6 papers
FocusOPD: Structure-Guided On-Policy Distillation for Diffusion Models
Xinrui Lin, Shumin Wang, Suqi Song +2
Multi-teacher on-policy distillation enables rectified-flow models with diffusion-transformer architectures to combine task-specific capabilities within a single student. However,…
When Pairwise Preferences Cycle: A Reliability-Anchored Preference Walk for Video GRPO
Xinrui Lin, Fan Li, Shumin Wang +2
Pairwise preference feedback has become a widely adopted supervision signal for reinforcement learning in video generation models, as pairwise comparisons provide a more reliable a…
-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?
Leilei Ding, Shumin Wang, Yuting Huang +10
Large language models (LLMs) now show strong reasoning and coding abilities, raising the prospect that they could assist in developing and optimizing the very infrastructure that p…
ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered Scenes
Xinrui Lin, Sha Zhang, Shumin Wang +3
Task-driven 3D affordance grounding aims to localize the functional region in a cluttered 3D scene that enables an action specified by a natural-language instruction. Existing meth…
On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
Shumin Wang, Yuexiang Xie, Wenhao Zhang +4
Entropy serves as a critical metric for measuring the diversity of outputs generated by large language models (LLMs), providing valuable insights into their exploration capabilitie…
Self-Supervised Pre-training with Combined Datasets for 3D Perception in Autonomous Driving
Shumin Wang, Zhuoran Yang, Lidian Wang +7
The significant achievements of pre-trained models leveraging large volumes of data in the field of NLP and 2D vision inspire us to explore the potential of extensive data pre-trai…