Chuchu Fan

Discrete Adjoint Matching

ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

Pragmatic Curiosity: Unifying Bayesian Optimization and Experimental Design via Active Inference

Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning

R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning

TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks

Simulation to Rules: A Dual-VLM Framework for Formal Visual Planning

Causal Explanations for Human Understanding in Deep Neural Policies

SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing

Collision- and Reachability-Aware Multi-Robot Control with Grounded LLM Planners

Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control

Neural Combinatorial Optimization for Time Dependent Traveling Salesman Problem

HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems

Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?

Steering Large Language Models between Code Execution and Textual Reasoning

TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming

Distributed Epigraph Form Multi-Agent Safe Reinforcement Learning

Grounded Robotic Action-Rule Induction through Language Models (GRAIL)