11 papers
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3
David Courtis, Wenhao Li, Scott Sanner
Learning a useful world model from minimal interaction is central to building agents that adapt to unfamiliar tasks. Programmatic world modeling approaches such as WorldCoder quick…
MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation
Hongpeng Wang, Zeyu Zhang, Wenhao Li +1
Human motion understanding and generation are crucial for vision and robotics but remain limited in reasoning capability and test-time planning. We propose MoRL, a unified multimod…
Certifiable Boolean Reasoning Is Universal
Wenhao Li, Anastasis Kratsios, Hrad Ghoukasian +1
The proliferation of agentic systems has thrust the reasoning capabilities of AI into the forefront of contemporary machine learning. While it is known that there \emph{exist} neur…
VAT: Vision Action Transformer by Unlocking Full Representation of ViT
Wenhao Li, Chengwei Ma, Weixin Mao
In robot learning, Vision Transformers (ViTs) are standard for visual perception, yet most methods discard valuable information by using only the final layer's features. We argue t…
MOCHA: Discovering Multi-Order Dynamic Causality in Temporal Point Processes
Yunyang Cao, Juekai Lin, Wenhao Li +1
Discovering complex causal dependencies in temporal point processes (TPPs) is critical for modeling real-world event sequences. Existing methods typically rely on static or first-o…
DICE: Data Influence Cascade in Decentralized Learning
Tongtian Zhu, Wenhao Li, Can Wang +1
Decentralized learning offers a promising approach to crowdsource data consumptions and computational workloads across geographically distributed compute interconnected through pee…
Bridging Technology and Humanities: Evaluating the Impact of Large Language Models on Social Sciences Research with DeepSeek-R1
Peiran Gu, Fuhao Duan, Wenhao Li +6
In recent years, the development of Large Language Models (LLMs) has made significant breakthroughs in the field of natural language processing and has gradually been applied to th…
Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction
Yudong W. Xu, Wenhao Li, Scott Sanner +1
We present a Transformer-based framework for Constraint Satisfaction Problems (CSPs). CSPs find use in many applications and thus accelerating their solution with machine learning…
Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects
Wenhao Li, Yudong Xu, Scott Sanner +1
The Abstraction and Reasoning Corpus (ARC) is a popular benchmark focused on visual reasoning in the evaluation of Artificial Intelligence systems. In its original framing, an ARC…
Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
Yuheng Cheng, Ceyao Zhang, Zhengwen Zhang +8
Intelligent agents stand out as a potential path toward artificial general intelligence (AGI). Thus, researchers have dedicated significant effort to diverse implementations for th…
Efficient Planning with Latent Diffusion
Wenhao Li
Temporal abstraction and efficient planning pose significant challenges in offline reinforcement learning, mainly when dealing with domains that involve temporally extended tasks a…