5 citations · 18 across the 24 of their papers we have counts for
4 papers · 2 filters
Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models
Minghe Shen, Zhuo Zhi, Chonghan Liu +3
Recent studies posit that Reinforcement Learning with Verifiable Rewards (RLVR) primarily amplifies behaviors inherent to the pre-training distribution rather than inducing new cap…
SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems
Peiran Li, Xinkai Zou, Zhuohang Wu +9
Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Des…
V2X-UniPool: Unifying Multimodal Perception and Knowledge Reasoning for Autonomous Driving
Xuewen Luo, Fengze Yang, Fan Ding +5
Autonomous driving (AD) has achieved significant progress, yet single-vehicle perception remains constrained by sensing range and occlusions. Vehicle-to-Everything (V2X) communicat…
mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation
Chan-Wei Hu, Yueqi Wang, Shuo Xing +4
Large Vision-Language Models (LVLMs) have made remarkable strides in multimodal tasks such as visual question answering, visual grounding, and complex reasoning. However, they rema…