6 papers
Graph-Conditioned On-Policy Agent Distillation from Off-the-Shelf Teachers
Xiaohan Yi, Wen Luo, Yani Huang +4
On-policy distillation (OPD) trains compact language agents with teacher feedback on student-generated trajectories. In multi-turn tasks, compounding errors can move students beyon…
VIG: Visual Information Gain as a Reward Signal for Multimodal Chain-of-Thought Compression
Wen Luo, Xiaohan Yi, Xiaotao Huang +1
Multimodal large reasoning models often rely on long Chain-of-Thought (CoT) traces in which a substantial fraction of tokens, such as repeated visual descriptions, self-reflection,…
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
Guikun Xu, Xiaohan Yi, Ziqiao Meng +2
Exploring molecular energy landscapes and identifying ground-state conformations are central challenges in computational chemistry. However, generating diverse low-energy conformer…
CrystalDiT: A Diffusion Transformer for Crystal Generation
Xiaohan Yi, Guikun Xu, Xi Xiao +4
We present CrystalDiT, a diffusion transformer for crystal structure generation that achieves state-of-the-art performance by challenging the trend of architectural complexity. Ins…
PIG-Nav: Key Insights for Pretrained Image Goal Navigation Models
Jiansong Wan, Chengming Zhou, Jinkua Liu +14
Recent studies have explored pretrained (foundation) models for vision-based robotic navigation, aiming to achieve generalizable navigation and positive transfer across diverse env…
UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
Wenbo Wang, Fangyun Wei, Lei Zhou +9
We introduce UniGraspTransformer, a universal Transformer-based network for dexterous robotic grasping that simplifies training while enhancing scalability and performance. Unlike…