activity
20242026
most citedUnderstanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

3 citations · 3 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2025

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play

Qinsi Wang, Bo Liu, Tianyi Zhou +6

Although reinforcement learning (RL) has emerged as a promising approach for improving vision-language models (VLMs) and multimodal large language models (MLLMs), current methods r…