9 papers
Policy Contrastive Decoding for Robotic Foundation Models
Shihan Wu, Xu Luo, Ji Zhang +4
Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our e…
Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols
Xu Luo, Ji Zhang, Lianli Gao +2
Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.However, there lacks a unified, rigorous evaluation protocol that is bot…
Multi-Agent Collaboration via Evolving Orchestration
Yufan Dang, Chen Qian, Xueheng Luo +11
Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-s…
InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning
Ji Zhang, Shihan Wu, Xu Luo +4
Leveraging pretrained Vision-Language Models (VLMs) to map language instruction and visual observations to raw low-level actions, Vision-Language-Action models (VLAs) hold great pr…
GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models
Min Zeng, Jingfei Sun, Xueyou Luo +4
In natural language processing tasks, pure reinforcement learning (RL) fine-tuning methods often suffer from inefficient exploration and slow convergence; while supervised fine-tun…
From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learning
Ji Zhang, Xu Luo, Lianli Gao +3
Deep neural networks often fail to adapt representations to novel tasks under distribution shifts, especially when only a few examples are available. This paper identifies a core o…