4 papers
FlowConsist: Make Your Flow Consistent with Real Trajectory
Tianyi Zhang, Chengcheng Liu, Jinwei Chen +5
Fast flow models accelerate the iterative sampling process by learning to directly predict ODE path integrals, enabling one-step or few-step generation. However, we argue that curr…
Visionary Co-Driver: Enhancing Driver Perception of Potential Risks with LLM and HUD
Wei Xiang, Ziyue Lei, Jie Wang +5
Drivers' perception of risky situations has always been a challenge in driving. Existing risk-detection methods excel at identifying collisions but face challenges in assessing the…
IKnow: Instruction-Knowledge-Aware Continual Pretraining for Effective Domain Adaptation
Tianyi Zhang, Florian Mai, Lucie Flek
Continual pretraining promises to adapt large language models (LLMs) to new domains using only unlabeled test-time data, but naively applying standard self-supervised objectives to…
Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference
Wenjie Qiu, Yi-Chen Li, Xuqin Zhang +4
Learning reward models from human preference datasets and subsequently optimizing language models via reinforcement learning has emerged as a fundamental paradigm for aligning LLMs…