deepseek-ai/DeepSeek-V4-Flash-Vision-Exp Image-Text-to-Text • 305B • Updated 7 days ago • 252k • • 804
FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving Paper • 2608.19758 • Published 19 days ago • 20
FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents Paper • 2608.18423 • Published 20 days ago • 21
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains Paper • 2608.09873 • Published 29 days ago • 29
PaDoc: Layout-Grounded Parallel Decoding for Document Parsing Paper • 2608.06146 • Published Aug 6 • 24
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning Paper • 2608.01837 • Published Aug 3 • 39