Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers Paper ⢠2611.06844 ⢠Published 15 days ago ⢠2
SceneActBench: Can Agents Act on the 3D Scenes They See? Paper ⢠2607.22393 ⢠Published Jul 24 ⢠8
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Paper ⢠2607.19064 ⢠Published Jul 21 ⢠76
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Paper ⢠2606.08063 ⢠Published Jun 6 ⢠33
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models Paper ⢠2606.11025 ⢠Published Jun 9 ⢠42
ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall Paper ⢠2510.07896 ⢠Published Oct 9, 2025 ⢠11
LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization Paper ⢠2506.09373 ⢠Published Jun 11, 2025 ⢠1
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training Paper ⢠2603.12255 ⢠Published Mar 12 ⢠84
LongVideoAgent: Multi-Agent Reasoning with Long Videos Paper ⢠2512.20618 ⢠Published Dec 23, 2025 ⢠57
Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding Paper ⢠2512.17532 ⢠Published Dec 19, 2025 ⢠68
Hawk: Learning to Understand Open-World Video Anomalies Paper ⢠2405.16886 ⢠Published May 27, 2024 ⢠1
LongLive: Real-time Interactive Long Video Generation Paper ⢠2509.22622 ⢠Published Sep 26, 2025 ⢠192