SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation Paper • 2606.30124 • Published 12 days ago • 7
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory Paper • 2607.02517 • Published 9 days ago • 32
ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning Paper • 2606.14697 • Published 29 days ago • 8
Alkatt/eval_demo_LAVLA_Async_VI_whiteblackcube_v2_2026_06_02_white_v2 Viewer • Updated Jun 2 • 4.49k • 16 • 1
Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs Paper • 2505.11277 • Published May 16, 2025 • 29
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling Paper • 2603.25746 • Published Mar 26 • 155