Bang Liu

GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks

VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations

ReCode: Unify Plan and Action for Universal Granularity Control

M$^{4}$olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping

Automating Environments For Measuring Agentic Learning

Concept-Based Steering of LLMs for Conditional Molecular Generation

AFlow: Automating Agentic Workflow Generation

OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection

System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts

MatExpert: Decomposing Materials Discovery By Mimicking Human Experts

Data Interpreter: An LLM Agent For Data Science

SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning