MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents Paper • 2601.12346 • Published 9 days ago • 47
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Paper • 2601.14004 • Published 7 days ago • 45
MMFormalizer: Multimodal Autoformalization in the Wild Paper • 2601.03017 • Published 21 days ago • 104
UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective Paper • 2410.03090 • Published Oct 4, 2024 • 1
UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation Paper • 2410.02719 • Published Oct 3, 2024 • 1
LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interaction Paper • 2509.07403 • Published Sep 9, 2025 • 35
SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning Paper • 2506.01713 • Published Jun 2, 2025 • 48