activity
20242026
collaborators

6 papers

cs.CL2026

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,…

cs.RO2025

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…

cs.CL2025

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…

cs.LG2025

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…

cs.AI2025

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…

cs.LG2024

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…