Search research

Topics & fields

Large Language Model Evaluation244 papers Unified Evaluation222 papers Jailbreak Evaluations184 papers Agentic Evaluations148 papers Artificial Intelligence Evaluation133 papers Adversarial Evaluation114 papers Evaluation Benchmarks96 papers Safety Evaluation83 papers Evaluation Metrics76 papers Off-Policy Evaluation70 papers Multimodal Evaluation67 papers Unified Evaluation66 papers

24,631–24,660 of 24,674

Papers

Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability
Date pendingYudong Gao, Linghan Chen, Wenhan Wu +5Vision-Language-Action Models Fault Injection Experiments
Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning
Date pendingPeng Du, Kiran Kamble, Rakshith Vasudev +5Supervised Fine-Tuning Agentic Tool Use
tinyDSM: A Framework for Skill Modeling and Development for Resource-Constrained Millirobots
Date pendingMarkus Kobelrausch, Michael Miedler, Axel JantschIntrinsic Motivation Cognitive Science
Efficient Adaptation of LLMs for Hate Speech Detection in Low-Resource Languages: A Comparative Study on Roman Urdu
Date pendingToneema Zubair, Muhammad Junaid Asif, Faisal Kamiran +2Hate Speech Low-Resource Languages
Improving Natural-Language Combinatorial-Optimization Accuracy in Resource-Constrained Language Models via Formal Abstractions
Date pendingShrenil Shaun Sharma, Avi SharmaScheduling Llm-Based Optimization Modeling
Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling
Date pendingTajwaar Shafiq, Hunzalah Hassan Bhatti, Firoj Alam +1Zero-Shot Inference
SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields
Date pendingBaixin Li, Haiyun HeWatermarks Diffusion Language Models
Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation
Date pendingJunyu Lu, Kaiyuan Liu, Kaichun Wang +8
'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
Date pendingFawzia Zehra (Fuzzy), Kara-Isitt, Sonal Khosla +1Multilingual Safety Large Language Model Safety
MRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven Characterization
Date pendingMartyna Żur, \Lukasz Piórecki, Marek Socha +5Key Vertebral Morphometry Variables Biomarker
CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery
Date pendingMahir Shahriar Tamim, Sharjil Khan, Md. Samiul Alim +3Robust Multimodal Learning Gradient Surgery
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Date pendingJunxiang Xu, Ruisi Wang, Fanyi Pu +49Visual Reasoning
FaultLens: Learning Compact Behavioral Test Suites for Generated Operational Programs
Date pendingZeming Liu, Hang Lyu, Jingtao ZhangStress Testing Mock-Interface Synthesis
Differentiable Jitter Correction using Deep Learning-based Image Quality Metric for Phase-Contrast Micro-CT
Date pendingJunan Chen, Yiting Jia, Joscha Maier +6Tomography Microscopy
How Proper Scoring Rules Shape LLM Forecasting
Date pendingBenjamin Turtel, Paul Wilczewski, Kris Skotheim +2Scoring Load Forecasting
Toward a Cross-Lingual Romanization Ecosystem for Sinitic Languages: A Paired Mandarin-Cantonese Case Study
Date pendingZijie Zhang, Tan Lee, Yong Cao +1Phonological Understanding Multilingual Automatic Speech Recognition
AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models
Date pendingSunghwan Han, Youngtae Han, Youngmin YiFlow-Matching Vision-Language-Action Hierarchical Flow Matching
Denoising as Projection: Constrained Optimization with Gradient-Guided Diffusion
Date pendingRunyu Zhang, Jiawei Zhang, Gioele Zardini +2Reward-Guided Diffusion Image Denoising
AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP
Date pendingJoan Nwatu, Tsedeniya Solomon Amare, Longju Bai +17Natural Language Datasets Legal Natural Language Processing Benchmarks
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
Date pendingShaoan Wang, Aocheng Luo, Fei Huang +17Embodied Navigation Spatial Reasoning
Design and Implementation of a Kalman Filter-Infused Algorithm for Tilt Estimation
Date pendingYuehan Ma, Hongji DaiExtended Kalman Filter Inertial Measurement Units
OUTLETS: Output-Length Prediction from Speculative Decoding Backbones
Date pendingWeihuang Wen, Yingying Liu, Yichuan Liu +5Speculative Decoding
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
Date pendingShaowen Wang, Ge Zhang, Kairong Luo +6Transformer Layers Transformer Architectures
Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis
Date pendingSubash Khanal, Yangzhi Cui, Daniel Cher +4
SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation
Date pendingQi Liu, Qinzheng Wang, Can Li +2Microscopic Traffic Simulations Self-Evolving Agents
When Minute-Resolution Monitoring Meets Session-Level Injury Labels: Landmark-Based Discrimination in Elite Women's Football
Date pendingEvangelos Chatzidimitriou, Konstantinos TserpesSports Science Physical Activities
Almost Free State Prediction Separation
Date pendingJohn Langford, Nathan Godey, Giovanni Monea +5Next-Token Prediction
Catalogue Photography as a Cold Start: Toward Deployable Rotary Milling Tool Recognition
Date pendingAbilash Philip Madavath, Chandra Yuvesh Aubeeluck, Augustin Raju +3Computer Vision Domain Shift
VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models
Date pendingChenyu Su, Zhaolong Shen, Yuan Qian +8Pretrained Vision-Language-Action Vision-Language-Action Models
GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning
Date pendingLong Xu, Zhiqi Zhang, Mi Yan +8Indoor Scene Generation Articulated Objects

Date pending · cs.CRJ/K move · Enter open · S save

Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability

Yudong Gao, Linghan Chen, Wenhan Wu, Mia Zhou+4

Quantized Vision-Language-Action (VLA) models expose a weight-fault surface: Rowhammer-style faults can corrupt deployed INT8 bits. We present the first bit-flip attack on a VLA: a few gradient-selected flips reduce closed-loop success to

0\%

, while hundreds of random flips are harmless. Across four model variants spanning three action-head families, damaging bits concentrate in a few action-generating layers, but the empirical budget depends sharply on the head: direct regression and token policies fall in

1

5

flips, whereas the evaluated flow-matching policies require

{\sim}100

300

. Our fixed-direction manifold-escape loss cuts \pizero{}'s budget from

{\sim}1000

{\sim}100

flips, and a matched five-direction sweep shows that the attack is not specific to an all-positive direction. On a direct head, protecting

3.1\%

of weights preserves

60\%

success at

K{=}100

, and protecting

5.3\%

moves the open-loop break threshold from 3 to 100 flips. Finally, task-calibrated emulated

K{=}100

flips yield

0/20

real-robot successes, versus

14/20

clean and

16/20

global-random. Weight integrity is therefore a security boundary for embodied foundation models. Code is included as ancillary material.

Vision-Language-Action Models Fault Injection Experiments Vulnerability Detection & Repair Loss Landscape Generative Adversarial Network

Open paper Ask about it PDF