Yushun Zhang
7 papers · 2021–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
NIPS (3)
ICLR (2)
ACL (1)
ICML (1)
Top co-authors
Keywords
stochastic gradient descent
(2)
adam optimizer
(2)
geometry problem solving
(1)
neural network optimization
(1)
gradient descent
(1)
hidden layer
(1)
optimization landscape
(1)
hyperparameter tuning
(1)
learning rate
(1)
multimodal large language model
(1)
critical point
(1)
local minimum
(1)
neural network
(1)
hessian spectrum
(1)
momentum parameter
(1)
block heterogeneity
(1)
auxiliary line construction
(1)
long-step reasoning
(1)
stochastic gradient
(1)
diagram comprehension
(1)
Papers
GeoLaux: A Benchmark for Evaluating MLLMs’ Geometry Performance on Long-Step Problems Requiring Auxiliary Lines
ACL 2026
Adam-mini: Use Fewer Learning Rates To Gain More
ICLR 2025
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
ICML 2024
Why Transformers Need Adam: A Hessian Perspective
NIPS 2024
HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning
ICLR 2022
Adam Can Converge Without Any Modification On Update Rules
NIPS 2022
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work
NIPS 2021