← Search

Jianfeng Cai

2 accepted papers

2026

Disentangling Length Bias in Preference Learning via Response-Conditioned Modeling

ICLR 2026poster

Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs) by modeling human preferences with a learnable reward model and employing a reinforcement learning algorithm to maximize the reward model's scores. However, these reward model…

Cited by 0SourceScholar
2025

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering

NeurIPS 2025poster

Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, hallucination, where the model generates plausible yet incorrect outputs, persists as a significant and under-addressed challenge in the video domain. Among existing solutions, activation engi…

Cited by 0SourceScholar