FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving Paper • 2608.19758 • Published 5 days ago • 17
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation Paper • 2608.17426 • Published 8 days ago • 157
Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning Paper • 2608.18746 • Published 7 days ago • 16
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination Paper • 2608.14391 • Published 12 days ago • 277
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published 25 days ago • 262
OPD-V: Visual On-Policy Self-Distillation with Modality Balance Paper • 2608.05131 • Published 20 days ago • 13
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published 22 days ago • 52
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 23 days ago • 156
SWE-Touch: Benchmarking Coding Agents When Users Touch the Code Paper • 2608.02499 • Published 23 days ago • 24
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering Paper • 2607.28568 • Published 27 days ago • 185
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents Paper • 2607.28227 • Published 27 days ago • 309