Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities Paper • 2505.21191 • Published 7 days ago • 2
PhyX: Does Your Model Have the "Wits" for Physical Reasoning? Paper • 2505.15929 • Published 13 days ago • 47
SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context Paper • 2411.16213 • Published Nov 25, 2024 • 1
RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video Paper • 2505.02064 • Published about 1 month ago • 2
UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models Paper • 2505.14679 • Published 14 days ago • 5
PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensions Paper • 2505.15472 • Published 13 days ago • 2
SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context Paper • 2411.16213 • Published Nov 25, 2024 • 1
PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensions Paper • 2505.15472 • Published 13 days ago • 2
RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video Paper • 2505.02064 • Published about 1 month ago • 2
UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models Paper • 2505.14679 • Published 14 days ago • 5
JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization Paper • 2503.23377 • Published Mar 30 • 57