collaborators

13 papers

cs.CV2026

DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning

Bingchen Huang, Yifu Chen, Zhiling Wang +1

Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our analyses suggest that classificat…

cs.CV2026

Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap

Bingchen Huang, Zhiling Wang, Yifu Chen +1

Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesizes code, or imagines new im…

cs.LG2026

On the Geometry of On-Policy Distillation

Zhennan Shen, Yanshu Li, Qingyu Yin +6

On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of O…

cs.RO2026

Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving

Zehan Zhang, Neng Zhang, Yaoyi Li +2

Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency. Small perturbations across frames can accumulate into unstable trajectories, degr…

cs.CL2026

Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training

Hengyu Shi, Tianyang Han, Peizhe Wang +3

LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it couples task adaptation to f…

cs.AI2026

Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards

Tianyang Han, Hengyu Shi, Junjie Hu +3

Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal wh…