8 citations · 14 across the 18 of their papers we have counts for
9 papers · 1 filter
Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL
Hanyu Wang, Nakul Agarwal, Hossein Nourkhiz Mahjoub +4
A verified reference solution provides a correct trajectory for training a reasoning model. Alternatively, a prefix of the reference can guide the model in generating a trajectory…
Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination
Suyu Ye, Zheyuan Zhang, Vaishnav Tadiparthi +5
Robots operating in the physical world will increasingly need to coordinate with other robots, particularly in manipulation tasks where an object may be too large or heavy for a si…
JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
Zheyuan Zhang, Suyu Ye, Nakul Agarwal +5
World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics differ from those seen during…
Test-Time Unlearning via Sparse Autoencoder
Pingzhi Li, Jinhao Duan, Vaishnav Tadiparthi +6
Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modify model weights via gradient a…
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…
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…
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…
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…
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…