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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 16:31 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 18:13 — 2026-11-09 18:13（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：2026-11-09 16:31最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 15,506 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 16:29（北京时间）
版本更新 · v2arXiv:2609.08850

Matching in Context: Temporal Fusion and Query Adaptation for Training-Free Video Temporal Grounding

Zhuo Cao, Bingqing Zhang, Sen Wang, Xue Li

原文摘要

Text-guided Video Temporal Grounding (VTG) localizes moments in an untrimmed video that correspond to a text query. Supervised approaches require costly temporal annotations and task-specific training, yet can generalize poorly under distribution shift. To reduce this dependence on task-specific supervision, training-free approaches use pretrained vision-language models to localize moments by measuring the similarity between video and query features. However, independently encoded frames provide limited temporal context, while a fixed query embedding can assign similar scores to different candidate moments within the video. To address these limitations, we propose DSE-VTG, a \underline{D}ual-\underline{S}ide \underline{E}nhancement framework that combines visual evidence across temporal granularities with video-specific query adaptation, without task-specific training. On the visual side, Multi-scale Similarity Fusion (MSF) combines frame- and clip-level similarities into a unified, temporally aware similarity profile. On the query side, Query-level Test-Time Adaptation (Q-TTA) uses pseudo-labels to optimize a lightweight additive offset for more discriminative matching within the video, without fine-tuning the backbone or calling external large language models. Experiments on three standard and two out-of-distribution (OOD) benchmarks show gains over the prior training-free methods. On Charades-STA, DSE-VTG improves mIoU by 5.89 percentage points over the strongest compared baseline under the same backbone. Under distribution shift, DSE-VTG reaches 50.86 mIoU on Charades-CG Novel-Word, surpassing the strongest supervised baseline by 2.76 mIoU. Our code will be released upon acceptance.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03344

FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell

Fedor Velikonivtsev, Mikhail Koltakov, Denis Kuznedelev

原文摘要

Attention remains a substantial computational cost in Transformer training, particularly at long context lengths. NVIDIA Blackwell GPUs provide high-throughput low-precision matrix multiplication, but exploiting it in attention requires addressing quantization overhead, causal information leakage through shared scales, and numerical inconsistencies between the forward and backward passes. We present FLAMIA, a family of attention kernels for Blackwell with MXFP8 and mixed NVFP4/FP8 training paths. Our design combines token-block scaling that reuses quantized operands across matrix orientations, targeted safeguards against scale-induced leakage, and consistent forward and backward computations. Fused quantization and architecture-specific kernel optimizations reduce overhead, while document-local scaling and workload-aware scheduling support variable-length documents directly in packed layouts without repacking. Across various causal packed-document workloads, the MXFP8 path accelerates the combined forward and backward attention call, including quantization, by factors of $1.10$--$1.40\times$ on B200 and $1.06$--$1.42\times$ on B300 relative to the fastest evaluated baseline for each workload. We validate training stability and quality preservation on pretraining Llama-style models. These results show how jointly designing quantization, training numerics, and document scheduling translates low-bit hardware throughput into practical attention acceleration.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.16193

UAV-DualCog: A Dual-Cognition Benchmark for Grounded UAV Agent-World Reasoning with MLLMs

Like Liu, Zhengzheng Xu, Hongzhe Li, Lin Wang, Dian Shao

原文摘要

Multimodal large language models (MLLMs) perform strongly across vision-language tasks, yet remain insufficiently explored in UAV scenarios. Recent UAV-oriented benchmarks have begun to evaluate MLLMs in aerial scenarios, but typically focus on scene understanding, event recognition, or navigation completion, rather than jointly assessing the dual-cognition capability required for UAV agents: reasoning about the UAV's own position, behavior, and observation state alongside external landmark states under continuously changing viewpoints, supported by explicit spatio-temporal grounding. To address this gap, we present UAV-DualCog, the first benchmark to formulate UAV dual cognition as the coordinated evaluation of Agent-State Reasoning and World-State Reasoning across multi-view images and egocentric videos, with explicit spatial or temporal grounding. The State-aware UAV Simulation Platform (SUSP) and the DualCog-aware Capture System (DCCS) construct 4,096 image and 2,048 video samples from 12 scenes, pairing complementary state questions within shared Agent-Landmark contexts. Extensive evaluations on 45 models show that current MLLMs remain far from reliable in UAV dual cognition: Agent-State Reasoning is generally weaker than World-State Reasoning, semantic answers do not reliably coincide with spatial or temporal grounding, and coordinated abilities remain limited. Thinking-mode comparisons, open-ended analyses, and sim-to-real validation show that these limitations persist across inference settings, formats, and environments. We further construct UAV-DualCog-Train and improve UAV dual-cognition performance through a lightweight optimization probe. Supplementary website, code, and dataset: https://smartdianlab.github.io/UAV-DualCog/

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03339

ArabGeoText: Tool-Augmented Vision-Language Models for Arabic Geospatial Text Spotting

Yakoub Bazi, Sarah Alsaleh, Mohamad M. Al Rahhal, Mohamed A. Mekhtiche, Mansour Zuair

原文摘要

Geospatial text spotting involves locating and transcribing geographic labels, such as road names, district names, and landmarks, in raster maps. These labels are often small, densely arranged, and arbitrarily oriented. Although Arabic text recognition has been studied extensively in documents and natural scenes, Arabic geospatial text spotting remains underexplored. We introduce ARABGEOTEXT, an Arabic-centric benchmark covering 970 geographic locations in Riyadh and Jeddah, with 17,875 manually annotated text instances per view type. For each location, we pair an OpenStreetMap (OSM) rendering with a composite created by overlaying that rendering on the corresponding remote sensing (RS) imagery. The paired views preserve label content and pixel geometry, allowing evaluation across different backgrounds. Geographic partitions support in-city and city-disjoint evaluation of detection, recognition, and end-to-end spotting. Experiments with direct Qwen3.5-4B spotting show difficulties in recovering all labels within a tile. We therefore propose a tool-augmented vision-language framework that combines YOLO26 localization and crop rectification with Qwen3.5-4B recognition adapted through low-rank adaptation (LoRA). The framework outperforms direct LoRA-adapted Qwen3.5-4B spotting across both image views and test cities. With localization held fixed, reader adaptation further improves recognition over the pretrained zero-shot reader. The dataset and code will be made publicly available at https://github.com/yakoubbazi/ArabGeoText.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33941

TurboWAM: Learning What Matters for Fast World Action Models

Guile Wu, Shuangzhi Li, Xingxin Chen, Chengjie Huang, Sam Hosseini, Tongtong Cao, Yingxue Zhang, Dongfeng Bai

原文摘要

World action models have demonstrated promising performance in robot policy learning, yet their high inference latency remains a critical bottleneck for real-world deployment. Recent approaches have sought to improve inference efficiency by eliminating test-time future-frame imagination or accelerating action prediction. However, aggregating representations from all video world model layers can introduce redundant computation, while standard backpropagation may distribute action-supervision gradients unevenly across layers, limiting the effectiveness of world representation learning. In this work, we propose TurboWAM, a fast world action model that learns to efficiently aggregate and optimize world representations for action prediction. Specifically, TurboWAM introduces an efficient world representation aggregation mechanism that restricts aggregation to a bounded range of relevant world model layers identified through layer relevance analysis. Within this bounded range, TurboWAM estimates aggregation weights for different world model layers based on the current action denoising state and combines them with learnable layer-wise weights to fuse world representations. Moreover, TurboWAM employs a world model gradient modulation mechanism that decomposes action-supervision gradients into a layer-shared component and layer-specific residual components, enabling more balanced gradient propagation across world model layers. This mechanism operates exclusively during training and introduces no additional inference computation. Together, these designs enable more efficient world representation learning and low-latency action prediction. Extensive experiments on multiple robot manipulation benchmarks and real-world manipulation tasks show that TurboWAM achieves low inference latency while maintaining competitive task success rates compared with state-of-the-art methods.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2501.19214

A SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization

Wei Liu, Yangyang Xu

原文摘要

Many real-world problems, such as those with fairness constraints, involve complex expectation constraints and large datasets, necessitating the design of efficient stochastic methods to solve them. Most existing research focuses on cases with no {constraint} or easy-to-project constraints or deterministic constraints. In this paper, we consider nonconvex nonsmooth stochastic optimization problems with expectation constraints, for which we build a novel exact penalty model. We first show the relationship between the penalty model and the original problem. Then on solving the penalty problem, we present a single-loop SPIDER-type stochastic subgradient method, which utilizes the subgradients of both the objective and constraint functions, as well as the constraint function value at each iteration. Under certain regularity conditions (weaker than Slater-type constraint qualification or strong feasibility assumed in existing works), we establish an iteration complexity result of $O(ε^{-4})$ to reach a near-$ε$ stationary point of the penalized problem in expectation, matching the lower bound for such tasks. Building on the exact penalization, an $(ε,ε)$-KKT point of the original problem is obtained. For a few scenarios, our complexity of either the {objective} sample subgradient or the constraint sample function values can be lower than the state-of-the-art results by a factor of $ε^{-2}$. Moreover, on solving two fairness-constrained problems and a multi-class Neyman-Pearson classification problem, our method is significantly (up to 466 times) faster than the state-of-the-art algorithms, including switching subgradient method and inexact proximal point methods.

math.OC · cs.CC · cs.LG · math.NA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03769

Metadata-Conditioned Audio Transformers for Adaptive Respiratory Sound Classification

George Kontogiannis, Pantelis Tzamalis, Sotiris Nikoletseas

原文摘要

Respiratory sound classification from auscultation recordings is confounded by heterogeneous acquisition conditions, including recording device, auscultation site, and patient characteristics, that introduce systematic variability unrelated to the underlying pathology. Although such metadata is often available, existing approaches either ignore it or rely on naïve fusion strategies that do not model how distinct metadata sources influence different components of the acoustic representation. We propose a family of metadata-conditioning mechanisms for the Audio Spectrogram Transformer (AST), progressing from gated residual fusion to Feature-wise Linear Modulation (FiLM) adapted to the Transformer architecture. We further introduce two novel variants: Token-Aware FiLM (TAFiLM), which applies distinct modulation to classification and patch tokens, and Soft-Factorized FiLM (SoftFiLM), which learns soft masks to align metadata factors with disentangled feature subspaces. Experiments on the ICBHI benchmark demonstrate consistent gains across all conditioning strategies. SoftFiLM achieves 64.11% on the official 4-class task (+3.94% over the baseline) and 72.40% on the 2-class task, establishing a new state-of-the-art on the 2-class task and competitive performance on the 4-class benchmark.

cs.SD · cs.AI · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03330

The SIMPLE Law for Energy Cost of LLM Inference

Hiari Pizzini Cavagna, Andrea Proia, Daniele Cesarini, Zeynep Kiziltan, Andrea Bartolini

原文摘要

Generative AI is billed per token, yet tokens are not equally expensive. Each token enters the KV-cache and raises the cost of those that follow, so energy grows non-linearly along a sequence whose tokens look identical. No analytical model states what a token costs, and the most accurate SOTA model is a fit, not a law: it absorbs architecture into fitted coefficients, requiring per-LLM fitting. We derive closed-form expressions of the computational and memory-access complexity of LLM inference in terms of architectural hyperparameters, covering MHA and GQA, and compare a family of analytical models of increasing granularity. From these, we obtain the SIMPLE Inference Model to Predict LLMs Energy (SIMPLE), a four-parameter law that separates prefill from decode, and decode into KV-cache cost and next-token computation. Over traces of 13 dense LLMs from six families on NVIDIA H100 GPUs, it attains R2 = 0.969 and 11.97% MAPE, 3.1-3.5x below the SOTA, without per-LLM calibration. The SIMPLE law explains as well as predicts: prefill energy grows quadratically with the hidden dimension, so larger LLMs suffer most from long inputs; and more aggressive GQA KV grouping reduces the per-token energy by up to 3x relative to standard MHA. Increasing the reasoning token budget pushes output length beyond the analytically derived energy minimum, driving super-linear energy growth; although accuracy grows with the budget, energy grows faster, so Intelligence per Joule peaks at an intermediate budget and falls by up to 3.14x across a 4.0x reasoning-budget range. Agentic serving raises energy per request by 13.0x relative to non-agentic ones, driven by the growth of both the prefill and the KV-cache terms with input length; while prefix caching removes most of the prefill cost (-93%), the KV-cache term is unaffected, so even a cached agentic request costs 4.8x more.

cs.AI · cs.LG · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.14746

Selective Safety Steering via Value-Filtered Decoding

Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh, Yarin Gal, Yaniv Romano

原文摘要

While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints. A growing line of work addresses this problem by modifying the model's sampling policy at decoding time using a safety score. However, existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model. Such unnecessary interventions are undesirable, as they can distort key properties of the base model such as helpfulness, fluency, style, and coherence. We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of responses. Our approach filters tokens using a value-based safety criterion and provides an explicit bound on the probability of false interventions. A single threshold hyperparameter controls this bound, allowing practitioners to trade off higher rates of unnecessary intervention for better output safety. Across multiple datasets and experiments, we show that our value-filtered decoding method outperforms existing baselines, achieving better trade-offs between safety, helpfulness, and similarity to the base model.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03327

From FAIR to AI-FAIR Metadata-First Infrastructure for AI-Enabled Science

Elizabeth G. Campolongo, Eric R. Sokol, Marty Downs, Gina Glenne, Gregory E. Maurer, Sydne Record, Dustin R. Rubenstein, Matthew J. Thompson 等 12 位作者

原文摘要

Artificial intelligence (AI) technologies and their capabilities have advanced rapidly over the past few years, leading to widespread interest and adoption in the biological and ecological sciences. However, the data infrastructure and computational resources that provide the foundation for AI workflows in ecology and biodiversity science remain fragmented. Moreover, the flow of value remains largely unidirectional: data move from collectors, through repositories and aggregators into models, and finally to research products or management actions. The derived value, such as corrected taxonomies, annotations, quality flags, and insights, rarely returns to source communities. We propose an extension of the original FAIR principles to address the needs of AI-ready infrastructure: the AI-FAIR metadata criteria, which place AI-enabled science in the context of a bidirectional Question-Data-Model triangle. This framework is designed to facilitate large-scale content-based analysis across diverse collections and ensure that the scientists generating the data benefit from the AI-enabled advances built on their data. Alongside these criteria, we introduce an agentic evaluation workflow that both rates existing datasets on the AI-FAIR and traditional FAIR criteria and provides actionable feedback where critical metadata is missing or incomplete. This modular dataset evaluation tool, paired with a domain-appropriate checklist, translates these principles into a reusable assessment of machine-learning readiness, AI-readiness for specified tasks, traceability, and ethical and CARE-aligned stewardship. Through this approach we aim to create a community-informed system to close the model data loop, so that AI also enriches data to further enable scientific discovery.

cs.AI · cs.DB · cs.HC · cs.IR · q-bio.QM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.07688

TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation

Ziheng Chen, Jiali Cheng, Zezhong Fan, Hadi Amiri, Diyuan Wu, Gabriele Tolomei, Yang Zhang

原文摘要

Generative recommendation formulates next-item prediction as autoregressive generation over semantic ID (SID) sequences derived from users' historical interactions, making modern recommender systems structurally similar to large language models (LLMs). As privacy and safety concerns grow, these systems increasingly require concept unlearning to remove sensitive or harmful concepts associated with items. However, existing LLM unlearning methods cannot be directly applied to generative recommendation. Unlike word tokens with explicit semantics, SIDs are abstract identifiers that are often shared by both forget and retain items, leading to severe conflicts between concept removal and recommendation utility preservation. To address this challenge, we propose TRACER, an end-to-end concept unlearning framework based on token reassignment. Rather than directly suppressing shared SIDs, TRACER reassigns concept-related items to alternative tokens that better facilitate forgetting while minimizing side effects on retained items. We further introduce a coherence regularizer to preserve semantic consistency among retain items during unlearning. Experiments on real-world recommendation datasets demonstrate that TRACER effectively removes target concepts while substantially better preserving recommendation utility than existing unlearning baselines.

cs.IR · cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03768

Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention

Serdarcan Dilbaz, Arjun Krishna, Kiran Kamble, Daniel M. Bikel

原文摘要

Sparse attention cuts the cost of long-context inference by making the attention matrix sparse: each query attends only a subset of the sequence, chosen by a fixed pattern or, in recent production LLMs, learned per query. In DeepSeek Sparse Attention (DSA), the attention of DeepSeek-V3.2 and the GLM-5 family, every layer is preceded by a lightning indexer that scores the whole cache and keeps the k=2048 highest-scoring tokens for the layer to attend. At long context this indexer scan, not the sparse attention it feeds, is where the decode time goes. But adjacent layers select nearly the same tokens, so a layer can attend the selection of the previous indexer layer instead of its own. This removes the dependency: each indexer then runs concurrently with the attention of its layer. The resulting Multi-layer Indexer (MLI) needs no retraining and no new weights. Its default realization changes no kernel, running inside SGLang's production decode graph; an optional fused decode kernel accelerates it further on DeepSeek-V3.2. MLI composes with IndexCache (the cross-layer reuse GLM-5.2 ships as IndexShare): IndexCache drops the indexer from some layers, and MLI hides the scan on the rest. We serve DeepSeek-V3.2 and GLM-5 under IndexCache's protocol at retentions 1/2 to 1/32 (the fraction of layers that keep an indexer) and contexts 10K to 195K. At equal retention the composition decodes faster than IndexCache: up to 14.5% faster on DeepSeek-V3.2 and 9.8% on GLM-5 at 1/2, and 7.9% and 5.1% at 1/4, largest where IndexCache keeps the most indexers and growing with context. At retention 1/r it is faster still than IndexCache at 1/(2r) while keeping twice the fresh selections: at 128K it reaches 1.32x the unmodified model's decode throughput at 1/4, above IndexCache's 1.28x at 1/8. Its LongBench, RULER and LongBench v2 accuracy stays within a few percentage points of IndexCache's.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2405.01708

A deep causal inference model for interpretable travel behaviour analysis

Kimia Kamal, Bilal Farooq

原文摘要

Transportation policy assessment often involves causal questions, yet traditional travel behaviour lacks the ability of distinguishing causal association from non-causal correlations. We present the deep CAusal infeRence mOdel for traveL behavIour aNAlysis (CAROLINA), a novel framework that addresses both observed and unobserved confounders in discrete choice modelling through causal discovery and the strengths of deep neural networks. Within this interpretable framework, we also introduce a Generative Counterfactual model for forecasting individuals' behaviour by adapting the Normalizing Flow method. Through the case studies of virtual reality-based pedestrian crossing behaviour, revealed preference travel behaviour from London, and synthetic data, we demonstrate the effectiveness of our proposed models in isolating causal relationships from confounding associations. Our proposed causal framework enhances predictive accuracy by employing data-driven algorithms, while maintaining interpretability. In addition, the counterfactual results show that intervention mechanisms that can reduce pedestrian stress levels lead to a 35.35% increase in individuals experiencing shorter waiting times. External interventions that reduce travel distances of non-mandatory trips in London lead to a 47% increase in the possible use of active and public transit modes.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03319

TrafficInstruct: A Multi-Task Network Traffic Dataset and Benchmark for Instruction Tuning

Zhengdao Li, Hui Wen, Zixuan Wan, Weifeng Zhang, Yan Wu, Benlong Wu, Nenghai Yu, Weiming Zhang 等 9 位作者

原文摘要

Instruction tuning for multi-task network traffic analysis requires data with clearly defined sources, supervision targets, and evaluation conditions. We introduce TrafficInstruct, a newly collected dataset comprising raw packet captures and 55,000 structured supervised fine-tuning records across ten tasks: malware traffic detection, botnet detection, malicious DNS-over-HTTPS detection, Web attack detection, advanced persistent threat detection, encrypted VPN detection, Tor behavior detection, encrypted application/service classification, website fingerprinting, and application classification under concept drift. An automated workflow captures traffic from controlled software executions, attack experiments, and application activities. Labels are supported by task-specific collection evidence, including process or socket attribution, activity records, and execution outcomes. Filtering, sanitization, and task-specific transformations produce instructions, traffic observations, and structured answers. We verify sample sources and partition the dataset by complete collection sessions, keeping all samples from the same session within one partition. The benchmark defines allowed inputs, deterministic label mappings, fixed training/validation/test partitions, and task-wise scoring rules. We evaluate majority-class, random-forest, and ET-BERT baselines, an unadapted 27B language model, and independently trained task-specific LoRA adapters on a shared frozen base. Adapters are selected using validation data and evaluated on the corresponding test sets. Task-specific adaptation improves classification performance, supporting instruction tuning across diverse traffic-analysis tasks.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03317

Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages

Lucinda Laurent, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono, Fajri Koto

原文摘要

Activation steering offers a lightweight mechanism for controlling model behavior, but existing methods depend on sentence-level contrastive data that is unavailable for most of the world's languages. We show that multilingual sentiment lexicons are a viable substitute across three model families: aggregated multilingual lexicons outperform English-derived steering vectors for mid- and low-resource languages, while monolingual lexicons remain stronger for languages a model has specialized in during pre-training. The steering efficacy is mechanistically dictated by both representational density and pre-training priors. Large-magnitude English vectors overwhelm the compact representations of low-resource languages, causing "linguistic collapse." This fragility is mitigated by the norm-dampening of multilingual aggregation. Architectural biases, including bilingual specialization penalty and latent numerical rigidity, also heavily constrain cross-lingual steering responsiveness. Ultimately, our work establishes lexicons as a practical steering signal and offers a comprehensive mechanistic account of cross-lingual steering dynamics.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.20840

A Phenomenology of Neural Geometry in Vision-Language-Action Models

Mozes Jacobs, Aiden Swann, Mathilde Papillon, Siddharth Boppana, Fenil R. Doshi, Usha Bhalla, Thomas Icard, Matt Feiszli 等 19 位作者

原文摘要

Robotic manipulation is inherently geometric, but what shape does the world take inside the policy that performs it? Prior work on vision-language-action (VLA) policies establishes that task-relevant variables are linearly readable from activations, yet readability certifies only that a variable is present and says nothing about the shape its values trace, which may be curved and multi-dimensional. Using controlled sweeps, natural rollouts, linear probes, and activation interventions, we build a taxonomy of seven task-relevant concepts in VLA models. We find that realized geometry is predominantly multi-dimensional and is shaped by the constraints under which the policy acts. Physical joint limits, for example, leave wrist orientation an open arc rather than a circle, and distance to the target, a single scalar, is realized in two orthogonal subspaces, a coarse ruler for the approach and a fine ruler for the grasp. The same geometries reappear in two further VLA models on real-world robot data, indicating that they are neither model-specific nor artifacts of simulation. We demonstrate how the findings are actionable by steering along the geometry a concept realizes. Overall, this work lays out an initial phenomenology of realized geometry in VLA policies and demonstrates that a concept's shape carries as much importance as its readability.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03309

MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages

Andrei-Alexandru Manea, Jindřich Libovický, Philipp J. Rösch

原文摘要

Previous research shows that vision-language (VL) models struggle to understand fine-grained image details and tend to focus on the overall layout. Moreover, any weakness in English tends to be further amplified in the multilingual setting. To study that, we extend InpaintCOCO, an English dataset focused on fine-grained visual details, to 13 typologically diverse languages across five language families, creating MultiInpaintCOCO - a new multilingual benchmark of 953 minimal-pair examples. We further test several state-of-the-art models in multilingual multimodal retrieval, considering both light VL CLIP-like encoders and large language models. Our results show that performance degrades substantially for lower-resource languages, with the strongest predictor being the data resources available for the languages rather than typological similarity to English. In cross-lingual retrieval, most models exhibit a systematic bias toward English: when given a correct caption in a non-English language and an incorrect one in English, models preferentially select the English caption. This bias varies considerably across architectures. Among the tested models, Gemma 3 shows the strongest English preference while Qwen 3 is the least biased, despite both reaching similar monolingual accuracy across languages. The code is available at https://github.com/ufal/multi-inpaint-coco.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03308

LLMs Depend on Specialist Tools for Out-of-Distribution Generalization in MS/MS Structural Elucidation

Gabriel Asher, Cailum M. K. Stienstra, Tomo Oga, Devesh Shah Antonio H. de O. Fonseca, Niall O'Connor, Michael Widrich

原文摘要

A frontier language model was recently reported to solve 1D NMR structural elucidation without tools. We ask whether this capability transfers to tandem mass spectrometry (MS/MS) in the de novo setting, where the model must propose a structure directly from the spectrum without a candidate list or reference library. To separate reasoning from recall, we build a 100-analyte benchmark from MassSpecGym, split by each analyte's textual footprint into in-distribution (well documented in literature) and out-of-distribution (essentially undocumented) arms. We hold the model, harness, and output format fixed and vary only the LLM's access to domain-specific tools. Without tools, a frontier LLM reaches 52% Top-1 accuracy in-distribution but only 2% out-of-distribution. Only access to de novo structure generators improves out-of-distribution accuracy, raising it to as much as 38% Top-1, and the resulting agent outperforms the standalone de novo models both in and out of distribution. These results suggest that LLMs are not effective at de novo MS/MS structural elucidation on their own, and that further gains depend on the specialist tools available to the agent rather than on the LLM itself.

cs.LG · cs.AI · cs.CL · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03307

Safe-Ballbot: Tilt-Consistent MPC with Control Barrier Functions for Ballbot Navigation

Duc Cuong Vu, Tung Lam Nguyen

原文摘要

Ball-balancing robots (ballbots) must lean to accelerate, and the lean is limited by the wheel torques and by safety. Planners that use the full robot model are expensive, while planners that ignore the balance dynamics produce references that cannot be followed. This paper presents a two-layer navigation scheme for a three-omni-wheel ballbot. The upper layer is a model predictive controller on a \emph{jerk model} of the ball position, with discrete-time control barrier functions for static, moving, rotating and concave obstacles. The lower layer is a hierarchical sliding mode controller with an extended state observer and a robust exponential control barrier function on the tilt (HSMC-ESO-ECBF). The layers are linked by an acceleration bound derived in closed form from the largest steady tilt that the barrier function admits, so that the plan never asks for a lean the tracker refuses. For obstacles whose motion is only predicted, the obstacles are inflated by conformal prediction radii that bound the prediction error with a prescribed probability. In MuJoCo, with omni-wheel roller contacts and torque saturation, the scheme keeps at least $10$\,cm of clearance, tracks the plan within $2$\,cm RMS, keeps the tilt below the limit and plans in $9$--$12$\,ms, $10$--$15$ times faster than a full-model nonlinear MPC that enters the inflated obstacles; with predicted obstacles, the conformal inflation removes the collisions of a constant-velocity predictor in $30$ random crossing scenarios and reduces them in an endless run on a closed path.The source code and video illustrations are available at https://safe-ballbot.github.io

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.07342

From Structured Graphs to Unstructured Evidence: Agentic Root Cause Analysis on Digital Twins

Nicolas Tacheny

原文摘要

Root cause analysis over telecom and datacenter infrastructures is commonly addressed by methods that consume structured data, from graph traversal and rule-based correlation to probabilistic and learned models. Yet a digital twin of such an infrastructure cannot model everything at a reasonable cost. Operators therefore record much of what changes as unstructured data attached to the graph, where the discriminating evidence often sits. Methods restricted to structured attributes cannot use it. A diagnosis needs a layer that interprets this data. An agentic layer is a natural candidate, since which fragment matters depends on hypotheses that emerge during the investigation. We demonstrate its feasibility with ReAct, the most widely used agentic architecture. A single LLM interprets the descriptions and explores the graph through a typed tool interface exposed via the Model Context Protocol (MCP). On a benchmark of nine synthetic scenarios covering single-node, multi-node and distractor-heavy evidence (360 runs across four LLMs), a frontier-tier model names the root cause and its type on every run. It reaches 96.7% end-to-end diagnostic accuracy, which also requires the exact supporting evidence. A mid-tier model reaches 86.7%. Accuracy drops for every model when the evidence must be combined across several resources.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03305

Calibrated Multiaccuracy: Deterministic and Randomized Sample Complexity

Jiuyao Lu, Georgy Noarov, Aaron Roth

原文摘要

Calibrated multiaccuracy asks that a predictor be globally calibrated and multiaccurate with respect to a bounded test family $G$; that is, its residuals should be uncorrelated with every test $g(x)\in G$. This weakening of multicalibration suffices for many applications. Its sample complexity was not known to improve on that of full multicalibration, which is $\widetildeΘ\left(\frac{\log|G|}{\varepsilon^2} + \frac{1}{\varepsilon^{3}}\right)$ when $|G|$ is at least a sufficiently large power of $\log(1/\varepsilon)$. We resolve the sample complexity of $\varepsilon$-calibrated multiaccuracy, showing that it scales as $$ \widetildeΘ\left(\frac{\log|G|}{\varepsilon^2} + \frac{1}{\varepsilon^{5/2}}\right), $$ separating it from the complexity of multicalibration. The upper bound is obtained by an algorithm that outputs a randomized predictor. For deterministic predictors, we establish the tight rate $$ \widetildeΘ\left( \frac{\log|G|}{\varepsilon^2} + \frac{(\log|G|)^{1/3}}{\varepsilon^{8/3}} \right) $$ whenever $\log|G|=Ω(\log(1/\varepsilon))$. When $\log|G|\le\varepsilon^{-1+κ}$ for any fixed $κ\in(0,1)$, this rate is polynomially larger than the rate for randomized predictors. Thus, unlike for multicalibration, calibrated multiaccuracy exhibits a genuine sample-complexity separation between deterministic and randomized predictors. The matching upper and lower bounds show that the unusual cube-root dependence on $\log|G|$ is intrinsic. At $\log|G|\asymp\varepsilon^{-1}$, the minimax rates for randomized and deterministic calibrated multiaccuracy both coincide with the minimax rate for multicalibration.

cs.LG · cs.DS · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03302

EventGPT: Next-Event Pretraining on Banking Customer Histories

Denis Burakov

原文摘要

A model pretrained to predict a customer's next event can estimate the probability of future events without training on their labels and provide a reusable representation for supervised downstream banking tasks. We pretrain EventGPT, a hierarchical causal transformer, by next-token maximum likelihood estimation on the public Multimodal Banking Dataset (MBD-mini: 100,224 clients, 38.8 million transactions and 66.3 million geolocation pings). Keeping one state per event, EventGPT trains in about two hours on one L4 GPU at windows up to 8,192 tokens. From its next-event distribution, with no labels, EventGPT scores five targets of the form "the client makes a transaction of a given kind for the first time next month" at ROC-AUC 0.79 to 0.92. Gradient boosting on 114 engineered features needs 10,000 to 300,000 labeled client-months to match it on four targets and stays below it on the fifth. For product prediction, frozen EventGPT embeddings score below the engineered features (mean ROC-AUC 0.787 against 0.808 over five test folds), and a rank-averaged ensemble of EventGPT, profile fields and token counts with the engineered features adds 0.014 to 0.017, of which 0.007 to 0.016 is EventGPT's own. The code and pretrained weights are released.

stat.ML · cs.LG · q-fin.ST

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.14348

Detecting Historical Turning Points in Italian Media: A Complex Systems Approach to a Diachronic News Corpus

Dario Zarcone, Salvatore Miccichè, David Sanchez

原文摘要

Introduction: The increasing availability of large-scale textual corpora has opened new possibilities for data-driven, quantitative approaches to historical analysis using Natural Language Processing (NLP). However, diachronic corpora with historical relevance from the pre-digital era remain scarce and often incomplete. Methods: We present a quantitative approach to historical analysis based on the reconstruction and exploration of a diachronic corpus of around 600,000 articles from the Italian newspaper "La Repubblica", covering all the articles published from the first of January 1985 to the 31st of December 2000 - a period of major political, social, and geopolitical change in Italy and globally. Using NLP techniques, we analyze the text at both lexical and semantic levels; we then apply tools from complex systems and statistical physics to trace shifts in media discourse over time. Results: The word usage in the corpus is bursty, with a heavy-tailed distribution of Fano factors that is robust across timescales. Changepoints in word salience and the block structure of semantic similarity allow us to detect key transition periods, such as the transition from the First Republic to the Second Republic in Italy, or major international conflicts like the Gulf War or the Kosovo War, without relying on prior labeling. Periods of war correspond to lower entropy in the semantic space, indicating a more focused discourse. Discussion: The results show how combining computational linguistics with ideas from complex systems can offer new quantitative insight into historical changes, opening up new paths for studying the dynamics of media and society through large-scale textual data.

physics.soc-ph · cond-mat.stat-mech · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03298

SQLoom: Set-Contrastive Learning of Syntactic, Semantic, and Logical Dependencies for Text-to-SQL

Hao Fu, Degang Sun, Wan Wei, Jinxia Wei, Chun Long, Peng Gao

原文摘要

Text-to-SQL translates natural language questions into SQL queries, enabling database access without writing SQL. Fine-tuning open-weight large language models (LLMs) is cost-effective, but existing methods treat SQL as ordinary text and optimize token-level likelihood without explicitly modeling its syntactic, semantic, and logical requirements. Thus, a single incorrect alias or comparison operator can invalidate a query while contributing little to training loss. We propose SQLoom, a constraint-aware fine-tuning framework with supervision at three levels: syntactic validity under SQL grammar and database schema, semantic alignment between query decisions and the question, and logical consistency across dependent clause decisions. SQLoom extends supervised fine-tuning with a unified set-contrastive objective favoring sets of correct outputs over minimally different incorrect ones at each level. LLM agents propose this supervision, which a SQL parser and execution on counterexample databases verify. We also release Spider-Refined, a training dataset correcting 378 flawed Spider annotations and enriching database schemas. Experiments on Spider, BIRD, and three perturbed Spider variants show that SQLoom improves execution accuracy for Qwen3-1.7B from 62.9% zero-shot to 88.7% on Spider development, reaching 89.2% on Spider test and 73.4% on BIRD development. It outperforms fine-tuning, reinforcement learning, and agent-based baselines with up to 70 billion parameters. On question perturbations, SQLoom loses at most 0.6 accuracy points versus up to 12.1 for agent-based methods. It generates SQL in a single pass at 0.42s per query, 23$\times$ faster than a GPT-4-based agent method. These results demonstrate the effectiveness of set-contrastive supervision over token-level training.

cs.DB · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03296

Inferring Transferable Rewards via Active Inverse Reinforcement Learning

Victor Villin, Till Freihaut, Andreas Schlaginhaufen, Christos Dimitrakakis, Maryam Kamgarpour, Giorgia Ramponi

原文摘要

Inverse Reinforcement Learning (IRL) aims to recover expert rewards that transfer across environments with differing dynamics. Prior work has shown that such transfer is possible when gathering expert demonstrations across sufficiently different dynamics. In practice, however, expert demonstrations are costly, making it critical to select the right dynamics to reduce the quantity of expert data required for learning transferable rewards. We propose a two-phase approach: we first cycle through the available dynamics to obtain a reliable reward estimate, then actively select dynamics to reduce our uncertainty about the expert reward. Crucially, this yields novel sample complexity guarantees on transfer that hold for any dynamics, with a rate independent of the number of available dynamics. Empirically, our method significantly reduces the number of expert demonstrations needed to learn a transferable reward.

cs.LG · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03294

ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation

Peiyuan Tang, Yao Li, Xiaodong Zhang, Wuyang Zhang, Qin Xia, Yanyong Zhang, Zijiang Yang

原文摘要

Contact-rich manipulation requires fine-grained control and complex physical interactions with the environment, posing significant challenges for robot policy learning. Vision-only policies struggle with such tasks, as contact states and interaction forces are difficult to infer from visual observations alone. Existing methods mitigate this issue by incorporating force or tactile sensing. However, they often treat these signals as auxiliary observations without fully exploiting their role in modeling future interaction dynamics. To address this, we propose ForceLDM, a force-aware latent dynamics model that learns future contact and motion dynamics to guide action generation. Rather than directly predicting future observations, which can entangle task-relevant dynamics with irrelevant sensory details, ForceLDM learns a compact representation of future dynamics through knowledge distillation. Specifically, a teacher network with privileged future force/torque and optical flow signals extracts future dynamic features, which are then distilled into a student network trained only on current observations. This enables the student model to reason about upcoming contacts and physical dynamics without relying on future sensory inputs at deployment. To improve robustness and generalization, we further introduce a curriculum-based progressive noise injection strategy to mitigate over-reliance on future features. Experiments on five real-world contact-rich manipulation tasks demonstrate that ForceLDM outperforms state-of-the-art baselines, generalizes effectively to novel objects, and remains robust to environmental perturbations. Project page and code are available at https://tpy001.github.io/ForceLDM/.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03767

Quantifying out-of-distribution data severity with Wasserstein distances: benchmarking large language models for alloy property prediction

YuJie Liu, Dezhen Xue, Jun Sun, Xiangdong Ding, Zhibin Gao, Turab Lookman

原文摘要

As general-purpose Large Language Models (LLMs), such as Gemini and DeepSeek, exhibit increasingly advanced reasoning capabilities, a critical question arises: how do their property prediction abilities compare to those of domain-specific pretrained materials models? In this study, we evaluate predictions for Ti, steels, high-entropy alloy (HEA) and Al, demonstrating that general-purpose LLMs surprisingly outperform SteelBERT, MatSciBERT, and SciBERT. To further enhance performance, we introduce a hybrid approach that utilizes numerical priors from a prior model, such as CatBoost or SteelBERT, to guide the general LLMs (Deepseek V3.1, Gemini-2.5-Flash). By inputting these initial estimates from a prior model as prompts, the LLM acts as a reasoning corrector, achieving accuracy superior to the prior model and "unguided mode". Furthermore, we investigate the impact of data strategy using a similarity-based metric, revealing that data quality dominates quantity; using merely 5% of high-similarity reference data of training set as input yields performance similar to the results of using 100% of training set. Additionally, the LLMs demonstrate excellent uncertainty calibration, where self-reported "high" confidence strongly correlates with minimal deviation from ground truth. Our findings suggest that synergizing general-purpose LLMs with prior model numerical baselines and high-quality data curation creates a cost-effective and accurate paradigm for materials discovery, reducing the need for expensive domain-specific pretraining.

cs.LG · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03293

ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning

Zhuoli Ouyang, Changxi Chi, Siyuan Li, Tailin Wu

原文摘要

Zeroth-order (ZO) optimization enables memory-efficient large language model (LLM) fine-tuning, and recent methods incorporate curvature-aware strategies. However, in the high-dimensional parameter space of LLMs, these methods inherently suffer from exploding gradient variance and prohibitive costs. Conversely, confining updates to a low-dimensional subspace reduces variance but discards critical high-dimensional information, degrading performance. This creates a fundamental dilemma: full-space optimization is informative but has high variance, while subspace optimization has low variance but loses information. To break this trade-off, we propose ENGINE (Endogenous Variational MultiScale). Inspired by computational mechanics, we adapt static Variational MultiScale (VMS) theory to dynamic optimization, treating low- and high-dimensional spaces as resolved coarse and unresolved fine scales. Through a multigrid-style V-cycle, ENGINE alternates between spaces, dynamically probing fine-grained information in the high-dimensional space and injecting it to correct the efficient low-dimensional sampling process. Under appropriate assumptions, statistical analysis characterizes variance reduction and correction of curvature-induced bias, and convergence analysis establishes a stationarity bound for the corrected coarse updates. Evaluations on standard LLM benchmarks show that ENGINE achieves higher accuracy and faster convergence than existing ZO methods, achieving up to a $2.61\times$ speed-up in forward passes with zero additional peak memory overhead. Code is available at https://github.com/AI4Science-WestlakeU/ENGINE.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2510.12405

Continuous SUN (Stable, Unique, and Novel) Metric for Generative Modeling of Inorganic Crystals

Masahiro Negishi, Hyunsoo Park, Kinga O. Mastej, Aron Walsh

原文摘要

To address pressing scientific challenges such as climate change, increasingly sophisticated generative models are being developed to efficiently sample the large chemical space of potential functional materials. The proliferation of these models has necessitated the establishment of rigorous evaluation metrics. While uniqueness (U), novelty (N), and stability (S) of samples serve as standard metrics, their current formulations show several limitations. U and N rely on binary comparisons of crystals, rendering them dependent on heuristic thresholds, incapable of quantifying the degree of similarity, sensitive to atomic coordinate perturbations, and not invariant to sample permutation. Similarly, the binary assessment of S risks a premature exclusion of marginally unstable yet potentially novel candidates. These limitations are addressed by making the aforementioned metrics continuous. Furthermore, we integrate them into a unified metric ``continuous SUN" (cSUN), which offers a smoother score distribution and greater tunability than the conventional binary SUN metric. Experimental results demonstrate that our continuous metrics provide granular insights into sample distributions and secondarily serve as a soft screening score for selecting samples for further analysis. Finally, the use of cSUN as a reward signal in reinforcement learning is explored, showing that its adjustable weighting scheme effectively enhances sample diversity and convergence to a better optima in a Chemeleon2 case study.

cs.LG · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2406.07243

MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs

Vera Neplenbroek, Arianna Bisazza, Raquel Fernández

原文摘要

Generative large language models (LLMs) have been shown to exhibit harmful biases and stereotypes. While safety fine-tuning typically takes place in English, if at all, these models are being used by speakers of many different languages. There is existing evidence that the performance of these models is inconsistent across languages and that they discriminate based on demographic factors of the user. Motivated by this, we investigate whether the social stereotypes exhibited by LLMs differ as a function of the language used to prompt them, while controlling for cultural differences and task accuracy. To this end, we present MBBQ (Multilingual Bias Benchmark for Question-answering), a carefully curated version of the English BBQ dataset extended to Dutch, Spanish, and Turkish, which measures stereotypes commonly held across these languages. We further complement MBBQ with a parallel control dataset to measure task performance on the question-answering task independently of bias. Our results based on several open-source and proprietary LLMs confirm that some non-English languages suffer from bias more than English, even when controlling for cultural shifts. Moreover, we observe significant cross-lingual differences in bias behaviour for all except the most accurate models. With the release of MBBQ, we hope to encourage further research on bias in multilingual settings. The dataset and code are available at https://github.com/Veranep/MBBQ.

cs.CL

查看论文
arXiv ↗PDF ↗