Hongming Zhang

Revela: Dense Retriever Learning via Language Modeling

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Don't Throw Away Your Pretrained Model

InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing

WebAggregator: Scaling Complex Logical Information Aggregation for Web Agents Foundation Models

MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression

DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

ParallelSpec: Parallel Drafter for Efficient Speculative Decoding

SePPO: Semi-Policy Preference Optimization for Diffusion Alignment

Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks