6 papers · 1 filter
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
Sudong Wang, Weiquan Huang, Xiaomin Yu +9
The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiab…
EventFlash: Towards Efficient MLLMs for Event-Based Vision
Shaoyu Liu, Jianing Li, Guanghui Zhao +4
Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, curre…
EventBench: Towards Comprehensive Benchmarking of Event-based MLLMs
Shaoyu Liu, Jianing Li, Guanghui Zhao +2
Multimodal large language models (MLLMs) have made significant advancements in event-based vision, yet the comprehensive evaluation of their capabilities within a unified benchmark…
Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios
Chunxiao Li, Xiaoxiao Wang, Meiling Li +5
With the rapid advancement of generative models, highly realistic image synthesis has posed new challenges to digital security and media credibility. Although AI-generated image de…
Towards Understanding How Knowledge Evolves in Large Vision-Language Models
Sudong Wang, Yunjian Zhang, Yao Zhu +4
Large Vision-Language Models (LVLMs) are gradually becoming the foundation for many artificial intelligence applications. However, understanding their internal working mechanisms h…
EventGPT: Event Stream Understanding with Multimodal Large Language Models
Shaoyu Liu, Jianing Li, Guanghui Zhao +5
Event cameras record visual information as asynchronous pixel change streams, excelling at scene perception under unsatisfactory lighting or high-dynamic conditions. Existing multi…