy, and cuts end-to-end latency by up to 4.3x relative to softmax attention.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗