Bo Dai

Spectral Bellman Method: Unifying Representation and Exploration in RL

Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior

MLE-Smith: Scaling MLE Tasks with Automated Multi-agent Pipeline

Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces

One-Step Flow Policy Mirror Descent

Causal Partial Identification with Data Augmentation

Towards Better Instruction Following Retrieval Models

Judging with Confidence: Calibrating Autoraters to Preference Distributions

An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation

Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL

REINFORCE Converges to Optimal Policies with Any Learning Rate

AmorLIP: Efficient Language-Image Pretraining via Amortization

Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs

EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games

Efficient Online Reinforcement Learning for Diffusion Policy

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

Martryoshka: Learning to Drive Black-Box LLMs with LLMs

VideoAgent: Self-Improving Video Generation