Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 13 days ago • 242
Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing Paper • 2610.02772 • Published 19 days ago • 8
CosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements Paper • 2609.07498 • Published Sep 7 • 34
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation Paper • 2609.04083 • Published Sep 3 • 25