4 papers
Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation
Yubo Jiang, Fengying Xie, Zhiguo Jiang +1
Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63.0-68.0% of groups…
Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation
Yubo Jiang, Xin Yang, Abudukelimu Wuerkaixi +7
Vision-Language Models (VLMs) are frequently undermined by object hallucination--generating content that contradicts visual reality--due to an over-reliance on linguistic priors. W…
Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding
Yubo Jiang, Yitong An, Xin Yang +7
Vision-Language Models (VLMs) are frequently undermined by object hallucination, generating content that contradicts visual reality, due to an over-reliance on linguistic priors. W…
V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization
Yubo Jiang, Yitong An, Xin Yang +7
We introduce V-tableR1, a process-supervised reinforcement learning framework that elicits rigorous, verifiable reasoning from multimodal large language models (MLLMs). Current MLL…