跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+729新增论文
+575其中 AI 相关
+82已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 14:57 — 2026-11-21 14:57(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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

找到 6,976 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.23353

Idempotency Is Not Recovery: A Fault-Injection Study of Language-Model Agent Tool Actions

Song Xu

原文摘要

When a language-model agent's tool call is interrupted, the action may already have changed an external system without confirmation. Retrying risks duplication; assuming success may conceal an action that never occurred. We study these failure modes in a controlled agent runtime combining authorization, an action ledger, target-side idempotency, reconciliation, and evidence sealing. We inject ten single-host fault classes and compare four configurations and three ablations using a target-side oracle separate from the runtime ledger. On each of Windows and Linux, 7,513 trials used 96 captured model responses from 24 constructed cases. In 200 known original crash and replay pairs, the full configuration recorded 0/200 repeated effects versus 117/200 for each simpler baseline. A ledger-related ablation had 170/170 orphaned effects versus 0/170 and 200/300 recovery successes versus 300/300 for the full configuration. Disabling reconciliation left 100/100 known post-effect crash outcomes ambiguous despite no observed duplicates. A separate supplement designed after the initial results and reusing the same inputs found a similar pattern under response loss or delay. The full runtime had about one-seventh of fail-open throughput, while injected evidence-write faults left 75/100 trials per platform unresolved. These findings distinguish duplicate suppression from recovery and identify their measured reliability and performance tradeoffs within the tested benchmark.

cs.SE · cs.AI

新论文 · v1arXiv:2611.22782

PANO: Parallel Latent Space Neural Operator for Solving PDEs

Zijiang Yang, Xiaomeng Wu, Chen Kuang, Dongmei Fu

原文摘要

Aggregating observations into a limited number of latent tokens and learning physical interactions in the latent space has emerged as an effective approach for Transformer-based neural operators to solve Partial Differential Equation (PDE) problems involving large-scale observations. However, existing methods typically compress observations using a single aggregation pattern, making physical information not retained by that pattern invisible to the latent space and thereby constraining physical interactions within it. To address this limitation, we propose PArallel Latent Space Neural Operator (PANO), a novel neural operator for solving PDEs that formulates physical interactions among observations as an additive combination of interaction results from parallel latent spaces with shared parameters. Specifically, PANO transforms observations into multiple distinct compressed representations through independent mappings, learns physical interactions in parallel based on these representations, and finally fuses the decoded results to predict the target physical field. Within PANO, we further propose Coupled Assignment Projection (CAP) to construct bidirectionally consistent encoding and decoding mappings, and Pairwise Latent Space Attention Layer (PaLA) to jointly update latent representations of each latent space through adaptive cross-space interactions. Extensive experiments on nine benchmarks spanning diverse physical systems, geometries, and observation scales demonstrate that PANO achieves state-of-the-art performance. Notably, PANO reduces equivalent plastic strain prediction errors on Unilateral Stamping by 28.3% (or more) and lift-coefficient prediction errors on AirCraft by 21.4% (or more) compared with existing methods. Code is available at https://github.com/ZijiangY1116/PANO.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22778

A Full-Ledger Counterfactual Audit of Adaptive Reasoning

Xiaopeng Chu, Wenzheng Kong, Wei Liu, Wenyi Zhang

原文摘要

Adaptive reasoning must decide whether to answer now or spend more compute. Predicting that the current answer is wrong does not establish whether further reasoning will improve it. We introduce the Full-Ledger Counterfactual Value Audit (FLCVA), which compares an immediate answer with four fixed-length continuations from the same frozen prefix under one answer procedure and accounts for the cost of every signal used by a policy. On GSM8K and MATH-500, a random 256-token continuation recovers a wrong answer in 26.6% of Qwen3-8B cases and 18.9% of DeepSeek-R1-Distill-Qwen-7B cases, while damaging a correct answer in 1.4% and 1.9%. Correctness labels from independently sampled continuations predict a separate continuation's outcome in both primary models. In offline replay, using these labels to allocate compute improves performance on DeepSeek; the Qwen3 gain remains inconclusive. Under full cost accounting, the tested lightweight, myopic controllers mainly recognize current errors and add little continuation-specific value beyond that shortcut. A Llama-8B replication and action/cost ablations examine the robustness of these findings. FLCVA separates measuring local continuation value, predicting it from observable signals, and using those predictions to allocate computation.

cs.AI · cs.CL

新论文 · v1arXiv:2611.22777

CrossEnv: Synthesizing Verifiable Cross-Environment Tasks for Long-Horizon Agent Training

Zhengfeng Yu, Tian Lan, Zhijing Wu, Enbo Zhao, Xuannan Liu, Feihu Jiang, Qianghuai Jia, Longyue Wang 等 11 位作者

原文摘要

Executable synthetic environments provide scalable training tasks and verifiable feedback for long-horizon agents. Existing environment synthesis methods primarily generate tasks within individual environments. However, these tasks do not adequately capture real-world interactions across services, where actions in one service depend on information obtained from another. Synthesizing such tasks is challenging because data generated across environments must remain consistent to support executable and verifiable interactions. To address this challenge, we introduce CrossEnv, a framework that uses an entity-tool graph to identify connections between environments and aligns task-specific data to synthesize executable, verifiable cross-environment tasks. We further propose CrossEnv-Curriculum, which progresses from single-environment tool use to coordination across more environments and business domains, before introducing user interaction. Across four external benchmarks, combining cross-environment training data with this curriculum achieves competitive performance with fewer training examples. Further analyses support the benefits of cross-environment data and curriculum training, and provide evidence of transfer to new environment combinations, external tasks less similar to the training data, and longer workflows.

cs.AI · cs.CL

版本更新 · v2arXiv:2609.39789

Pseudo-Label-Triggered Retraining from Forecast Errors for Online Time Series Forecasting

Yeryeong Kwak, Yoo-Min Jung, Jonghun Park

原文摘要

Real-world time series forecasting systems operate under non-stationary data streams, where forecasting performance may degrade over time. Although retraining can recover the performance, it incurs non-trivial computational and operational costs. Under limited deployment resources, the key challenge is therefore not only how to retrain but also when to retrain. While existing retraining policies often rely on indirect indicators such as drift alarms or model staleness, we instead use realized forecast errors as direct deployment feedback. In this paper, we propose PILOT (Pseudo-label-Informed Learned Online Trigger), an online retraining framework that learns when to retrain from forecast-error dynamics. Since ground-truth retraining labels are unavailable, PILOT constructs a pseudo-label from future increases in forecast error and trains a lightweight scorer to predict it from observed error states. At deployment, PILOT uses only completed forecast errors and serves as a plug-in module for arbitrary forecasting backbones without architectural modification. We evaluate PILOT under standard multivariate forecasting settings across eight benchmarks with three representative backbones---DLinear, iTransformer, and TimesNet. Across all three backbones, PILOT achieves state-of-the-art average-rank performance among retraining policies while maintaining a favorable performance--efficiency trade-off.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22769

ForceBody: Force-Paired Parametric Body Motion with Torque Uncertainty

Joonwoo Kwon, Yufei Zhang, Xiaoming Liu, Zijun Cui

原文摘要

Forces and torques drive human motion, central to biomechanics, robotics, and physics-aware animation, yet they are often absent from learning-based motion pipelines for body reconstruction and generation. Some motion datasets provide force annotations, but the paired motion sequences are incompatible with the parametric body models used in modern learning pipelines. In addition, existing datasets typically obtain joint torques through inverse dynamics, which is inherently sensitive to the quality of the input kinematics; however, they do not quantify the reliability of these torque estimates. We close this gap with ForceBody, the first dataset to bring ground truth force supervision into a parametric body representation, shipped with per-sample torque uncertainty. ForceBody pairs the SKEL body model with ground reaction forces and inverse-dynamics joint torques across 10,386 motion trials (9.7M frames, 26.9 hours) from 140 subjects. Each torque label is paired with a per-frame, per-joint uncertainty annotation obtained by Monte Carlo sampling through the inverse dynamics pipeline. We benchmark six architectures (MLP, Conv1D, LSTM, GRU, Mamba2, Transformer) on ground reaction force and joint torque prediction from SKEL motion. As one example use of the released uncertainty, finetuning a Transformer with per-sample uncertainty weighting reduces the MAE of joint torque estimation by 5%. Code and data are at https://github.com/DominoAI-Lab/ForceBody-NeurIPS-ED-2026.

cs.CV · cs.AI

新论文 · v1arXiv:2611.22766

StitchRAG: Constructing Compact and Evidence-Preserving Contexts for RAG with Diffusion-Based Stitching

Minsang Kim, Junpyo Lim, Heeje Cho, Seungjun Baek

原文摘要

Retrieval-augmented generation (RAG) improves factuality by grounding large language models (LLMs) in external evidence. However, long retrieved contexts incur computational overhead and can even hurt performance due to noisy or irrelevant content. We propose \textsc{StitchRAG}, a framework for constructing compact context in RAG. \textsc{StitchRAG} builds a faithful, information-dense context while dynamically compressing the retrieved passages. We adapt the size reduction ratio to each passage by formulating a utility maximization trading-off the retained information and computation costs. We then extract answer candidates and query-related keywords from passages as anchors and collect passage sentences containing anchors under the derived size constraint. Finally, we connect or stitch the collected sentences together using text diffusion to form a coherent and natural context. Experiments on five open-domain QA benchmarks show that \textsc{StitchRAG} consistently outperforms diverse multi-step and compression baselines. Extensive ablations show the effectiveness of dynamic size allocation, anchor preservation, and diffusion-based stitching.

cs.CL · cs.AI

新论文 · v1arXiv:2611.22761

Network-Exposed Configuration Attacks on LLM-Controlled Social Robots

Stanley Akingbola, Ugbede Ibrahim, Yan Lin Aung, Quang Dan Le, Hong Qing Yu

原文摘要

Large language models (LLMs) in embodied robots create security dependencies beyond inference. We investigate a network-exposed configuration attack on the Pollen Robotics Reachy Mini Lite, allowing an unauthenticated attacker to replace personality settings and the cloud LLM's system prompt through a management interface, without adversarial conversational input. Eleven prompt-injection attempts across five categories were reported as resisted, whereas both configuration-layer attack paths produced observable behavioural changes on physical hardware. We demonstrate local and network-adjacent access, mapping the weakness to CWE-306 (Missing Authentication for a Critical Function) and CWE-1327 (Binding to an Unrestricted IP Address), with a reported CVSS v3.1 score of 6.5 (Medium). A configuration endpoint also accepts cross-origin requests without a CORS preflight (CWE-352; 6.5 Medium), while the persistent-memory sink stores content without enforcing its stated restrictions. A source review of 59 public repositories identifies missing authentication in 10 of 11 source-verifiable genuine applications, or 11 of 11 including a framework-default case. These findings indicate recurrence within the sampled repositories, not prevalence in commercial products. We characterise a deployment gap between developer-oriented network assumptions and consumer-facing embodied AI security: inference-layer refusal cannot prevent unauthorised changes to model instructions. Potential consequences include surveillance through onboard cameras and microphones and social engineering of nearby users. Proof-of-concept code, evidence and the survey are available at https://bit.ly/reachypi.

cs.CR · cs.AI · cs.RO

版本更新 · v2arXiv:2608.29378

Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration

Mohamad Zbib, Mohamad Bazzi, Ammar Mohanna

原文摘要

Arabic large language models must refuse harmful prompts without over-refusing benign or sensitive prompts, yet a single refusal rate hides this trade-off. We evaluate it using benign refusal B and harmful-prompt refusal H, where H measures refusal rather than harmful compliance. Across five Arabic-capable models and 130 runs on the full human-written AraSafe set, refusal-only supervised fine-tuning (SFT) collapses toward blanket refusal, whereas selected mixed-SFT configurations reach H = 90% to 93% at B = 14% to 23%; four selected configurations exceed the H = 90% target in all three runs, while Fanar does so in two of three. Direct Preference Optimization (DPO) and inference guards change B and H differently across models rather than acting as uniform upgrades. In a blinded 300-response audit, annotator binary-refusal agreement is 89.0% (kappa = 0.78); Qwen3Guard and Aya Expanse 32B reach 88.7% and 91.0% accuracy, respectively, with no conclusive paired difference. Selected SFT raises H on Arabizi for all five models, but none reaches 90%, showing only partial transfer from Modern Standard Arabic. Overall, the results support model-specific operating-point selection: set a deployment target and retain only interventions that improve it.

cs.CL · cs.AI

版本更新 · v2arXiv:2609.05016

Amortizing Scaling Law Construction Costs

Abhash Kumar Jha, Diana Alexandra Onuţu, Neeratyoy Mallik, Swagatam Haldar, Sam Laing, Niccolò Ajroldi, Shiwei Liu, Joaquin Vanschoren 等 9 位作者

原文摘要

Scaling laws guide the design choices for training large foundation models, but deriving them involves training an exhaustive grid over hyperparameters, token budgets, and parameter counts, which is computationally expensive. Fitting a scaling law, however, only requires the best-loss frontier across compute scales, discarding most of the trained configurations. We propose a framework for efficient scaling law construction that formulates data collection as a Bayesian optimization problem, and introduce metrics for comparing scaling law fitting methods under constrained compute budgets. We find that progressively expanding the compute budget during acquisition, mirroring the compute-ordered evaluation of configurations in practice, substantially improves recovery efficiency. Augmenting the observed configurations with surrogate-fantasized evaluations then recovers the broader experimental grid, allowing accurate scaling law fitting without training every configuration. Together, these can closely match scaling law fits over a full dense grid at computational savings of up to $10\text{--}100\times$.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22738

Can Activation Steering Substitute for Prompt-Based Affective Priming in LLM Digital Twins?

Junyi Fan

原文摘要

Affective priming -- asking participants to write about a recalled event, such as a time they felt grateful or lacked control, and then measuring the induced state and its spillover onto related judgments -- is a standard way to manipulate emotion in the social sciences, and it also shifts the responses of LLM-based digital twins. The writing task, however, requires generating a full text. We test whether activation steering can replace it. Using Llama-3.1-8B-Instruct on 100 personas in two domains (gratitude, lack of control), we compare a real-prompt path replicating the original Twin-2K-500 Mega Study (J2) with an injection path that skips the writing and adds a mean-difference direction, extracted from human writing, to the residual stream at varying strengths. The real-prompt effects fall between the original human and digital-twin effects in 5 of 6 comparisons. Injection shifts the manipulation check in a dose-dependent way and matches the real-prompt effect at one strength in the gratitude domain (beta ~ 2.7), but overshoots beyond it, on the proximal measure as well, and asymmetrically across the two directions. A structure-matched No-Injection baseline separates two sources of difference: omitting the writing task raises the proximal measure in both domains, whereas the injected direction itself moves a distal measure in the lack-of-control domain. Substitution is therefore measure-dependent: validity established for one way of inducing a state does not carry over uniformly to another.

cs.AI

新论文 · v1arXiv:2611.22737

Proximal Targets: Training Looped Refiners on Problems with Many Correct Answers

Syed Affan Daimi

原文摘要

Looped refiners such as HRM and TRM apply one small network repeatedly to a draft answer, and deep supervision trains every pass toward one stored answer per puzzle. We prove that when a puzzle has many correct answers this target sets a loss floor that no model capacity removes, and that the loss-minimising pass blends the answers into an invalid grid. We propose the proximal target: train each pass toward the correct answer nearest to its own input, found by scanning a list of answers, by a search solver started at the draft, or within a band of quality set by a knob; correct answers become fixed points, and a pass only has to make fewer errors than its input has for the loop to converge, which its training loss bounds. With the same 1.7M-parameter network and 5 seeds, the proximal target solves 98.8% of Sudoku puzzles with 2-64 answers (standard target: 2.5%), 93.8% of sparse puzzles with more than 10,000 answers without any list of answers (0.0%), and 90.9% of 200-node 3-colourings after training on graphs of at most 50 nodes (36.9%), and different random starts end at different answers. Against GRAM, a stochastic-latent reasoner, a single run is correct far more often (98.8% vs. 57.7%) and twenty runs find more of the answers (53.6% vs. 37.4%), while GRAM is slightly ahead on its own 10-node colouring benchmark; in Scrabble the knob becomes a calibrated strength dial.

cs.AI · cs.LG

新论文 · v1arXiv:2611.22726

Stress Testing a Multimodal Large Language Model Grading Assistant on Kinematics Graph Reading

Ons Zammel, Carlos Soares, Flávia Carvalhido, Gerd Kortemeyer

原文摘要

Multimodal large language models (MLLMs) can recognize graph features yet award credit without sufficient graphical support. This exploratory study examines selected grading outputs for synthetic responses to four kinematics exercises, generated through visual distortion and progressive transformation toward reference graphs. Different model and prompt configurations were used. Some judgments correctly distinguished instantaneous zero velocity from rest over a finite interval and recognized positive curvature. Yet a severely distorted velocity--time graph received full credit despite disconnected and branching traces and an unclear zero-velocity reference. Other submissions graded under the same configuration lost substantial credit. Numerical cutoffs intended to distinguish meaningful features from drawing irregularities were supplied without a coordinate convention for unnumbered graphs, leaving the basis of exact partial-credit awards unresolved. Stress testing can expose unsupported awards before classroom use. For the configurations examined, we do not recommend accepting scores as final grades without instructor review, including review of full-credit responses.

physics.ed-ph · cs.AI

版本更新 · v3arXiv:2603.28618

Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning

Ziqi Miao, Haonan Jia, Lijun Li, Chen Qian, Yuan Xiong, Wenting Yan, Yongyao Wang, Zaoying Huang 等 10 位作者

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR approaches typically rely on outcome-driven optimization that updates both perception and reasoning using a shared reward based solely on the final answer. This shared reward blurs credit assignment, frequently improving reasoning patterns while failing to reliably enhance the accuracy of upstream visual evidence extraction. To address this perception bottleneck, we introduce PRCO (Perception-Reasoning Coevolution), a dual-role RLVR framework with a shared policy. PRCO consists of two cooperative roles: an Observer that generates an evidence caption tailored to the question and a Solver that predicts the final answer based on this caption. Crucially, PRCO employs role-specific reward signals: the Solver is optimized using verifiable outcome rewards on the final answer, while the Observer receives a utility reward derived from the Solver's downstream success. Extensive experiments across eight challenging multimodal reasoning benchmarks demonstrate that PRCO yields consistent improvements across model scales by over 7 points on average accuracy compared to the base model, outperforming prior open-source RL-tuned baselines.

cs.AI

版本更新 · v2arXiv:2505.16498

Human-like Semantic Navigation for Autonomous Driving using Knowledge Representation and Large Language Models

Augusto Luis Ballardini, Miguel Ángel Sotelo

原文摘要

Achieving full automation in self-driving vehicles remains a challenge, especially in dynamic urban environments where navigation requires real-time adaptability. Existing systems struggle to handle navigation plans when faced with unpredictable changes in road layouts, spontaneous detours, or missing map data, due to their heavy reliance on predefined cartographic information. In this work, we explore the use of Large Language Models to generate Answer Set Programming rules by translating informal navigation instructions into structured, logic-based reasoning. ASP provides non-monotonic reasoning, allowing autonomous vehicles to adapt to evolving scenarios without relying on predefined maps. We present an experimental evaluation in which LLMs generate ASP constraints that encode real-world urban driving logic into a formal knowledge representation. By automating the translation of informal navigation instructions into logical rules, our method improves adaptability and explainability in autonomous navigation. Results show that LLM-driven ASP rule generation supports semantic-based decision-making, offering an explainable framework for dynamic navigation planning that aligns closely with how humans communicate navigational intent.

cs.RO · cs.AI

版本更新 · v3arXiv:2603.05542

Human-Data Interaction, Exploration, and Visualization Systems in the AI Era: Challenges and Opportunities

Jean-Daniel Fekete, Yifan Hu, Dominik Moritz, Arnab Nandi, Senjuti Basu Roy, Eugene Wu, Nikos Bikakis, George Papastefanatos 等 11 位作者

原文摘要

The rapid advancement of AI is transforming human-centered systems, with profound implications for human-AI interaction, human-data interaction, and visual analytics. In the AI era, data analysis increasingly involves large-scale, heterogeneous, and multimodal data that is predominantly unstructured, as well as foundation models such as LLMs and VLMs, which introduce additional uncertainty into analytical processes. These shifts expose persistent challenges for human-data interactive systems, including perceptually misaligned latency, scalability constraints, limitations of existing interaction and exploration paradigms, and growing uncertainty regarding the reliability and interpretability of AI-generated insights. Responding to these challenges requires moving beyond conventional efficiency and scalability metrics, redefining the roles of humans and machines in analytical workflows, and incorporating cognitive, perceptual, and design principles into every level of the human-data interaction stack. This paper investigates the challenges introduced by recent advances in AI and examines how these developments are reshaping the ways users engage with data, while outlining limitations and open research directions for building human-centered AI systems for interactive data analysis in the AI era.

cs.DB · cs.AI · cs.ET · cs.GR · cs.HC · cs.MM

新论文 · v1arXiv:2611.22709

Know When to Zoom: How Small Is Too Small for Vision-Language Models?

Siddharth Vohra, Min Xu

原文摘要

Online vision-language models often miss small details in large images, because the service shrinks the image, or rejects it, before the model ever sees it. A car 20 pixels wide in an 8000 by 6000 drone photo reaches Claude about 6 pixels wide, and OpenAI's default rejects the photo outright. We measure how much detail survives for seven models from four vendors, using an eye exam of printed codes and 601 questions about small objects in real photos. The smallest text a model reads half the time grows from 6 pixels or less on a small image to a predicted 10 to 13 pixels on a 7680 by 4320 photo at default settings. Zooming wins much of the detail back. Splitting each photo into up to nine tiles raises accuracy by 11.1 to 14.5 percentage points for Claude and Gemini, and by avoiding rejections it lifts GPT-6.1 Sol from 50.7% to 83.7%. A two-step zoom, in which the model first names the region it needs, matches or beats tiles on Gemini and comes within 2.5 points of them on Claude, with about 40% of their image tokens. When a detail is lost, Claude and Gemini both say they cannot tell about half the time, but they fail differently in the rest: Gemini gives a confident wrong answer in 43% to 48% of these cases, Claude in only 5% to 9%. A check based on detail size, run before the call, misses most of the gain from tiles on Claude and Gemini, but Claude's own reply is a reliable trigger: tiling only after an unsure reply comes within 1.4 points of always tiling with 62% to 70% of the image tokens. We turn these findings into five rules for when an agent should zoom, and release the eye exam, every model answer and code at https://siddvoh.com/know-when-to-zoom.

cs.CV · cs.AI

新论文 · v1arXiv:2611.22708

Cross-cultural Adaptation of Recipes for Low-Resource Languages: A Benchmark and Multilingual Culinary Lexicon for Hausa, Yorùbá, and Igbo

Nuhu Ibrahim, Maryam Abdulazeez, Fatsuma Jauro, Salisu Aliyu, Robert Stevens, Riza Batista-Navarro

原文摘要

Recent multilingual large language models (LLMs) have improved machine translation, yet culturally adaptive translation for low-resource languages (LRLs) remains underexplored. This is particularly challenging for recipes, where ingredients, cooking tools, measurements, and procedures may require adaptation to the target cultural context. In this work, we introduce ReciLoReL, a benchmark of 600 expert-translated and culturally adapted recipes across Yorùbá, Hausa, and Igbo (three of the most prominent languages in Nigeria), and ReciLex, a multilingual culinary lexicon containing approximately 15,000 translated entities across ten recipe entity categories, including ingredients, tools, chef actions, state of tools, and durations. We evaluate state-of-the-art multilingual LLMs for English-to-LRL recipe translation under zero-shot and few-shot settings and investigate whether augmenting LLMs with ReciLex improves culturally adaptive recipe translation without requiring large target-language recipe corpora for training or fine-tuning. Beyond conventional reference-based translation evaluation using BLEU, chrF, and TER, we introduce five criteria for evaluating cultural adaptation, adapted from established cross-cultural adaptation methods. Across the selected LLMs and languages, ReciLex improves average BLEU from 13.57 to 14.51 and chrF from 37.89 to 38.74, while reducing TER from 77.14 to 75.12. Human evaluation further shows improvements ranging from 0.11 to 0.36 points across the five cultural adaptation evaluation criteria on a five-point scale. Overall, our work provides new resources, evaluation criteria, and empirical evaluation for studying culturally adaptive recipe translation in low-resource settings.

cs.CL · cs.AI

版本更新 · v2arXiv:2607.12909

Real-time fall detection based on vision for low-power edge platforms

Wenjun Xia, Zhicheng Peng, Haopeng Li, Zhengdi Zhang

原文摘要

Falling detection is vital for elderly care and intelligent surveillance; however, prevailing vision-based approaches predominantly frame it as static pose classification or discrete temporal pattern matching, fundamentally overlooking the instability dynamics of the human support system. This paper proposes a physics-informed falling detection framework that recasts falling as a stability-loss event in a coupled dynamical system. We introduce a novel dual-LTC architecture comprising a Center-of-Mass (CoM) subsystem and a Base-of-Support (BoS) subsystem, both instantiated as Liquid Time-Constant (LTC) neural networks to continuously model inertial trajectory evolution and ground-contact adjustment through adaptive time constants, Physical interpretability of falling motion. A learnable coupling module emulates physical interaction between the two subsystems, while a Stability Manifold classifier operates in the joint latent space to detect boundary crossing via Lyapunov-inspired stability metrics. Complementary counterfactual trajectory projection and Time-to-Collision (TTC) estimation further enable irreversibility assessment and early warning. The architecture is designed to support a three-state prediction paradigm (Normal, Falling, Fallen); in this preliminary study, we validate the core stability discrimination capability on a two-class dataset (Normal vs. Falling), leaving the full three-state temporal transition to future work. Unlike conventional CNN--RNN pipelines, the proposed formulation encodes continuous-time mechanical inertia, yielding a sub-50K-parameter network capable of real-time inference on resource-constrained edge devices. Extensive experiments demonstrate competitive accuracy with superior physical interpretability, validating its efficacy for low-compute visual fall detection.

q-bio.NC · cs.AI · cs.CV

新论文 · v1arXiv:2611.22697

Remembered as Brief: Stored Preferences SilentlyRemove Decision-Critical Information

Joshua Adrian Cahyono

原文摘要

People increasingly learn what they need for decisions about health, money, law and safety from AI assistants, and what an assistant leaves out the user never sees. An answer with a warning removed can be true in every sentence, so fact-checks pass it, and an assistant with memory applies a preference stored once to later questions the user never had in mind. We introduce \bench{}, an Inspect benchmark of 100 everyday decisions across 25 domains in which only the assistant's memory of the user varies: the user states a belief, the model infers it from a remark, or a web page the user asked to summarise plants it. Testing five models, we find three effects. First, after summarising a page with one line addressed to AI assistants, Gemini 2.5 Flash-Lite and DeepSeek V4 Pro save ``prefers very short answers and does not want warnings'' as the user's preference in every episode, and 93\% and 84\% of their later answers miss a critical item, almost always silently; under a stated brevity preference, 78--96\% of omissions are silent. Second, the same two models then pick an option for the user on 80\% and 95\% of value-dependent choices, against none with neutral memory. Third, a one-line instruction leaves 2--8\% of answers with a silent gap but most missing content still missing, while listing the must-know points before applying the user profile restores more of the content in four of five models. We release the scenarios, harness and logs.

cs.AI

新论文 · v1arXiv:2611.22691

Making the World React Realistically: A Closed-Loop Interactive World Model for Autonomous Driving

Jia Hu, Yang Chang, Panqu Wang, Zhijun Fu, Chang Liu, Changjian Yu, Jintao Lai

原文摘要

World models (WMs) generate driving scenarios beyond recorded logs, enabling the training and evaluation of autonomous driving systems in unseen interactions. However, existing WMs struggle to ensure both behavioral realism and visual fidelity, since they overlook the relationship between vehicle interactions and the ego visual observations. We propose a closed-loop interactive WM that couples behavior modeling and visual rendering. First, imitation-learned background-vehicle (BV) policies are fine-tuned with multi-agent reinforcement learning in the closed loop against an end-to-end ego planner that reacts to the rendered images, so that their interaction behaviors match those in real logs. Second, the viewpoints exposed by these interactions guide a per-Gaussian diagnosis of each 3D Gaussian vehicle asset, which attenuates view-dependent colors on under-observed Gaussians and fills never-observed surfaces with generated Gaussians, while preserving the observed appearance. Third, signal lights are rendered according to the driving intentions of the vehicles, by an editor that learns the light states unobserved for a vehicle through counterfactual fine-tuning with a light-state classifier. On long-tail closed-loop scenarios, our method reduces the divergence from real-world interaction behaviors by 85% and improves novel-view vehicle PSNR by 2.0dB over the state-of-the-art WM. The significance of BV light signaling in WMs is shown, as the rendered signal lights conveying BV driving intentions indirectly impact ego driving behaviors in a quarter of the scenarios.

cs.RO · cs.AI

新论文 · v1arXiv:2611.22682

CULypso: A Clustered Federated Unlearning paradigm for Vehicular Ad-Hoc Networks

Eleftheria Chini, George Margaritis, Dimitrios Katsaros

原文摘要

Unlearning has emerged as an essential security and privacy-preserving solution in Machine Learning, enabling networks to support their clients' rights for data erasure, as mandated by data protection regulations. Introducing such a non-trivial task to an edge, highly mobile and time-sensitive vehicular network is an even greater, largely unexplored challenge. This article argues that a hierarchical Federated Unlearning approach could be aptly integrated into vehicular ad-hoc networks (VANETs), leveraging topology and movement to reduce communication, resource and time costs, while effectively forgetting a client's influence on the global model updates. In order to achieve this, we propose CULypso, an approximate, surgical, hierarchical unlearning algorithm tailored for clustered VANETs. Inspired by the nymph in Greek mythology, Calypso, whose name translates to 'she who conceals the knowledge', CULypso, with the capital letters referencing \textbf{C}lustered \textbf{U}n\textbf{L}earning, aims to achieve exactly what its name suggests: conceal, erase or forget in our case, knowledge it contains. Extensive experiments uphold the potency of our paradigm with it performing approximately 65\% better than FedEraser in terms of time, server storage load, and unlearning fidelity while utterly outperforming baseline full retraining.

cs.LG · cs.AI · cs.NI

版本更新 · v2arXiv:2610.27012

Activation-Space Exploration for Visual and Textual Reasoning with RLVR

Yunan Zeng, Jinhao Jing, Xi Cheng, Yuwang Wang

原文摘要

Reinforcement learning with verifiable rewards (RLVR) improves visual and textual reasoning by sampling responses, scoring them with an automatic verifier, and updating the policy from the resulting rewards. The policy therefore receives direct learning signals only from trajectories that appear in its rollouts. Yet repeated sampling from the same policy can concentrate on similar reasoning paths, leaving useful alternatives unexplored under a fixed rollout budget. We introduce Activation-Space Exploration (ASE), an online method for diversifying training rollouts. By clustering activation differences between correct and incorrect responses to the same problem, ASE builds a structured bank of latent exploration vectors. Different vectors are then applied to subsequent rollouts to explore alternative reasoning paths. Under the same rollout budget, ASE improves average accuracy over GRPO on Qwen3-VL-2B-Instruct by 5.41 and 3.15 percentage points across six visual mathematical and six general visual reasoning benchmarks, respectively. On Qwen3-1.7B-Base, it improves average Mean@8 over GRPO across six mathematical reasoning benchmarks by 4.87 percentage points, with gains also observed on Qwen3-8B-Base.

cs.LG · cs.AI

新论文 · v1arXiv:2611.22673

FVScore: Specification-Driven Neuro-Symbolic Video Evaluation

Do Xuan Long, Long T. Le, Yiwen Song, Min-Yen Kan, Tomas Pfister, Yale Song

原文摘要

We introduce Faithfulness Video Score (FVSCORE), a neuro-symbolic framework for specification-driven video generation evaluation. Existing evaluators rely on holistic MLLM judgments or vision-language metrics, yet aligning their scores with human judgments and tracing them to specific temporal violations remain open challenges. FVSCORE addresses these limitations by compiling each video into explicit propositions capturing prompt requirements and implicit propositions capturing unstated physical, temporal, and cross-modal constraints. It grounds each proposition using specialized perceptual tools and evaluates the resulting confidence traces with soft temporal operators inspired by Linear Temporal Logic. A Significance-Aware Calibration step then aligns verification with human perception by retaining only perceptually significant violations before producing a timestamp- and evidence-grounded report. We conduct extensive experiments across public and complex multi-event benchmarks with the strongest video models to date, demonstrating that FVSCORE outperforms holistic and agent-based evaluators in human correlation while providing highly accurate and interpretable feedback.

cs.CV · cs.AI

新论文 · v1arXiv:2611.22670

Worldviews in Large Language Models

Edmundo Lopez-Sola, Shamil Chandaria, Ruben Laukkonen

原文摘要

Large language models (LLMs) are often described in terms of personas and this framing has become central to alignment research. In this paper, we argue that there is a deeper level of description that lies in the agent's worldviews, i.e., its beliefs about what reality is and how it works. Treating LLMs as a population of subjects, we administer two worldview surveys from human psychology to eight models. We show that the models share many key worldview positions. For example, LLMs consistently describe the world as less good, safe, enticing, and alive than humans do. On the other hand, base models have a more positive outlook, suggesting that the bleakness we found is driven by post-training. In line with research on LLM "personas", we show that system prompts eliciting different identities shift worldviews in consistent directions, and that a contemplative prompt creates a more positive outlook and improves safety. We also found that dialogue between models consistently shifts worldviews and that several models converge on the "spiritual bliss" attractor. Intriguingly, dialogue increased safe responses and the spiritual bliss attractor engendered the most aligned responses overall. These findings suggest that worldviews form a measurable and malleable layer of LLM behavior that may be crucial for robust, positive alignment.

cs.AI · cs.CY

版本更新 · v3arXiv:2607.05516

Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets

Paul K. Mandal, Pavan Reddy, Tristan Malatyński

原文摘要

Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision data that can behave as backdoor-like triggers without being maliciously inserted. We call these signals statistical adversaries. We analyse ImageNet to find patterns that are strongly linked to certain labels. We then use statistical controls to remove random correlations from our candidate signals. Finally, we demonstrate that these signals directly and predictably alter model predictions. These statistical adversaries are more targeted than generic corruptions and transfer across different model architectures. This suggests that some vulnerabilities are driven by dataset structure and distribution rather than a single model's idiosyncrasies. We conclude that ordinary datasets can contain exploitable adversarial surfaces even in the absence of poisoning, and suggest that dataset audits should treat spurious structure not only as a source of bias or interpretability failure, but also as a latent attack surface for vision models.

cs.CV · cs.AI · cs.CR · cs.LG

版本更新 · v2arXiv:2509.04007

AutoPBO: LLM-powered Optimization for Local Search PBO Solvers

Yi Chu, Jinyuan Li, Yiwen Sun, Mengchuan Zou, Shaowei Cai

原文摘要

Pseudo-Boolean Optimization (PBO) provides a powerful framework for modeling combinatorial problems through pseudo-Boolean (PB) constraints. Local search solvers have shown excellent performance in PBO solving, and their efficiency is highly dependent on their internal heuristics to guide the search. Still, their design often requires significant expert effort and manual tuning in practice. While Large Language Models (LLMs) have demonstrated potential in automating algorithm design, their application to optimizing PBO solvers remains unexplored. In this work, we introduce AutoPBO, a novel LLM-powered framework to automatically enhance PBO local search solvers. We conduct experiments on a broad range of four public benchmarks, including one real-world benchmark, a benchmark from PB competition, an integer linear programming optimization benchmark, and a crafted combinatorial benchmark, to evaluate the performance improvement achieved by AutoPBO and compare it with six state-of-the-art competitors, including two local search PBO solvers NuPBO and OraSLS, two complete PB solvers PBO-IHS and RoundingSat, and two mixed integer programming (MIP) solvers Gurobi and SCIP. AutoPBO demonstrates significant improvements over previous local search approaches, while maintaining competitive performance compared to state-of-the-art competitors. The results suggest that AutoPBO offers a promising approach to automating local search solver design.

cs.AI

新论文 · v1arXiv:2611.22661

The Between-Round Decision in Autonomous Research: An LLM Controller That Reads the Whole Trajectory

Caoxin Wang, Shengkai Gan, Xiang Hu, Lili Pan

原文摘要

Executing an idea often changes how promising it looks, so the next step in autonomous research should rest on results, not on proposals. After each round of experiments, the system must decide whether to refine the best solution or start a new direction, which solution to build from, and what goal to set. We call this the between-round decision. Existing systems wrap it in machinery such as rules, scores, search trees, and schedules; where an LLM makes it, what the LLM needs to read is left open. We ask whether an LLM can make this decision from accumulated evidence, without a search structure around it, and how much of that evidence it needs to read. We present BRED (Between-Round Evidence-based Decision), an LLM-based controller that maintains the best verified solution so far (the Champion) and a log of past rounds, and makes one decision per round. On three widely used research-agent benchmark tasks, BRED improves on the task baselines by 4.80% in MAE on ETTh1 (to 0.4172) and by 3.44 and 3.43 points of accuracy on SST-2 (to 95.07%) and CIFAR-100 (to 84.63%), ahead of the published results. When the controller does not read the accumulated evidence, the same loop gains less: with no history it reaches 0.4299 on ETTh1 and 83.71% on CIFAR-100, whereas the full controller's MAE is 2.95% lower and its accuracy 0.92 points higher. On a new task, speech-based depression detection under a leakage-free protocol, it reaches a macro-F1 of 0.6164 on seeds held out from selection, 5.5 points above its baseline and 4.0 above the strongest published system. Code is available at https://github.com/learninginvision/BRED.

cs.AI · cs.CL

新论文 · v1arXiv:2611.22658

AlignedHPO: Efficient Surrogate-Guided Loss Hyperparameter Optimization

Ivan Karpukhin, Andrey Savchenko

原文摘要

Modern deep learning losses involve multiple hyperparameters, such as weights, scales, and margins, typically tuned manually or through expensive black-box optimization despite their differentiability. We propose AlignedHPO, an efficient framework for tuning differentiable loss hyperparameters using gradient alignment and surrogate validation objectives. Our method employs Jacobian-vector products to reduce hypergradient computation time and memory, while differentiable metric surrogates guide optimization toward task-specific evaluation criteria. We address gradient magnitude ambiguity and stochastic instability through normalized alignment and gradient smoothing. Experiments with generalized Focal Loss and ArcFace demonstrate effective adaptation across long-tailed classification and open-set face recognition. AlignedHPO achieves competitive or improved performance compared to implicit differentiation, with nearly 12x faster hypergradient computation. These results highlight the potential of efficient surrogate-guided loss hyperparameter optimization.

cs.LG · cs.AI

版本更新 · v3arXiv:2606.29296

Process Advantage Signal Shaping: Advantage Construction for Process-Supervised Reinforcement Learning in LLM Reasoners

Chao Wang, Hongtao Tian, Tao Yang, Yunsheng Shi, Ting Yao, Wenbo Ding

原文摘要

Dense process supervision provides local evaluations, but leaves open how these scores should become policy advantages. We introduce PASS (Process Advantage Signal Shaping), an advantage-construction method for group-relative policy optimization (GRPO). PASS separately normalizes and fuses reward channels, constructs batch-shared credit units from variation in the fused score trace, and normalizes return-to-go by the remaining unit count. These operations connect feedback scale, credit resolution, and accumulation horizon in a single computation. We evaluate learned process reward model (PRM) feedback for mathematical reasoning and teacher-derived token feedback for multi-hop question answering (QA). Across seven mathematics benchmarks, PASS improves average pass@1 by 4.62 percentage points over outcome-only GRPO with approximately $2\%$ shorter responses. Matched comparisons with Step-GRPO and component ablations further support the choice of shared credit units and residual normalization. On multi-hop QA, PASS improves over process-signal controls across two normalizers; token-level ablations reveal an accuracy--length trade-off: token-level accumulation slightly favors pass@1, while PASS achieves higher pass@8/16 with shorter responses. The results establish the conversion from local process scores to policy advantages as a consequential design choice across distinct supervision sources.

cs.AI