6 papers
Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models
Zili Zhang, Yilin Wang, Heng Wang +2
Large language models (LLMs) can solve complex multi-hop problems yet exhibit puzzling failures on simple two-hop queries: although a model may correctly store each individual hop,…
A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models
Yilin Wang, Shangzhe Li, Haoyi Niu +3
We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data cov…
Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models
Yilin Wang, Heng Wang, Yuyang Bai +1
In Large Language Models (LLMs) generation, there exist knowledge conflicts and scenarios where parametric knowledge contradicts knowledge provided in the context. Previous works s…
PTCL: Pseudo-Label Temporal Curriculum Learning for Label-Limited Dynamic Graph
Shengtao Zhang, Haokai Zhang, Shiqi Lou +4
Dynamic node classification is critical for modeling evolving systems like financial transactions and academic collaborations. In such systems, dynamically capturing node informati…
Driving behavior recognition via self-discovery learning
Yilin Wang
Autonomous driving systems require a deep understanding of human driving behaviors to achieve higher intelligence and safety.Despite advancements in deep learning, challenges such…
Efficient and Scalable Deep Reinforcement Learning for Mean Field Control Games
Nianli Peng, Yilin Wang
Mean Field Control Games (MFCGs) provide a powerful theoretical framework for analyzing systems of infinitely many interacting agents, blending elements from Mean Field Games (MFGs…