惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

V
Vulnerabilities – Threatpost
大猫的无限游戏
大猫的无限游戏
M
MIT News - Artificial intelligence
IT之家
IT之家
B
Blog
博
博客园 - 【当耐特】
H
Hackread – Cybersecurity News, Data Breaches, AI and More
AI
AI
S
SegmentFault 最新的问题
N
News | PayPal Newsroom
人人都是产品经理
人人都是产品经理
I
InfoQ
GbyAI
GbyAI
WordPress大学
WordPress大学
Hugging Face - Blog
Hugging Face - Blog
D
DataBreaches.Net
Google DeepMind News
Google DeepMind News
L
LINUX DO - 最新话题
爱范儿
爱范儿
博
博客园 - 叶小钗
雷峰网
雷峰网
腾
腾讯CDC
Recent Announcements
Recent Announcements
F
Fortinet All Blogs
U
Unit 42
C
CERT Recently Published Vulnerability Notes
S
Security Archives - TechRepublic
Cyberwarzone
Cyberwarzone
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
H
Heimdal Security Blog
A
Arctic Wolf
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
Google DeepMind News
Google DeepMind News
www.infosecurity-magazine.com
www.infosecurity-magazine.com
Google Online Security Blog
Google Online Security Blog
T
The Blog of Author Tim Ferriss
T
Tailwind CSS Blog
美
美团技术团队
N
Netflix TechBlog - Medium
Last Week in AI
Last Week in AI
T
The Exploit Database - CXSecurity.com
Scott Helme
Scott Helme
S
Security @ Cisco Blogs
Apple Machine Learning Research
Apple Machine Learning Research
Y
Y Combinator Blog
小众软件
小众软件
Jina AI
Jina AI
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC

cs updates on arXiv.org

A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development Query-Adaptive Semantic Chunking for Retrieval-Augmented Generation: A Dynamic Strategy with Contextual Window Expansion Knowledge Distillation for Low-Resource Open-source Text-to-SQL Model RAS: Reflection-Augmented Scaling with In-Context Learning for Executable Cypher Query Generation Learnability-Informed Fine-Tuning of Diffusion Language Models Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance A Reproducible Universal Dependencies-Style Pipeline for Katharevousa Greek Parliamentary Text Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management A Comparative Evaluation of Structural Topic Models and BERTopic for Short, Open-Ended Survey Responses When Symptoms Are Not Enough: Evidence-Weighting Patterns in Large Language Model Psychiatric Screening Same Model, Different Weakness: How Language and Modality Reshape the Jailbreak Attack Surface in Frontier MLLMs Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving Self-Improving In-Context Learning Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement When Is Next-Token Prediction Useful? Marginalization, Ergodicity, Mixture Identifiability, Local Sufficiency, RAG, Tools, and Programming AraHopeCorpus: Annotation Guidelines and Dataset for Hope Speech in Arabic Social Media Crisis Discourse ClimateChat-300K: A Multi-Modal Facebook Dataset for Understanding Diverse Perspectives in Climate Communication Emotion Recognition in Sign Language Conversation GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation Cultural Adaptation in Large Language Models for Political Discourse From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding EquiSumm : A Gender Bias-Aware Framework for Inclusive Tweet Summarization Improved Vision-to-Chart Buoy Association with Learned World-to-Image Projection Articulatory strategy as a source of variation in acoustic vowel dynamics GazeBehavior Annotation Toolkit (GBAT): AI-powered toolkit for automatic annotation of egocentric eye-tracking and video data of child-caregiver interaction Naturalistic measure of social norms alignment CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration Scene Reconstruction as Mapping Priors for 3D Detection ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning Asking For An Old Friend: Diagnosing and Mitigating Temporal Failure Modes in LLM-based Statutory Question Answering Millimeter-wave Imaging for Anthropometric Body Measurement Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts Benchmarking Google Embeddings 2 against Open-Source Models for Multilingual Dense Retrieval and RAG Systems RoboSurg-VQA: A Multimodal Benchmark for Surgical Segmentation-Aware Visual Question Answering How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models Inconsistency-aware Multimodal Schrödinger Bridge for Deepfake Localization OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images Metadata Predictability Is Not Evidence Dependence: An Intervention-Based Audit for Weak-Label Benchmarks Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment Agentic Proving for Program Verification MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents Solving the Aircraft Disassembly Scheduling Problem Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents CP or DP? Why Not Both: A Case Study in the Partial Shop Scheduling Problem EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals Human-in-the-Loop Multi-Agent Ventilator Decision Support with Contextual Bandit Preference Learning Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning DART: Semantic Recoverability for Structured Tool Agents Ontological Knowledge Blocks: Executable Compliance and Profile-Based Validation for Trustworthy AI Systems Parallel Context Compaction for Long-Horizon LLM Agent Serving Design and Report Benchmarks for Knowledge Work GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models Foundation Protocol: A Coordination Layer for Agentic Society AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery Redrawing the AI Map: A Theory of Accountability Boundaries in Agentic Ecosystems Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Tracking CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems A Fine-Tuned BERT Classifier for Personal-Letter Titles in Late-Ming and Early-Qing Collected Works PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering Model Collapse as Cultural Evolution DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methods The TIME Machine: On The Power of Motion for Efficient Perception Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography Brain-LLM Alignment Tracks Training Data, Not Typology The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems A Proactive Multi-Agent Dialogue Framework for Assessing Social Language Disorder Traits in Autism Memorization Dynamics of Fill-in-the-Middle Pretraining Graph Alignment Topology as an Inductive Bias for Grounding Detection EVE-Agent: Evidence-Verifiable Self-Evolving Agents Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision? Mediative Fuzzy Logic: From Type-1 Foundations to Type-2, Type-3 and Quantum Extensions ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems How Far Will They Go? Red-Teaming Online Influence with Large Language Models SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research RMA: an Agentic System for Research-Level Mathematical Problems NeuroNL2LTL: A Neurosymbolic Framework for Natural Language Translation of Linear Temporal Logic BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems Evaluating Large Language Models in a Complex Hidden Role Game An AI-Driven Framework for Energy-Efficient Environmental Monitoring in Smart Cities Using Edge Intelligence
Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing
[Submitted on 12 Jun 2026] · 2026-06-15 · via cs updates on arXiv.org

View PDF HTML (experimental)

Abstract:Diffusion-based Vision-Language-Action (VLA) policies enable strong generalization in robotic manipulation, but remain sensitive to spurious visual correlations and noisy action generation, leading to brittle behavior under perturbations. We introduce Selected Diffusion Noise (SDN), a simple, training-free test-time method that improves both robustness and success rate by leveraging the diffusion noise space as a controllable degree of freedom. SDN dynamically samples noise vectors that are maximally separated from a reference set to mitigate reliance on spurious cues, while selecting candidates that yield more coherent action trajectories. This dual objective encourages stable behavior even under object-masked observations and reduces action jitter without modifying model parameters. We evaluate SDN on two simulation benchmarks (Google Robot, Widow-X) and two real-world robotic datasets across multiple VLA policies, including pi_0, Groot-N1.5, and Groot-N1.6. SDN consistently improves success rates by +8% in simulation and +10% in real-world settings, while producing smoother and more stable actions. Our results highlight that diffusion noise selection can serve as an effective and general mechanism for enhancing VLA policies at test time.

Submission history

From: Tung Luu [view email]
[v1] Fri, 12 Jun 2026 03:59:47 UTC (14,458 KB)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。