Yicheng Zhang
Undergraduate Student, Computer Science and Technology
Tsinghua University, Beijing
About
I am an undergraduate student in the Department of Computer Science and Technology at Tsinghua University. I am interested in making large models faster and cheaper, at both the architecture and the systems level, and in AI systems that can help build better AI.
- Efficient Model Architecture — sparse attention, quantization
- Machine Learning Systems — CUDA / Triton kernel optimization
- Recursive Self-Improvement — AI systems that build better AI
News
- MLS-Bench received the Honorable Mention Award at the ICML 2026 AI for Math Workshop.
- Our team won 1st place (out of 48 teams) in the Tsinghua Student Supercomputing Challenge.
- Our survey of efficient attention methods is out, under review at IEEE TPAMI.
Publications
* equal contribution
-
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
ICML 2026 AI for Math Workshop, 2026 Honorable Mention Award
A benchmark that evaluates LLM agents on real ML research tasks, adopted by Kimi-K2.7-Code, Kimi-K3 and Qwen3.8-Max. I led the ML Systems & Efficient ML track.
-
Second-Look Prompting Improves Vision-Language Models
Preprint, 2026
A training-free method that repeats the image–question sequence to enable question-aware visual processing, improving all 12 evaluated VLMs across 12 reasoning and perception benchmarks.
-
A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention
Under review at IEEE TPAMI, 2025
A taxonomy of efficient attention from four perspectives: hardware efficiency, sparsity, compactness and linearity. I wrote the sparse attention section.
Honors & Awards
-
Champion (1st / 48 teams), Tsinghua Student Supercomputing Challenge2025
Led the GPU optimization track; implemented high-performance attention kernels in CUDA.
-
Comprehensive Scholarship, Dept. of Computer Science and Technology, Tsinghua2025
-
National Scholarship, Ministry of Education of China2024
Top 0.2% of undergraduates nationwide.
Education
-
Tsinghua University, B.Eng. in Computer Science and Technology2023 – now
GPA 3.96 / 4.0 · Rank 6 / 173
Activities
- Class President, Class 34, Dept. of Computer Science2024 – 2025
- Student Welfare Representative, Class 34, Dept. of Computer Science2023 – 2024
- Member, Intelligent Agents Division, Student Association for Science and Technology2024 – 2026
- Member, Tsinghua University Drama Troupe2024 – now