activity
20232026
most citedMulti-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations

4 citations · 5 across the 9 of their papers we have counts for

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2026

When Good Verifiers Go Bad: Silent Negative Transfer in Verifier-Guided VLM Training

Jianzhe Lin

Verifier reliability is not portable across tasks. A verifier-guided self-DPO pipeline with genuine held-out gains on MathVista (+9.6 points on self-training data, +8.0 held out) c…