activity
20242026
collaborators

10 papers

cs.LG2026

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

Kangwen Zhao, Jianfeng Cai, Jinhua Zhu +5

Reinforcement Learning from Human Feedback (RLHF) relies on reward models to align large language models with human preferences. However, RLHF often suffers from reward hacking, wh…

cs.CV2026

EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive Model

Ruixiao Dong, Zhendong Wang, Keli Liu +5

Subject-driven generation is a critical task in creative AI; yet current state-of-the-art methods present a stark trade-off. They either rely on computationally expensive, per-subj…

cs.AI2025

Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks

Ruopei Sun, Jianfeng Cai, Jinhua Zhu +5

RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences, demonstrating exceptional and measurable efficacy in instruction fol…

cs.CV2025

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering

Jianfeng Cai, Wengang Zhou, Zongmeng Zhang +3

Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding.However, hallucination, where the model generates plausible yet incorrect outputs,…

cs.LG2025

Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling

Jianfeng Cai, Jinhua Zhu, Ruopei Sun +4

Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs) by modeling human preferences with a learnable reward m…

cs.CV2025

Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression

Hanyue Tu, Siqi Wu, Li Li +2

Autoencoder-based structures have dominated recent learned image compression methods. However, the inherent information loss associated with autoencoders limits their rate-distorti…