SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation Paper • 2606.30124 • Published Jun 29 • 8
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory Paper • 2607.02517 • Published Jul 2 • 33
ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning Paper • 2606.14697 • Published Jun 12 • 8
Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs Paper • 2505.11277 • Published May 16, 2025 • 64
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling Paper • 2603.25746 • Published Mar 26 • 155