Hongxia Yang

SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue Solving

Model Merging Scaling Laws in Large Language Models

InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners

Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning

InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning

InfiR2: A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models

InfiMed-Foundation: Pioneering Advanced Multimodal Medical Models with Compute-Efficient Pre-Training and Multi-Stage Fine-Tuning

PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models

InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios

InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion

InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models

Law of Vision Representation in MLLMs

Law of Vision Representation in MLLMs

ParallelComp: Parallel Long-Context Compressor for Length Extrapolation

How Can LLM Guide RL? A Value-Based Approach