20 papers · 1 filter
Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems
Zongqian Li, Tengchao Lv, Shaohan Huang +8
Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We…
Code Aesthetics with Agentic Reward Feedback
Bang Xiao, Lingjie Jiang, Shaohan Huang +5
Large Language Models (LLMs) have become valuable assistants for developers in code-related tasks. While LLMs excel at traditional programming tasks such as code generation and bug…
Geometric-Mean Policy Optimization
Yuzhong Zhao, Yue Liu, Junpeng Liu +9
Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unf…
VibeVoice Technical Report
Zhiliang Peng, Jianwei Yu, Wenhui Wang +10
This report presents VibeVoice, a novel model designed to synthesize long-form speech with multiple speakers by employing next-token diffusion, which is a unified method for modeli…
VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
Lingjie Jiang, Shaohan Huang, Xun Wu +3
Multimodal large language models (MLLMs) have significantly advanced the integration of visual and textual understanding. However, their ability to generate code from multimodal in…
Think Only When You Need with Large Hybrid-Reasoning Models
Lingjie Jiang, Xun Wu, Shaohan Huang +7
Recent Large Reasoning Models (LRMs) have shown substantially improved reasoning capabilities over traditional Large Language Models (LLMs) by incorporating extended thinking proce…