Tianyu Liu

Kimi-Dev: Agentless Training as Skill Prior for SWE-agents

OJBench: A Competition Level Code Benchmark For Large Language Models

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models

Self-Evolving Critique Abilities in Large Language Models

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

ML-Bench: Evaluating Large Language Models for Code Generation in Repository-Level Machine Learning Tasks

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

CodeChain: An Open, Million-scale Dataset for Code Language Models at the Repository Level