34 citations · 89 across the 18 of their papers we have counts for
18 papers
HorizonBench: Long-Horizon Personalization with Evolving Preferences
Shuyue Stella Li, Bhargavi Paranjape, Kerem Oktar +9
User preferences evolve across months of interaction, and tracking them requires inferring when a stated preference has been changed by a subsequent life event. We define this prob…
CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production
Yixin Nie, Lin Guan, Zhongyao Ma +19
This report presents CharacterFlywheel, an iterative flywheel process for improving large language models (LLMs) in production social chat applications across Instagram, WhatsApp,…
Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
Zhihan Liu, Lin Guan, Yixin Nie +6
Generalist LLM agents are often post-trained on a narrow set of environments but deployed across far broader, unseen domains. In this work, we investigate the challenge of agentic…
Scale-Adaptive Power Flow Analysis with Local Topology Slicing and Multi-Task Graph Learning
Yongzhe Li, Lin Guan, Zihan Cai +3
Developing deep learning models with strong adaptability to topological variations is of great practical significance for power flow analysis. To enhance model performance under va…
Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning
Atharva Gundawar, Mudit Verma, Lin Guan +3
As the applicability of Large Language Models (LLMs) extends beyond traditional text processing tasks, there is a burgeoning interest in their potential to excel in planning and re…
Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors
Lin Guan, Yifan Zhou, Denis Liu +3
Large-scale generative models are shown to be useful for sampling meaningful candidate solutions, yet they often overlook task constraints and user preferences. Their full power is…
LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks
Subbarao Kambhampati, Karthik Valmeekam, Lin Guan +5
There is considerable confusion about the role of Large Language Models (LLMs) in planning and reasoning tasks. On one side are over-optimistic claims that LLMs can indeed do these…
Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
Lin Guan, Karthik Valmeekam, Sarath Sreedharan +1
There is a growing interest in applying pre-trained large language models (LLMs) to planning problems. However, methods that use LLMs directly as planners are currently impractical…
Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
Lin Guan, Karthik Valmeekam, Subbarao Kambhampati
Generating complex behaviors that satisfy the preferences of non-expert users is a crucial requirement for AI agents. Interactive reward learning from trajectory comparisons (a.k.a…
Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion
Utkarsh Soni, Nupur Thakur, Sarath Sreedharan +4
There is a growing interest in developing automated agents that can work alongside humans. In addition to completing the assigned task, such an agent will undoubtedly be expected t…
Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
Lin Guan, Sarath Sreedharan, Subbarao Kambhampati
Creating reinforcement learning (RL) agents that are capable of accepting and leveraging task-specific knowledge from humans has been long identified as a possible strategy for dev…
Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers
Lin Guan, Xia Xiao, Ming Chen +1
Feature selection has been an essential step in developing industry-scale deep Click-Through Rate (CTR) prediction systems. The goal of neural feature selection (NFS) is to choose…
Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning
Yantian Zha, Lin Guan, Subbarao Kambhampati
Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. An ambiguous demonstration can usually be interpreted in m…
Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems
Subbarao Kambhampati, Sarath Sreedharan, Mudit Verma +2
Despite the surprising power of many modern AI systems that often learn their own representations, there is significant discontent about their inscrutability and the attendant prob…
Contrastively Learning Visual Attention as Affordance Cues from Demonstrations for Robotic Grasping
Yantian Zha, Siddhant Bhambri, Lin Guan
Conventional works that learn grasping affordance from demonstrations need to explicitly predict grasping configurations, such as gripper approaching angles or grasping preshapes.…
Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation
Lin Guan, Mudit Verma, Sihang Guo +2
Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under t…
Leveraging Human Guidance for Deep Reinforcement Learning Tasks
Ruohan Zhang, Faraz Torabi, Lin Guan +2
Reinforcement learning agents can learn to solve sequential decision tasks by interacting with the environment. Human knowledge of how to solve these tasks can be incorporated usin…
Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset
Ruohan Zhang, Calen Walshe, Zhuode Liu +6
Large-scale public datasets have been shown to benefit research in multiple areas of modern artificial intelligence. For decision-making research that requires human data, high-qua…