Prof. YANG Hongxia
Research Highlight
LLM with Ultra-Low Resource and Strong Reasoning Capability
High-quality pre-training data forms the foundation of a model's core capabilities and is essential for strong reasoning performance.
MLLM with Ultra-Low Resource and Strong Multimodal Reasoning
InfiGUI-G1 addresses critical challenges in GUI interaction through grounding enhanced reinforcement learning.
Ultra-Efficient Low-Bit LLMs: Train & Development
Our breakthrough research addresses the critical challenge of performance degradation in quantized models, particularly for reasoning-related tasks.
Unconstrained Model Fusion for Enhanced LLM Reasoning
InfiFusion revolutionizes model collaboration through a unified framework that enables knowledge transfer across different domains and model scales.
Model Fusion via Preference Optimization for Enhanced LLM Reasoning
Low-Resource Model Fusion, Outperforms Peer Models with Equal Size
Agentic AI
Our autonomous AI agent systems demonstrate sophisticated decision-making capabilities through advanced architectural designs.
AoE: Angle-Optimized Embeddings for Semantic Textual Similarity
To address this, we propose AnglE (Angle-optimized Embeddings), a novel text embedding approach that optimizes angle differences in complex space instead of relying on cosine similarity.
LLM4Decompile: Decompiling Binary Code with Large Language Models
• 100%+ improvement over GPT-4o and Ghidra in re-executability
• 6K GitHub stars and featured in Weekly Trending
• 67 citations on Google Scholar
