31 citations · 77 across the 20 of their papers we have counts for
20 papers
MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning
Letian Chen, Yiren Lu, Justin Fu +5
Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in semantic understanding and common sense reasoning, making them promising candidates for solvi…
PulseCol: Periodically Refreshed Column-Sparse Attention for Accelerating Diffusion Language Models
Yanyi Lyu, Letian Chen, Futing Sun +3
Inference in diffusion large language models (dLLMs) is computationally expensive, as full self-attention must be repeatedly executed at each step of the denoising process without…
FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
Runzhe Zhang, Letian Chen, Wenpeng Zhang +2
We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the curved sampling trajectories…
Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models
Zhaoxin Li, Zhang Xi-Jia, Batuhan Altundas +3
Semantic interpretability in Reinforcement Learning (RL) enables transparency and verifiability of decision-making. Achieving semantic interpretability in reinforcement learning re…
ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
Letian Chen, Nina Moorman, Matthew Gombolay
Reinforcement learning (RL) has demonstrated compelling performance in robotic tasks, but its success often hinges on the design of complex, ad hoc reward functions. Researchers ha…
Faster Model Predictive Control via Self-Supervised Initialization Learning
Zhaoxin Li, Xiaoke Wang, Letian Chen +3
Model Predictive Control (MPC) is widely used in robot control by optimizing a sequence of control outputs over a finite-horizon. Computational approaches for MPC include determini…
Interpretable Reinforcement Learning for Robotics and Continuous Control
Rohan Paleja, Letian Chen, Yaru Niu +10
Interpretability in machine learning is critical for the safe deployment of learned policies across legally-regulated and safety-critical domains. While gradient-based approaches i…
Learning Models of Adversarial Agent Behavior under Partial Observability
Sean Ye, Manisha Natarajan, Zixuan Wu +3
The need for opponent modeling and tracking arises in several real-world scenarios, such as professional sports, video game design, and drug-trafficking interdiction. In this work,…
Adversarial Search and Tracking with Multiagent Reinforcement Learning in Sparsely Observable Environment
Zixuan Wu, Sean Ye, Manisha Natarajan +3
We study a search and tracking (S&T) problem where a team of dynamic search agents must collaborate to track an adversarial, evasive agent. The heterogeneous search team may only h…
The Effect of Robot Skill Level and Communication in Rapid, Proximate Human-Robot Collaboration
Kin Man Lee, Arjun Krishna, Zulfiqar Zaidi +5
As high-speed, agile robots become more commonplace, these robots will have the potential to better aid and collaborate with humans. However, due to the increased agility and funct…
Utilizing Human Feedback for Primitive Optimization in Wheelchair Tennis
Arjun Krishna, Zulfiqar Zaidi, Letian Chen +3
Agile robotics presents a difficult challenge with robots moving at high speeds requiring precise and low-latency sensing and control. Creating agile motion that accomplishes the t…
Safe Inverse Reinforcement Learning via Control Barrier Function
Yue Yang, Letian Chen, Matthew Gombolay
Learning from Demonstration (LfD) is a powerful method for enabling robots to perform novel tasks as it is often more tractable for a non-roboticist end-user to demonstrate the des…
Athletic Mobile Manipulator System for Robotic Wheelchair Tennis
Zulfiqar Zaidi, Daniel Martin, Nathaniel Belles +20
Athletics are a quintessential and universal expression of humanity. From French monks who in the 12th century invented jeu de paume, the precursor to modern lawn tennis, back to t…
Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations
Letian Chen, Sravan Jayanthi, Rohan Paleja +3
Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. However, c…
Strategy Discovery and Mixture in Lifelong Learning from Heterogeneous Demonstration
Sravan Jayanthi, Letian Chen, Matthew Gombolay
Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. A key chal…
Towards Sample-efficient Apprenticeship Learning from Suboptimal Demonstration
Letian Chen, Rohan Paleja, Matthew Gombolay
Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-roboticist end-users to teach robots to perform novel tasks by providing demonstrations. However, as…
Learning from Suboptimal Demonstration via Self-Supervised Reward Regression
Letian Chen, Rohan Paleja, Matthew Gombolay
Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-roboticist end-users to teach robots to perform a task by providing a human demonstration. However,…
Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation
Letian Chen, Rohan Paleja, Muyleng Ghuy +1
Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning o…
Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations
Rohan Paleja, Andrew Silva, Letian Chen +1
Resource scheduling and coordination is an NP-hard optimization requiring an efficient allocation of agents to a set of tasks with upper- and lower bound temporal and resource cons…
Efficient Model-Free Reinforcement Learning Using Gaussian Process
Ying Fan, Letian Chen, Yizhou Wang
Efficient Reinforcement Learning usually takes advantage of demonstration or good exploration strategy. By applying posterior sampling in model-free RL under the hypothesis of GP,…