Jie Tang

AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

LogicEvolve: Advancing Logical Reasoning Toward Self-Evolution

Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model

Vector Quantization using Gaussian Variational Autoencoder

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents

TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference

MLE-RL: Reinforcement Learning for Self-Improvement in Machine Learning Agents

RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension

ReST-RL: Reinforcing LLM Reasoning through Self-Training and Value-Guided Decoding

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

Listens like Mel: Boosting Latent Audio Diffusion with Channel Locality

SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression

UI2Code$^N$: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation

PROBE: Benchmarking Reasoning Paradigm Overfitting in Large Language Models

A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models

Scaling Speech-Text Pre-training with Synthetic Interleaved Data

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

Can Large Language Models Master Complex Card Games?

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Does RLHF Scale? Exploring the Effects of Data, Model, and Method

MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model

RedHat: Towards Reducing Hallucination in Essay Critiques with Large Language Models

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

VisScience: An Extensive Benchmark for Evaluating K12 Educational Multi-modal Scientific Reasoning

LVBench: An Extreme Long Video Understanding Benchmark

DataSciBench: An LLM Agent Benchmark for Data Science