Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes Paper • 2610.32749 • Published 14 days ago • 29
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence Paper • 2610.34283 • Published 12 days ago • 41
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning Paper • 2610.18683 • Published 12 days ago • 16
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence Paper • 2610.34283 • Published 12 days ago • 41
Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents Paper • 2610.33568 • Published 13 days ago • 39
Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents Paper • 2610.33568 • Published 13 days ago • 39
Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents Paper • 2610.26233 • Published 18 days ago • 19
PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking Paper • 2610.27628 • Published 17 days ago • 40
PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking Paper • 2610.27628 • Published 17 days ago • 40
BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business Paper • 2610.20424 • Published 23 days ago • 65
BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business Paper • 2610.20424 • Published 23 days ago • 65
UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation Paper • 2610.09823 • Published about 1 month ago • 33
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Paper • 2608.11772 • Published Aug 12 • 3
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence Paper • 2609.05571 • Published Sep 4 • 79
CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion Paper • 2606.30030 • Published Jun 29 • 5
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence Paper • 2609.05571 • Published Sep 4 • 79
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Paper • 2608.11772 • Published Aug 12 • 3
ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction Paper • 2608.13622 • Published Aug 13 • 17
AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents Paper • 2605.17933 • Published May 18 • 7