127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

94,811 results

Safety

Training-free Behavior Cloning

DGX agent

arXiv:2609.30134v1 Announce Type: new Abstract: Neural behavior cloning compresses demonstrations into large models, making individual actions difficult to trace and policy updates costly. Retrieval p

safetyarxiv-cs-ro

25 Sept 2026

Research

Training-Free Hold-Usage Detection in Sport Climbing with Foundation Pose Models

DGX agent

arXiv:2609.30026v1 Announce Type: new Abstract: Detecting which holds a climber uses, and when, underpins automated scoring, movement analysis, and assistive systems for sport climbing. Existing appro

All entries

Training-free Behavior Cloning

Training-Free Hold-Usage Detection in Sport Climbing with Foundation Pose Models

Training Object Permanence in World Models

Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching

Transformers as Cross-Task Learners: Shared Structure Drives Sample Efficiency in In-Context Learning

TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification

TTLab at StanceEval-2026: A Cloze-Style Prompting Approach for Arabic-Language Stance Detection (CLASP-Ar)

TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split

TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment

Two Emojis of Difference: What Multilingual Affective Generation Benchmarks Actually Measure

Type-Safe Is Not Error-Free: A Constrained Decision Head Follows the Option Name, Not the Rubric Bound to It

UCON: Uncertainty-aware Navigation with Historical Re-association in Dynamic Environments

UltraBench 2: Towards Robust Evaluation of Vision Foundation Models on Ultrasound

Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy

Uncovering Residential PV-EV Co-Adoption from Smart-Meter Data: Load Archetypes and Detection for Demand-Side Planning

Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning

Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage

Unmasking Shortcut Learning in IoT Intrusion Detection: A Forensic, Multi-Paradigm Evaluation of Feature Dependence and Data Leakage

Unraveling the cognitive patterns of Large Language Models through module communities

UNWIND: Any-Length Facial Video for Stress Detection without Temporal Windowing

UO-FIE: Combining Exact-Label Supervision with Graded Utility for Factivity Inference

UpDown-SC: Gravity-Canonicalized Dual-Envelope Scan Context for Indoor LiDAR Place Recognition

Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities

Vector Bellman Theory for Multichain Robust Average-Reward Markov Decision Processes

VG-TIE: An interpretable tabular-to-image encoding method based on visibility graphs

VietPrism: A large-scale Vietnamese speech and deepfake corpus with diverse dialects and code-switching

ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation

Visual Representation and History Modeling for Navigation World Models

WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation

WaterClear-GS: Optical-Aware Gaussian Splatting for Underwater Reconstruction and Restoration

Wearable ECG Quality Assessment: A Deep Learning and Ambulatory Context-Awareness Approach

WeatherDiagFlow: Evidence-Grounded Radar Nowcasting with Diagnostic Flow Refinement

WebArxiv: A Reproducible Benchmark for Evaluating Multimodal Web Agents on arXiv Tasks

What a Cross-Model Fixed-Point Census Can and Cannot Arbitrate About Repetition

What, When, and How: Audio Description as Constrained Global Optimization

When Agents Act Unwatched: The Reduced-Supervision Paradox in Agentic AI

When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression

When Does Action Credit Need Updating?

When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detection

When Explanations Cannot Be Read: Measuring and Correcting SHAP and LIME Rendering for Right-to-Left Languages

When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse

When Honesty is Not Enough in AI Debate

When Identical Rows Disagree: From Benchmark Identifiability to Replication-Robust Anomaly Detection

When Misalignment Becomes Supervision: Structured Label Noise in Supervised Synthetic CT Generation

When No One Owns the Judgment: Accountability Under Contribution Dissolution in Human-AI Collaboration

When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing

When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers

Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents