QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation Paper • 2512.19134 • Published 6 days ago • 31
MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs Paper • 2511.14159 • Published Nov 18 • 24
More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models Paper • 2509.25848 • Published Sep 30 • 80
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning Paper • 2509.22647 • Published Sep 26 • 32
Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic Paper • 2509.01363 • Published Sep 1 • 58
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification Paper • 2508.05629 • Published Aug 7 • 180
LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers Paper • 2507.04404 • Published Jul 6 • 21