Guangtao Zeng

BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization

EvoScale: Evolutionary Test-Time Scaling for Software Engineering

Tailored Primitive Initialization is the Secret Key to Reinforcement Learning

RegMix: Data Mixture as Regression for Language Model Pre-training

Scaling up Masked Diffusion Models on Text

Long Context Transfer from Language to Vision

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning

MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation

Effi-Code: Unleashing Code Efficiency in Language Models