2 citations · 2 across the 7 of their papers we have counts for
8 papers
X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization
Sitao Cheng, Xunjian Yin, Zhiyuan Sun +4
Multi-step agents are trained on flat action streams: SFT and RLVR weight every token uniformly and ignore the sub-procedures that recur across tasks, the hierarchy that lets human…
Visual prompt engineering for video models
Robert Geirhos, Yuxuan Li, Thaddäus Wiedemer +7
In the age of foundation models, a model is only as good as its prompt. For this reason, prompt engineering has become an essential technique for improving language model performan…
Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies
Sitao Cheng, Xunjian Yin, Ruiwen Zhou +5
Does Reinforcement Learning (RL) merely amplify existing skills, or synthesize novel skills? We investigate this question through the lens of Complementary Reasoning: the critical…
Accident Anticipation via Temporal Occurrence Prediction
Tianhao Zhao, Yiyang Zou, Zihao Mao +7
Accident anticipation aims to predict potential collisions in an online manner, enabling timely alerts to enhance road safety. Existing methods typically predict frame-level risk s…
Video models are zero-shot learners and reasoners
Thaddäus Wiedemer, Yuxuan Li, Paul Vicol +6
The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models.…
How well can LLMs provide planning feedback in grounded environments?
Yuxuan Li, Victor Zhong
Learning to plan in grounded environments typically requires carefully designed reward functions or high-quality annotated demonstrations. Recent works show that pretrained foundat…
EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos
Yuxuan Li, Vijay Veerabadran, Michael L. Iuzzolino +3
We introduce EgoToM, a new video question-answering benchmark that extends Theory-of-Mind (ToM) evaluation to egocentric domains. Using a causal ToM model, we generate multi-choice…
Understanding Representations Pretrained with Auxiliary Losses for Embodied Agent Planning
Yuxuan Li, Luca Weihs
Pretrained representations from large-scale vision models have boosted the performance of downstream embodied policy learning. We look to understand whether additional self-supervi…