5 papers
MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
Guangchen Lan, Sipeng Zhang, Tianle Wang +7
As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving perfor…
Soundness-Aware Level: A Microscopic Signature that Predicts LLM Reasoning Potential
Xuansheng Wu, Xiaoman Pan, Wenlin Yao +1
Reinforcement learning with verifiable rewards (RLVR) can elicit strong reasoning in large language models (LLMs), while their performance after RLVR varies dramatically across dif…
DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes
Zhaowei Wang, Hongming Zhang, Tianqing Fang +6
Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding. However, their potential to comprehend e…
Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization
Daoan Zhang, Guangchen Lan, Dong-Jun Han +8
Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffer…
Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots
Hongming Zhang, Xiaoman Pan, Hongwei Wang +3
We introduce Cognitive Kernel, an open-source agent system towards the goal of generalist autopilots. Unlike copilot systems, which primarily rely on users to provide essential sta…