8 papers
Towards Ultrafast Depth Sensing Via Active Event-based Stereo Vision
Jianing Li, Yunjian Zhang, Haiqian Han +2
Conventional frame-based imaging for active stereo systems has encountered major challenges in fast-motion scenarios. However, how to design a novel paradigm for ultrafast depth se…
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…
SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition
Peiran Xu, Sudong Wang, Yao Zhu +3
Spatial cognition is fundamental to real-world multimodal intelligence, allowing models to effectively interact with the physical environment. While multimodal large language model…
Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
Yunjian Zhang, Sudong Wang, Yang Li +5
Large language models (LLMs) have exhibited remarkable performance on complex reasoning tasks, with reinforcement learning under verifiable rewards (RLVR) emerging as a principled…
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…