Oral Presentations
Poster Presentations
Chain of Code: Reasoning with a Language Model-Augmented Code Interpreter
Building Cooperative Embodied Agents Modularly with Large Language Models
Confronting Reward Model Overoptimization with Constrained RLHF
From Text to Tactic: Evaluating LLMs Playing the Game of Avalon
Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making
Ring Attention with Blockwise Transformers for Near-Infinite Context
FoMo rewards: Casting foundation models as generic reward functions
Language Conditioned Semantic Search Based Policy for Robotic Manipulation Tasks
Capture the Flag: Uncovering Data Insights with Large Language Models
Asking Clarifying Questions using Language Models and Probabilistic Reasoning
Investigating the Effectiveness of Self-critiquing in LLMs solving Planning Tasks
ENERGY-BASED REINFORCEMENT LEARNING WITH STEIN SOFT ACTOR CRITIC
Robotic Offline RL from Internet Videos via Value-Function Pre-Training
Self-Select: Optimizing Instruction Selection for Large Language Models
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
GPT-4 Doesn’t Know It’s Wrong: An Analysis of Iterative Prompting for Reasoning Problems
Target Rate Optimization: Avoiding Iterative Error Exploitation
The Unsolved Challenges of LLMs in Open-Ended Web Tasks: A Case Study
Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting
Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations
STEVE-1: A Generative Model for Text-to-Behavior in Minecraft
NexusRaven: A Commercially-Permissive Language Model for Function Calling
ExPT: Scaling Foundation Models for Experimental Design via Synthetic Pretraining
METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View
Language Agents as Digital Representatives in Collective Decision-Making
Vision-Language Models Provide Promptable Representations for Reinforcement Learning
Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion
RF-POLICY: Rectified Flows are Computation-Adaptive Decision Makers
Eureka: Human-Level Reward Design via Coding Large Language Models
Prospector: Improving LLM Agents with Self-Asking and Trajectory Ranking
Semantically-Driven Object Search Using Partially Observed 3D Scene Graphs
Voyager: An Open-Ended Embodied Agent with Large Language Models
Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents
Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
D^3-Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Robotic Manipulation
Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment
AdaPlanner: Adaptive Planning from Feedback with Language Models
Agnostic Architecture for Heterogeneous Multi-Environment Reinforcement Learning
Large Language Models as Commonsense Knowledge for Large-Scale Task Planning
Towards End-to-End Embodied Decision Making with Multi-modal Large Language Model
Language Model Agents Suffer from Compositional Decision Making
Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
B-Coder: On Value-Based Deep Reinforcement Learning for Program Synthesis
LASER: LLM Agent with State-Space Exploration for Web Navigation
Vision-and-Language Navigation in Real World using Foundation Models
Selective Perception: Learning Concise State Descriptions for Language Model Actors
TD-MPC2: Scalable, Robust World Models for Continuous Control
Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training
Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
Learning to Solve New sequential decision-making Tasks with In-Context Learning
Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks
GROOT: Learning to Follow Instructions by Watching Gameplay Videos
TPTU: Task Planning and Tool Usage of Large Language Model-based AI Agents
Identifying the Risks of LM Agents with an LM-Emulated Sandbox
Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
Linear diffusion models meet contextual bandits with large action spaces
Double Policy Estimation for Importance Sampling in Sequence Modeling-Based Reinforcement Learning
A Universal World Model Learned from Large Scale and Diverse Videos
VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View
N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics
On the Tool Manipulation Capability of Open-sourced Large Language Models
When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
AVIS: Autonomous Visual Information Seeking with Large Language Model Agent
Natural Language-based State Representation in Deep Reinforcement Learning