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

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 14:28 — 2026-11-16 14:28(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 02:59

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

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

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

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.14093

BODYinTRANSIT-Lab: A Multimodal Dataset for Investigating Sensory-Driven Transformations in Body Perception and Affective Experiences

Mohammad Mahdi Dehshibi, Tomás Martínez Cortés, Amar D'Adamo, Daniel de la Prida, Luis-Antonio Azpicueta-Ruíz, Laia Turmo Vidal, Marte Roel Lesur, Joaquín R. Díaz-Durán 等 14 位作者

原文摘要

Multimodal datasets that combine synchronised behavioural and physiological signals with subjective affective and body perception measures are still rare. This limits both the understanding of embodied experience and the development of computational models that infer subjective states from sensor data. We introduce BODYinTRANSIT-Lab, a multimodal dataset that addresses this gap by capturing affective, perceptual, and behavioural responses to the Footsteps Illusion. In this closed-loop paradigm, participants perform walking tasks while receiving real-time manipulated auditory feedback of their own footsteps intended to alter perceived body weight. The dataset comprises synchronised recordings from 101 participants recruited through systematic stratification by eating-disorder symptomatology and physical activity level. BODYinTRANSIT-Lab combines full-body kinematics with electromyography, electrocardiography, respiration, and electrodermal activity. Its annotations capture both immediate and post-trial experience, including within-trial perceived-weight ratings, post-trial assessments of body feelings and affective experience, 3D avatar body visualisations, and quantitative body maps. Psychological, behavioural, demographic, and social measures provide further information about factors that may influence individual responses. We provide a deep learning benchmark that uses walking kinematics to classify relative affective valence and perceived weight within subjects. On within-session, segment-level splits, the baseline model achieved mean balanced accuracies of 45.9% for affective valence and 44.5% for perceived weight. The BODYinTRANSIT-Lab dataset provides an experimentally controlled resource for cognitive neuroscience and affective computing research, with potential applications in affect-aware interactive systems, health and well-being technologies, and creative embodied experiences.

cs.HC · cs.LG

版本更新 · v2arXiv:2611.09672

ODEAction: From Predicting Chunks to Evolving Actions

Qishen Wang, Pengxiang Ding, Shifeng Bao, Mingyang Sun, Hengtao Li, Yi Gao, Baohua Yin, Yang Liu 等 17 位作者

原文摘要

Vision-language-action (VLA) models typically generate actions in chunks, dividing continuous robot execution into separately predicted action chunks, which can introduce discontinuities at chunk boundaries. We propose ODEAction, a chunk-free action generation paradigm that replaces action chunk prediction with Continuous Action Evolution. We use an ordinary differential equation (ODE) to describe the continuous evolution of actions, and define the vector field of this ODE as the Action Transition Field to characterize how actions evolve with respect to evolution time. During inference, the model takes the current action as the initial condition and numerically solves the ODE defined by the learned Action Transition Field, thereby recursively generating subsequent actions with explicit dependencies. ODEAction is implemented as a modular action head that can be integrated with different vision-language backbones. Experiments on LIBERO, EBench, RoboTwin, and real-robot tasks show that, compared with action-chunk-based baselines, ODEAction improves both task performance and trajectory quality, with particularly pronounced gains on fine manipulation tasks.

cs.RO

新论文 · v1arXiv:2611.14092

DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning

Huaijin Pi, Zehong Shen, Yong Wang, Kechun Xu, Changpeng Wang, Dingkun Wei, Xueyang Wang, Wenjia Wang 等 11 位作者

原文摘要

We study how to generate diverse, physically executable robot demonstrations for dexterous vision-language-action (VLA) learning. Existing demonstration-generation methods typically rely on costly teleoperated examples. Meanwhile, human hand--object datasets provide a reusable source, but existing transfer methods mainly reproduce given interactions. Turning these interactions into VLA training data further requires coverage of different objects and manipulation locations, together with executable arm and finger actions, and visual observations. To achieve this, we present DexSeed, a framework for low-cost generation of dexterous robot data from human hand--object interactions. Our key idea is to expand human sequences while preserving their grasps and realizing the resulting motions under arm-tracking dynamics in physics simulation. Specifically, we organize source sequences by grasp mode with shared language descriptions. InteractionMesh-based retargeting and arm trajectory augmentation adapt these sequences to the robot hand, different object geometries, and pick-and-place locations while preserving local hand--object relationships. An RL finger-control policy produces executable rollouts, while the arm tracks precomputed trajectories. Rendered observations and recorded actions from successful rollouts are paired with grasp descriptions to fine-tune a VLA. Experiments show improved contact fidelity in retargeting and more reliable whole-arm execution than the evaluated baselines. Simulation evaluation and real-world deployment further demonstrate that a VLA fine-tuned solely on the generated demonstrations can execute language-specified grasps. Project page: https://robbyant-research.github.io/DexSeed/.

cs.RO

新论文 · v1arXiv:2611.14087

Classical Tensor Codes and Quantum Tanner Codes Achieve Capacity on Erasure Channels

Henry D. Pfister, Oscar Sprumont, Gilles Zémor

原文摘要

We show that on the classical erasure channel, the tensor product of two capacity-achieving code families is itself capacity-achieving under mild conditions. We also prove that duals of tensor products of independent uniform random binary linear codes achieve erasure capacity. Using these local codes, for every erasure probability $ρ\in(0,1/2)$ and every rate gap $\varepsilon>0$, we obtain a family of binary quantum Tanner codes of rate at least $1-2ρ-\varepsilon$. For fixed $ρ$ and $\varepsilon$, these codes have bounded check weights, minimum distance growing linearly with the blocklength, and a linear-time erasure decoder whose decoding error decays exponentially with the blocklength.

cs.IT

新论文 · v1arXiv:2611.14083

Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models

Tomer Solberg

原文摘要

We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with no floating-point step, in which every rounding, normalization, softmax and sampling decision is determined by its inputs, and proves it with a constraint system whose relations provably never wrap modulo the 31-bit KoalaBear prime. The proof batches zerochecks and LogUp-GKR lookups into one sumcheck per domain, and commits to every witness tensor and weight in one multilinear commitment built from Reed-Solomon codes, BLAKE3 Merkle trees and a mixed-length BaseFold opening. The prover streams the model layer by layer on one GPU. On one NVIDIA RTX PRO 6000 Blackwell GPU, Sable proves all 64 layers of Qwen2.5-32B in 92.5 s for 4,096 tokens and 398 s for 16,384 tokens, and covers Qwen3-32B and the mixture-of-experts Qwen3-30B-A3B (4,096 tokens in 121.8 and 84.7 s). A proof costs 41 to 50 times the serving time, or 6.4 cents per 4,096-token request at public GPU prices, and 40 to 64 times less time per parameter and token than zkLLM. On WikiText-2, F_O's greedy token matches the BF16 model's at 86.3% of positions; on Qwen3, F_O is within 1.6 points of BF16 on MMLU and 1.7 points on GSM8K. A verifier with a compiled core checks a proof on one CPU core in 19 to 56 s. In the random-oracle model, the interactive proof has round-by-round soundness error 2^-103. The proof is not zero-knowledge, so the system targets open-weight models. Code: https://github.com/moonmath-ai/Sable

cs.CR · cs.AI · cs.LG

版本更新 · v5arXiv:2509.05956

Pandora's Knapsack via Simple Policies

Zohar Barak, Asnat Berlin, Ilan Reuven Cohen, Alon Eden, Omri Porat, Inbal Talgam-Cohen

原文摘要

We introduce Pandora's Knapsack: a hybrid of the classic stochastic knapsack [Dean, Goemans, and Vondr'ak, 2008] and Pandora's box [Weitzman, 1979]. As in stochastic knapsack, items have sizes drawn from known distributions, and items that fit within a knapsack contribute to the total value. As in Pandora, every item $i$ comes in a box that costs $c_i$ to open. What distinguishes our problem is that the size is revealed only after opening the box and paying the cost. A motivating application from contract design is knapsack contracts, where a principal sequentially delegates jobs with stochastic processing times to agents before a deadline, and must pay each agent to incentivize effort, even if the job ends up not completing in time. We study the power of simple decision-making policies to approximate Pandora's Knapsack, along two complexity axes: (i)~knowledge of size distributions, and (ii)~adaptivity. We show that, compared to the classic stochastic knapsack and Pandora's box, policies in our model must be significantly more complex along both axes to be approximately optimal. Conversely, we show that with full distributional information and by allowing adaptive skipping of items, a constant approximation can be recovered. Our analysis reveals an economic quantity, namely ROI (return-on-investment, defined as the jobs' minimum utility over cost), which smoothly characterizes the performance of simple policies. Across a hierarchy of increasingly adaptive policies, we establish tight adaptivity gaps all governed by ROI. To demonstrate the importance of the ROI parameter in characterizing simple policies, we revisit Pandora's box, and show that return-on-investment exactly captures the adaptivity gap in this classic problem as well.

cs.GT

版本更新 · v3arXiv:2603.16382

Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models

Deng Liu, Song Chen

原文摘要

Bit-flip corruption of quantized weights poses a serious reliability threat to Large Language Models (LLMs), as even a small number of weight faults can trigger catastrophic model degradation. We show that such failures can be strongly amplified when corrupted weights are coupled to high-sensitivity activation channels. Based on this observation, we propose Rotated Robustness (RoR), a training-free sensitivity-aware hierarchical rotation that applies matched orthogonal transformations to activations and weights, redistributing sensitive channel contributions across feature dimensions while preserving the underlying linear mapping in exact arithmetic. Across eight evaluated LLMs, RoR matches or exceeds all compared methods in the number of cumulative PBS flips sustained before PPL exceeds 100 within the 100-flip evaluation horizon. Under BER-based random bit-flip injection, no RoR failures are observed in the evaluated 1,000-trial experiments for the tested models. Under defense-aware SPoF reconstruction, RoR increases the cost of reproducing specified one-bit catastrophic failures to thousands of deployed INT8 bit changes. RoR also preserves downstream-task utility under PBS perturbations. On NVIDIA H200 at batch size 8, RoR incurs 0.097\%--0.584\% persistent storage overhead, 5.2\%--14.1\% Prefill overhead, and 0.5\%--9.8\% Decode overhead across four representative models. These results show that sensitivity-aware hierarchical rotation provides a practical approach to improving the bit-flip robustness of quantized LLM Linear weights.

cs.CR

版本更新 · v2arXiv:2605.05202

Optimizing Bit-Labeling of Voronoi Constellations

Carilyn Rumrill, David Muzzey, Connor Davis, Stephen Mackes, Dan Chew

原文摘要

We optimize the bit-to-symbol map of the $D_4$ and $E_8$ root lattices in reference to bit error rate, by implementing two searches on a performance metric, Hamming Density. The first search is a traditional gradient descent and the second is an efficient search using twisted theta functions. We hold other sources of lattice gain constant by fixing the lattice constellation, and consider basis changes that permute the integer labelings of the lattice points. After searching the possible basis matrices for $D_4$ and $E_8$, we found up to 0.09 dB of gain in $D_4$ bit error rate curves, and up to 0.36 dB of gain in $E_8$ compared to the standard bases commonly used in literature at a BER of $10^{-4}$, which is on the scale of gain from Gray coding uncoded QAMs.

cs.IT

新论文 · v1arXiv:2611.14079

From Bias to Positionality: A critical grammar for Large Language Models

Dave Murray-Rust, Elisa Giaccardi, Federico Bomba, Maria Luce Lupetti

原文摘要

Bias has become a default lens for understanding what machine learning systems do and how we should relate to them. Bias is at root a deviation from a standard; in decision making systems we can supply a standard from outside: a law, a protected attribute, a benchmark, a statistical property. However, even there, biased is often used as a shorthand, without stating what the position taken is - a silent ``relative to''. In a general use of language models, nothing supplies the standard: there is no decision to audit and no counterfactual output, so the shorthand fails. We argue that positionality -- the located, articulated, owned and contestable position from which anything is said -- is the better grammar for the question these models now force: who is speaking, from where? Against the vendors' answer of nowhere and the seductive possibility of everywhere, we argue that when a model is taken as-if speaking, it speaks from somewhere, and this means positionality can describe models, and the way they are believed beyond their warrant, even though they are not accountable speakers. A model's positionality is laminar -- laid down across corpus, tuning, system prompt, application and the live conversation. We separate three sets of factors: the positionality of a model's creators, the behaviour they intend for it, and the behaviour it enacts, and situate current work within this matrix. This lets us highlight what each stratum inherits from the one below, with ruptures and collapses where that inheritance is disavowed. We then return to where models speak from, and discuss the implications for how models are made, read and held accountable.

cs.CL · cs.AI · cs.HC

版本更新 · v2arXiv:2403.13441

Robustness Verification in Neural Networks

Adrian Wurm

原文摘要

In this paper we investigate formal verification problems for Neural Network computations. Of central importance will be various robustness and minimization problems such as: Given symbolic specifications of allowed inputs and outputs in form of Linear Programming instances, one question is whether there do exist valid inputs such that the network computes a valid output? And does this property hold for all valid inputs? Do two given networks compute the same function? Is there a smaller network computing the same function? The complexity of these questions have been investigated recently from a practical point of view and approximated by heuristic algorithms. We complement these achievements by giving a theoretical framework that enables us to interchange security and efficiency questions in neural networks and analyze their computational complexities. We show that the problems are conquerable in a semi-linear setting, meaning that for piecewise linear activation functions and when the sum- or maximum metric is used, most of them are in P or in NP at most.

cs.AI · cs.LG

新论文 · v1arXiv:2611.14076

ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision

Haozhan Shen, Liangbo He, Jun Lan, Huijia Zhu, Weiqiang Wang, Tiancheng Zhao, Jianwei Yin

原文摘要

Fine-grained visual perception requires Vision-Language Models (VLMs) to locate and interpret subtle evidence within complex scenes. Constructing supervision for this ability is challenging: questions must have correct, unambiguous answers that depend on actual fine-grained visual details rather than coarse cues or language priors. Verifying these properties makes manual annotation labor-intensive and automatic generation difficult for models that themselves struggle with fine-grained perception. Yet the same models can often recognize such details once the region is zoomed in. We exploit this global-to-zoom perception gap and introduce ZoomGain, a data construction pipeline that constructs questions about the full image from visual information gained only by zooming in. It verifies each answer on the zoomed view with multiple models, ensures that each question remains unambiguous in the full image and cannot be answered from language priors, and specifically generates high-quality distractors for multiple-choice questions. With this pipeline and human-only screening (no manual QA editing), we build ZoomGainBench, a 1,000-question bilingual benchmark on which the best of 28 VLMs achieves only 61.08. Failure analysis reveals that models favor a particular type of distractor when answering multiple-choice questions incorrectly. Beyond evaluation, training on just 9K ZoomGain samples substantially improves the visual perception capabilities of our 4B/9B models, enabling them to outperform several hundred-billion-parameter models across various perception benchmarks. The trained 9B model achieves SoTA performance on several benchmarks, such as 90.25 on HR-Bench 4K. These results establish global-to-zoom perception gaps as a practical basis for scaling fine-grained visual supervision for both evaluation and training. Our code is available at https://github.com/inclusionAI/ZoomGain.

cs.CV · cs.AI

版本更新 · v2arXiv:2511.14521

A Generative Data Framework with Reliable Supervision for Underwater Image Restoration and Enhancement

Yufeng Tian, Yifan Chen, Zhe Sun, Libang Chen, Mingyu Dou, Jijun Lu, Ye Zheng, Xuelong Li

原文摘要

Learning-based underwater image restoration and enhancement rely heavily on high-quality paired training data. However, obtaining clear reference images for real underwater scenes remains challenging. Existing datasets often use the outputs of enhancement algorithms as references, which may introduce uncertainty into supervision targets. To address this issue, we propose a generative data framework that preserves clear source images as restoration references and synthesizes corresponding underwater inputs through unpaired image-to-image translation. Using representative underwater appearances to guide the translation, we construct UWNature from natural photographs. We systematically examine the reliability of the generated supervision through its agreement with real underwater appearances, structural consistency, and depth-related degradation characteristics. Experiments across 6 restoration architectures and 3 test sets evaluate its effectiveness through objective metrics, human perceptual assessment, and the correspondence between synthetic degradation and learned restoration behavior. The results demonstrate competitive restoration performance and favorable perceptual quality on real underwater images. Further analysis reveals that greater spatial plausibility of synthetic degradation does not necessarily improve restoration performance, highlighting the importance of evaluating both the intrinsic properties of synthetic data and their effectiveness for model learning. These findings support a scalable framework for constructing and evaluating reliable paired supervision for underwater image restoration and enhancement. The generated datasets are available at: https://github.com/tianyufengcn/SynUIEDatasets.

cs.CV

新论文 · v1arXiv:2611.14074

Obscured Wildfire Flame Detection by Spatio-temporal Analysis of Smoke Patterns Using Frame-wise Transformers

Uma Meleti, Abolfazl Razi, Fatemeh Afghah

原文摘要

In this paper, we propose a new paradigm in wildfire management for detecting both visible and obscured fire using Deep Learning (DL). The essence of our method is the joint spatial and temporal analysis of RGB videos, embracing the fact that temporal patterns of smoke motions in consecutive video frames can indicate obscured fire flames. This perspective contrasts the traditional approach of independently analyzing images and individual video frames. To this end, we propose a frame-wise transformer architecture that applies an attention mechanism between the consecutive frames while preserving spatial information within frames as opposed to regular attention mechanisms like the non-local block, which combines spatial and temporal information into a single vector. We also optimize the temporal pattern lengths under different spatial resolutions to achieve the highest performance while reducing the computational cost. To investigate the applicability of our method in aerial image processing, we applied it to a curated version of the FLAME2 dataset that includes dual-mode RGB/IR videos. The IR video feed is used to extract ground truth, while the model is trained only on RGB videos to maintain applicability to lowcost commercial drones (which are equipped only with regular cameras) and facilitate processing existing RGB-only datasets. Our proposed method achieves a Segmentation Foreground Dice score of 92.61%, an Object Detection Precision and Recall rate of 93.21% and 91.73%, and clip-level classification accuracy of 98.02%, respectively. We also investigated the efficacy and generalizability of our method through ablation study

cs.CV · cs.AI

版本更新 · v3arXiv:2608.02157

RamanPFN: A physics-guided spectral foundation framework for in-context learning across diverse Raman applications

Xingyu Pan, Huan Wang, Jinjia Guo, Zhenlin Zhao, Siming Dong, Jixi Lu

原文摘要

Raman spectroscopy enables label-free molecular characterization across materials science, analytical chemistry, biomedicine, and industrial process monitoring. However, machine learning for high-dimensional spectroscopy remains constrained by limited labeled data and a mismatch between the physical organization of spectra and feature-agnostic models. Tabular foundation models such as TabPFN predict in context without parameter updates, but on wide spectra feature subsampling preserves channel coverage while losing joint visibility: in the five widest tasks, every channel was covered, yet only 4.4% of random channel pairs co-occurred in any forward pass. We present RamanPFN, a general-purpose spectral foundation framework for unified in-context inference through physics-guided spectral learning, which encodes the additive mixing of constituent spectra and the locality of vibrational bands. Global Compositional Unmixing decomposes distributed, multi-band mixture signatures into shared non-negative bases to couple covarying peaks across the full spectrum, while Local Vibrational Subspace Encoding extracts orthogonal modes within contiguous spectral neighborhoods to preserve peak morphology, intensity fluctuations, and peak shifts. Posterior marginalization over admissible unmixings unifies both scales into in-context prediction without updating the model. Across 74 public Raman datasets exceeding 330,000 spectra, RamanPFN outperformed 26 methods spanning chemometrics, spectral neural networks, deep tabular learners, and tabular foundation models on 129 regression targets, reducing backbone RMSE by 13.2%. We demonstrate across TabPFN-3, TabICLv2, and Kumo-Tabular that this advantage generalizes to both regression and classification tasks, reducing regression error by 12.3%-25.7% and multiclass log loss by 42.4%-63.5% to enable data-efficient quantitative analysis and sample identification.

cs.LG · cs.AI

版本更新 · v2arXiv:2308.14527

MDS Array Codes With Small Sub-packetization Levels and Small Repair Degrees

Jie Li, Yi Liu, Xiaohu Tang, Yunghsiang S. Han, Bo Bai, Gong Zhang

原文摘要

High-rate minimum storage regenerating (MSR) codes are known to require a large sub-packetization level, which can make meta-data management difficult and hinder implementation in practical systems. A few maximum distance separable (MDS) array code constructions have been proposed to attain a much smaller sub-packetization level by sacrificing a bit of repair bandwidth. However, to the best of our knowledge, only one construction by Guruswami et al. can support the repair of a failed node without contacting all the surviving nodes. This construction is certainly of theoretical interest but not yet practical due to its requirement for very large code parameters. In this paper, we propose a generic transformation that can convert any $(\overline{n}, \overline{k})$ MSR code with a repair degree of $\overline{d}<\overline{n}-1$ into another $(n=s\overline{n},k)$ MDS array code that supports $d<n-1$ with a small sub-packetization level and $(1+ε)$-optimal repair bandwidth (i.e., $1+ε$ times the optimal value) under a specific condition. We obtain three MDS array codes with small sub-packetization levels and $(1+ε)$-optimal repair bandwidth by applying this transformation to three known MSR codes. All the new MDS array codes have a small repair degree of $d<n-1$ and work for both small and large code parameters.

cs.IT

新论文 · v1arXiv:2611.14068

What a CAGE 4 Score Measures: An Audit of a Learned Cyber-Defense Benchmark, Its Reference Defenders, and the Tables Built on Them

James Rice, Ji Hwan Park, Andres Kwasinski

原文摘要

CAGE Challenge 4 is the benchmark on which learned multi-agent cyber defenders are compared. We reproduce its two reference defenders, KEEP and H-MARL Expert, in a pinned container and show that three things read from it measure less than they are taken to measure. First, the simulator silently discards any action asserted for an agent whose previous action is still running, and charges one point for a discarded Restore as for one that runs. The documented observation does not expose the busy flag. Both reference defenders read it in their own wrappers, and switching that check off at evaluation costs KEEP's released policy 99.58 points per episode and H-MARL's 145.98, in both cases the charge for Restores sent to busy agents, with H-MARL's executed actions unchanged step for step. On a supervisory harness, holding interventions until the agent is idle is worth 25.3 and 27.6 points per episode at the published setting. In training, the check decides how a busy step enters the trajectory. Trained without it, KEEP leads at a hundred updates in all four paired seeds and trails from two hundred on in all four. Continued to two thousand updates on three seeds, the repaired recipe ends inside the released interval on one seed and short on two, by 27 and 125 points, a spread across training seeds far wider than the released reproduction interval. Second, the evaluation seeds the environment but not the policy, so a reported mean is one draw, and 88.9% of per-episode outcome variance is the policy's own sampling draw. Third, recovery precision depends on the truth it is scored against. Across five published comparison tables, none states the artifact, sampling, criterion and adversary that would make its numbers comparable. We release the instrument, our patches to both defenders, the traces and checkpoints behind every number, and a five-item disclosure checklist.

cs.CR · cs.LG

版本更新 · v6arXiv:2409.18745

A study on the effects of mixed explicit and implicit communications in human-artificial-agent interactions

Ana Christina Almada Campos, Bruno Vilhena Adorno

原文摘要

Communication between humans and artificial agents is essential for their interaction. This is often inspired by human communication, which uses gestures, facial expressions, gaze direction, and other explicit and implicit means. This work presents interaction experiments where humans and artificial agents interact through explicit and implicit communication to evaluate the effect of mixed explicit-implicit communication against purely explicit communication and the impact of the task difficulty in this evaluation. Results obtained using Bayesian parameter estimation show that the task execution time did not significantly change when mixed explicit and implicit communications were used in neither of our experiments, which varied in the type of artificial agent (virtual agent and humanoid robot) used and task difficulty. The number of errors was affected by the communication only when the human was executing a more difficult task, and an impact on the perceived efficiency of the interaction was only observed in the interaction with the robot, for both easy and difficult tasks. In contrast, acceptance, sociability, and transparency of the artificial agent increased when using mixed communication modalities in both our experiments and task difficulty levels. This suggests that task-related measures, such as time, number of errors, and perceived efficiency of the interaction, as well as the impact of the communication on them, are more sensitive to the type of task and the difficulty level, whereas the combination of explicit and implicit communications more consistently improves human perceptions about artificial agents.

cs.RO

版本更新 · v2arXiv:2610.02274

Awomo-SimDataEngine: Agentic Simulation-ReadyWorld Generation

Awomo-PhysicalRSI Team, Danjiao Ma, Enhui Ma, Haohan Liu, Heng Jia, Hui Shan, Jianhua Xu, Jiahuan Zhang 等 24 位作者

原文摘要

Generating useful robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyvalid, and tasks must admit repeatable execution. We present\textbf{Awomo-SimDataEngine}, an agentic system that connects asset and scenegeneration to robot demonstration synthesis. Shared asset services providerigid and articulated objects, including structure-grounded part and jointgeneration with ISArt. Scene generation supports two complementary routes:Unravel reconstructs editable scenes from images, while SimForge buildssingle-room and multi-room environments from text. A graph-native harnesscoordinates construction, validation, andbounded repair, routing failures to the responsible module while retainingunaffected scene state. PolicyForge binds validated worlds to tasks and robotembodiments to produce replayable demonstrations. Evaluations cover assetgeometry, scene quality, and downstream policy learning. On MuJoCo-basedLIBERO-Plus, co-training with Isaac Sim demonstrations improves the overallsuccess rate of a World-Action Model (WAM) from $77.17\%$ to $89.43\%$. Goal and spatialsuccess improve by $31.66$ and $6.25$ percentage points, respectively . These results support the utility of the generated data for cross-simulatorpolicy training, with more limited gains on long-horizon tasks.

cs.RO

新论文 · v1arXiv:2611.14066

Generalizing Causal Decision-Making: Markov Equivalence, Transportability and Counterfactuals

Min Woo Park, Sanghack Lee

原文摘要

Structural causal bandits use causal knowledge to guide exploration when reward mechanisms are unknown. This paper extends the approach to partially known causal structure, information from other environments, and realizable counterfactual actions. First, we develop graphical criteria for minimal intervention sets under Markov equivalence and characterize possibly-optimal minimal intervention sets for maximal ancestral graphs. A search algorithm finds sets that are possibly optimal in at least one graph represented by a partial ancestral graph. Second, we derive target reward bounds from source distributions through partial transportability, accounting for non-manipulable variables. Dominance relations provide further bounds for action pruning and restricted exploration, with a regret guarantee under valid prior bounds. Third, we formulate counterfactual structural causal bandits over actions supported by specified experimental capabilities. Graphical characterizations of minimality and possible optimality yield algorithms that remove equivalent or dominated choices while preserving an optimal action. Experiments with specified structural causal models examine how these reductions and transferred bounds affect learning. Together, these results clarify how causal knowledge and experimental capabilities determine which actions merit exploration and guide learning within the retained action space.

cs.LG

版本更新 · v3arXiv:2604.18556

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Alireza Dadgarnia, Soroush Tabesh, Mahdi Nikdan, Michael Helcig, Eldar Kurtic, Maximilian Kleinegger, Dan Alistarh

原文摘要

Quantization has become a standard tool for efficient LLM deployment, especially for local inference, where models are now routinely served at 2-3 bits per parameter. The state of the art is currently split into simple scalar quantization techniques, such as GPTQ or AWQ, which are widely deployed but plateau in accuracy at 3-4 bits per parameter (bpp), and "second-generation" vector- or trellis-quantized methods, such as QTIP, GPTVQ and AQLM, which push the accuracy frontier but are notoriously hard to implement and to scale. In this paper, we ask whether this gap is fundamental, or whether a carefully optimized $\textit{scalar}$ quantizer can recover most of it. We answer in the affirmative, by introducing GSQ (Gumbel-Softmax Quantization), a post-training scalar quantization method which jointly learns the per-coordinate grid assignments and the per-group scales using a Gumbel-Softmax relaxation of the discrete grid. GSQ matches the cardinality of the relaxation to the small number of levels available in the target bit-width regime (e.g., 3-8 levels for ternary and 3 bpp, respectively), making optimization tractable. Practically, on the standard Llama-3.1-8B/70B-Instruct models, GSQ closes most of the gap between scalar quantization and the QTIP frontier at 2 and 3 bits, while using a symmetric scalar grid with group-wise quantization, and thus remains compatible with existing scalar inference kernels. We further show that the same discrete-assignment optimization can be applied to practical GGUF K-Quant checkpoints: starting from publicly released GGUF models, GSQ improves accuracy while projecting the result back into the same deployment format. Finally, GSQ scales to trillion-scale Mixture-of-Experts models such as Kimi-K2.5, where vector-quantized methods are difficult to apply. The source code is publicly available at https://github.com/IST-DASLab/GSQ.

cs.CL · cs.LG

版本更新 · v2arXiv:2604.18585

RECURSUM: Automated Code Generation for Recurrence Relations Exceeds Expert Optimization via LayeredCodegen

Rubén Darío Guerrero

原文摘要

Automated code generation can systematically exceed expert hand-optimization for recurrence relations--computational primitives ubiquitous in orthogonal polynomials, special functions, numerical integration, and molecular integral evaluation. We present RECURSUM, a Python DSL generating optimized C++ for arbitrary recurrence relations via three backends--template metaprogramming, a novel LayeredCodegen backend, and runtime loop-based evaluation--specifying recurrences in 10--30 lines of Python that generate 650+ lines of production C++. LayeredCodegen achieves 9.8$\times$ speedup over expert hand-written code and 1.9$\times$ over template metaprogramming for McMurchie-Davidson Hermite coefficients, through zero-copy output parameters, guaranteed inlining, and exact-sized stack buffers. A DAG-topological generalization of this architecture--built to express the four-center electron-repulsion integral that LayeredCodegen's tower model cannot--beats libint2, a mature, two-decade-refined production library, on 12 of 14 Cartesian integral classes, with $\sim$2$\times$ faster contracted Coulomb/exchange (J/K) matrix construction (alkanes and 3-D DNA fragments alike) and 1.1--2.7$\times$ faster one-electron integrals, completing the full Hartree-Fock integral set from one DAG framework. We validate 24 recurrence types spanning pure mathematics, numerical analysis, and quantum chemistry; production benchmarks confirm these speedups propagate to complete algorithms, matching expert baselines within 3.3\%. By eliminating the dual expertise barrier of domain knowledge and C++ metaprogramming, RECURSUM establishes systematic code generation--not hand-tuning--as the performance ceiling for recurrence algorithms.

cs.PL

新论文 · v1arXiv:2611.14064

DEIA: Evidence-Grounded Crash Repair with Change-Aware Test Design for HarmonyOS ArkTS

Xuhui Lu, Zhihao Liu, Xiaoke Fang, Yuhuan Fan, Yanzhe Tang, Xiaohui Wan, Xiaoyu Wu, Zheng Zheng

原文摘要

Mobile crash repair requires more than identifying a source edit. Developers must establish how the edit relates to the reported failure and whether the modified application can be built, launched, and exercised without disrupting valid behavior. In HarmonyOS applications, this assessment also depends on platform-specific packaging and runtime execution. To address this need, we present DEIA, an evidence-grounded workflow for HarmonyOS crash repair. DEIA constructs a bounded source-evidence package, uses a large language model to propose content-anchored edits, and relies on a deterministic writer to materialize and check the patch. It derives fail-to-pass (F2P) obligations from the reported fault and pass-to-pass (P2P) obligations from the potential impact of the patch. A stage-level ledger links the patch, test obligations, runtime observations, and candidate-generation cost. We evaluate DEIA on 30 repair tasks from 24 HarmonyOS applications and compare it with an OpenHands-based workflow on 29 matched tasks. DEIA's first-added-line location exactly matches the curated reference in 25/29 tasks (86.2%), compared with 19/29 (65.5%) for OpenHands, a difference of 20.7 percentage points. DEIA also uses 81.5% fewer tokens, makes 60.8% fewer model calls, and takes 34.9% less candidate-generation time on average. Only two of the 58 behavior-specific P2P obligations were executed, both for one repair pattern; comprehensive behavior preservation therefore remains unestablished.

cs.SE

新论文 · v1arXiv:2611.14062

A human-in-the-loop Control Paradigm for Construction Robotics: From VR-Guided Teleoperation to Semi-Autonomous Dual-Arm Operation

Jinhua Chen, Xiaoji Xu, Zhongyuan Liao, Huang Zhenmin, Zhang Ye, Changying Xiang

原文摘要

Construction tasks in hazardous and unstructured environments require both human adaptability and robotic precision, yet existing approaches often treat teleoperation and autonomy as separate control modes. This paper presents a human-in-the-loop control paradigm that enables structured transitions among VR-guided teleoperation, semi-autonomous shared control, and rule-based autonomous execution for contact-rich dual-arm construction tasks. The proposed system combines immersive VR guidance, a manually defined library of reusable skill primitives, and a shared-autonomy framework with explicit human-robot role allocation and command-priority rules. This integration allows operators to retain supervisory and corrective authority while delegating repetitive and precision-critical actions to the robot. The paradigm is validated on a dual-arm platform through representative facade-installation tasks. Results show that autonomous execution provides the best performance under well-calibrated nominal conditions, whereas semi-autonomous control improves resilience when environmental disturbances exceed the predefined autonomous pipeline's correction capability. Semi-autonomous control also substantially reduces subjective operator workload compared with full teleoperation. These findings demonstrate that effective construction-robot control should adapt human involvement to task and environmental uncertainty, using autonomy for repeatable operations and shared control for disturbance recovery.

cs.RO

新论文 · v1arXiv:2611.14061

Isolation Is Not Confidentiality: Security Boundaries of Geometric Access Control in RAG

Steve Nouyep, Maxime Puys, Sébastien Salva

原文摘要

Retrieval-Augmented Generation (RAG) systems increasingly rely on vector databases containing documents governed by different access-control policies. Recent search-preserving geometric approaches enforce such access control by structuring the embedding space so that transformed embeddings, which we call protected representations, remain retrievable without exposing information across policy boundaries. We provide a unified security analysis of this paradigm, covering policy isolation, representation confidentiality, query forgery resistance, and policy-membership hiding. We consider both a curious cloud service provider observing the protected representations stored in the vector database and a curious user holding aligned pairs of original embeddings and protected representations. Evaluating the available implementations of the works proposing these geometric transformation mechanisms across three encoders, we find that geometric transformations preserve retrieval utility and provide strong policy isolation, but do not provide the other security properties. A curious user can recover the original embeddings from a few hundred pairs and forge policy-compatible queries at a higher cost that grows with encoder dimension for secret per-policy transformations. Moreover, policy-dependent geometry can leak policy membership even when unauthorized retrieval is prevented. These results show that policy isolation, confidentiality, forgery resistance, and membership hiding are distinct security objectives.

cs.CR

版本更新 · v6arXiv:2510.05107

Structured Cognitive Loop for Behavioral Intelligence in Large Language Model Agents (Extended Revision: From Behavioral Architecture to Epistemic Accountability)

Myung Ho Kim

原文摘要

The central challenge for AI agents is not performance but accountability. An agent that produces correct outputs through an opaque process offers no basis for verifying why a decision was permitted, attributing errors to identifiable causes, or delegating authority with justified confidence. We introduce the Structured Cognitive Loop (SCL), an architecture that separates cognition, control, action, and memory: the language model proposes, a lightweight controller mediates every proposal before action, and memory is kept externally as a structured store of verified facts. Against ReAct and common LangChain agents on three tasks under matched models, tools, and decoding, SCL achieves 86.3% task success versus 70.5-76.8% across 360 episodes, with higher goal fidelity, fewer redundant calls, more reliable reuse of intermediate states, and fewer unsupported assertions; ablations show that control and external memory contribute independently. We then situate SCL within a broader accountability architecture comprising context-aware human-in-the-loop control, Pool-Gated Retrieval, and the Horizon-Warrant-Commitment framework, and outline the current direction of development, in which instructions are compiled into programs validated before execution so that execution authority derives from a verified program rather than per-cycle model interpretation. For the kind of accountability it pursues, SCL adopts neither multi-agent consensus as a proxy for truth nor the imitation of human cognition as a design goal: it institutionalizes cognition rather than imitating it.

cs.AI

新论文 · v1arXiv:2611.14060

Where Do Vision-Language Models Get Left and Right? Position-Code Counterfactuals in Qwen2.5-VL, Qwen3-VL and InternVL3

Enhao Cui, Junzhi Yang, Yaoshun Lin, Yuhan Feng, Zijian Chen

原文摘要

A vision-language model may take left-right direction from the orientation of image content within patches, its vision transformer's (ViT) position code, or token positions and order in its language model (LLM). Ablations show the ViT code is necessary; we test sufficiency by mirroring only a position code. In Qwen2.5-VL-7B, Qwen3-VL-4B and InternVL3-2B, mirroring ViT width positions reproduces the flipped-image answer on 84.3-93.2% of CV-Bench left-right questions (Qwen2.5-VL-3B: 87.5%, partly a left fallback). With two options, this also counts disruption; a half-grid shift flips most answers too. With the ViT code intact, LLM-side id and token-order mirrors change few left-right answers in all three series (a weak id test in Qwen2.5-VL). In Qwen2.5-VL-7B the effect sits in the global-attention ViT blocks, mostly the last. On What'sUp, flipping content and token order, not the position code, keeps more on/under than left-right answers at the flipped-image answer. Post hoc analyses qualify these results. On CV-Bench items with located objects, random permutations flip 18.9-31.0 points more answers when reversing the objects' order than when keeping it. On What'sUp, in Qwen2.5-VL and Qwen3-VL, the share of the left-right changes made by random permutations that land on the mirror relation is mostly below chance. Counted as returns to the original answer, the What'sUp contrast of support with left-right relations is clear only in InternVL3-2B. Most remaining errors give the same relation whichever object is asked about, suggesting that repair may target relation binding, object localization or use of the reference object.

cs.CV · cs.LG

新论文 · v1arXiv:2611.14058

CURRENT: A Recurrent Neural Network for Concurrent Spatial and Temporal Super-Resolution of 4D Flow MRI

Luuk Jacobs, Pietro Dirix, Sebastian Kozerke

原文摘要

Objective: To improve the spatial and temporal resolution of aortic 4D flow MRI through a unified deep learning framework for post-acquisition super-resolution (SR) of reconstructed velocity vector fields. Methods: We propose CURRENT, a recurrent neural network that performs spatial and temporal SR with a single network architecture. Supervised training was conducted using paired low- and high-resolution datasets generated by embedding computational fluid dynamics simulations of aortic flow into in vivo thoracic MRI backgrounds, followed by controlled spatial and temporal downsampling. CURRENT was evaluated for two-fold spatial and temporal SR against 4DFlowNet and for two-fold spatiotemporal SR against sequential spatial and temporal SR pipelines based on 4DFlowNet. Image-based and k-space-based quantitative metrics were considered and conventional interpolation were used as baselines. In addition, the impact of CURRENT's spatiotemporal SR on physics-informed relative pressure estimation was assessed. Finally, the ability of CURRENT to generalize from synthetic training data to in vivo acquisitions was investigated. Results: CURRENT achieved superior spatial SR performance and comparable temporal SR performance to dedicated 4DFlowNet models while providing a unified solution for both tasks. Simultaneous spatiotemporal SR using CURRENT yielded more accurate relative pressure estimates than either spatial or temporal SR alone and outperformed sequential 4DFlowNet-based spatial and temporal SR approaches. Furthermore, the proposed model demonstrated promising generalization to in vivo 4D flow MRI data despite being trained exclusively on synthetic datasets. Conclusion: CURRENT provides a unified framework for spatial and temporal SR of 4D flow MRI. The proposed approach has the potential to enhance physics-based analysis and broaden the applicability of accelerated 4D flow MRI.

cs.CV · physics.med-ph

新论文 · v1arXiv:2611.14059

HandsOnAid: Building and Evaluating an Offline First-Aid Assistant for Emergency Response Scenarios

Rezwan Islam Salvi, Saiyma Sittul Muna, Mushfiqur Rahman Mushfique

原文摘要

Emergencies can occur where there is no phone signal and no ambulance nearby. A small language model on a phone can be helpful in such situations, but its advice needs to be safe and accurate. We built HandsOnAid, a 4-bit Gemma 2B model fine-tuned with QLoRA on FirstAidQA dataset, a corpus of 5,550 first-aid question-answer pairs. We compared seven configurations, including the base, 4-bit and 8-bit fine-tuned models, and versions with a length floor, safety gate, or retrieval. We used a 41-pair question-answer bank with medically reviewed references that followed ANZCOR guidelines, and a strict 0-5 score rubric, with twelve safety overrides. Four frontier LLM judges (GPT-5.6 Sol, Claude Opus 5, DeepSeek V4 Pro, GLM-5.3) blindly scored every answer, with 45 hidden controls used to check judge reliability. Fine-tuning improved the mean score by +1.08 over the base model to 2.34. The best configuration scored 2.51 out of 5 which was the fine-tuned 4-bit model with retrieval. A medical professional also conducted a blind evaluation of 40 answers across the base, the 4-bit fine-tuned, and the retrieval configurations, and the scores were similar to the LLM judges' average scores. A keyword audit found limited coverage of several details of ANZCOR guidelines in the training corpus, that are required by the rubric, which suggests that missing information in the training data could be a cause of the low scores. On a smartphone device (Pixel 7 Pro) with six CPU threads and no network connection, the 4-bit fine-tuned model produced its first displayable text in 6.86 seconds and a complete answer in 14.88 seconds on average over ten questions.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.14051

Can KV Cache Be Reused Across Model Updates? A DeepSeek-V4-Flash Case Study

Zhikun Tao, Fangyong Jin, Junping Zhao

原文摘要

Reusing key--value (KV) caches across language model updates could avoid repeated computation of shared context, but changes in model weights raise a fundamental question about what these caches preserve. We investigate direct cache reuse across four model updates, with a detailed study of DeepSeek-V4-Flash to Flash-0731. Our central finding is that caches can retain useful task information without faithfully reproducing the updated model's behavior. Retrieval accuracy varies substantially across updates, ranging from near-native performance to large losses. With source caches already available, reuse achieves median time-to-first-token speedups of $2.10$--$5.08\times$ on three longer-prefix QA benchmarks. To characterize the behavioral differences behind these outcomes, we introduce Functional Cache Divergence, which compares next-token distributions under reused and native caches. Direct KV cache reuse better preserves native model behavior in natural-text continuation, whereas compatibility degrades with increasing prefix length in single-token retrieval tasks. Answer-margin analyses help explain how correct retrieval decisions survive substantial internal state changes. Yet even agreement on the first generated token does not ensure agreement in answer content or stopping behavior. These findings establish task utility and fidelity to native inference as distinct criteria for evaluating cross-version KV cache reuse.

cs.DC · cs.AI

新论文 · v1arXiv:2611.14050

Ontology-Guided Knowledge Graph Construction and Robust Evidence Retrieval for Indian Knowledge Systems

Anand Kaniyaar Sriranga Prasad, Avinash Holenarasipur Nagendra, Mohan Raghavan

原文摘要

Retrieving evidence from Indian Knowledge Systems is complicated by transliteration variants, ambiguous names, and relations distributed across passages. We present an ontology-guided knowledge graph (KG) pipeline that links typed entities and relations extracted with Qwen3-32B to original textual evidence. Retrieval combines sense-aware grounding, bounded graph traversal, lexical anchors, relationship-vector search, and passage reranking. We evaluate KG alone, single-vector retrieval (SV), and KG unions with SV and Entity Notes on 320 questions from Dhara Bench, matching the per-question candidate count across internal systems under BGE and Qwen rerankers. Standalone KG has the highest Precision@5 under both rerankers and the highest MRR@20 in Counting, Composite, and Multi-hop among the evaluated internal configurations. With Qwen, KG achieves Multi-hop MRR@20 of 0.8722, compared with 0.7622 for the fully reranked KG + SV union. The KG + SV + Entity Notes union instead provides the highest overall Recall@20 (0.5134), compared with 0.4347 for KG. On the 15 Multi-hop questions, Qwen KG achieves complete-evidence MRR@20 of 0.4651 versus 0.3372 for SV, while both full unions complete ten questions within twenty results compared with nine for KG. Gemini 3.7 Flash, evaluated through manually reviewed source mappings, re mains stronger on overall MRR and nDCG, while internal systems have category-specific advantages. All comparisons are descriptive. A separate deployment timing study measures mean retrieval times of 20.374 s for KG and 0.646 s for SV. The findings support selecting KG or its unions according to the required balance of early relevance, evidence completeness, and retrieval cost.

cs.IR