TEST-TIME ADAPTATION WITH CLIP REWARD FOR ZERO-SHOT GENERALIZATION IN VISION-LANGUAGE MODELShttps://openreview.net/pdf?id=kIP0duasBbEfficient Test-Time Prompt Tuning for Vision-Language Modelshttps://arxiv.org/html/2408.05775v1Self-Generated Critiques Boost Reward Modeling for Language Modelshttps://arxiv.org/html/2411.16646v2Rewarding Progress: Scaling Automated Process Verifiers for LLM Reason..