activity
20242026
collaborators

9 papers

cs.CV2026

SAGE: Synchronized Action-Gaze Recognition and Anticipation for Human Behavior Understanding

Chenyi Kuang, Nakul Agarwal

Human object interaction (HOI), gaze pattern, and their anticipation are intricately linked, providing valuable insights into cognitive processes, intentions, and behavior. However…

cs.CL2026

Generative Skill Composition for LLM Agents

Xinyu Zhao, Zhen Tan, Vaishnav Tadiparthi +5

Recent LLM agents benefit from skills for solving complex tasks. Skills encapsulate modular packages of procedural knowledge and instructions for performing specialized tasks, such…

cs.AI2026

Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner

Chunhui Zhang, Zhongyu Ouyang, Kwonjoon Lee +4

Theory-of-Mind (ToM) enables humans to infer mental states-such as beliefs, desires, and intentions-forming the foundation of social cognition. However, existing computational ToM…

cs.RO2026

MERGE: Guided Vision-Language Models for Multi-Actor Event Reasoning and Grounding in Human-Robot Interaction

Joerg Deigmoeller, Nakul Agarwal, Stephan Hasler +8

We introduce MERGE, a system for situational grounding of actors, objects, and events in dynamic human-robot group interactions. Effective collaboration in such settings requires c…

cs.CV2026

Towards Driver Behavior Understanding: Weakly-Supervised Risk Perception in Driving Scenes

Nakul Agarwal, Yi-Ting Chen, Behzad Dariush

Achieving zero-collision mobility remains a key objective for intelligent vehicle systems, which requires understanding driver risk perception-a complex cognitive process shaped by…

cs.LG2026

Learning Robust Reasoning through Guided Adversarial Self-Play

Shuozhe Li, Vaishnav Tadiparthi, Kwonjoon Lee +6

Reinforcement learning from verifiable rewards (RLVR) produces strong reasoning models, yet they can fail catastrophically when the conditioning context is fallible (e.g., corrupte…