Zhongwang Zhang
7 papers · 2021–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(5)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
🐝
Cross-Pollinator
(15)
Conferences
NIPS (2)
ACL (1)
EMNLP (1)
ICLR (1)
ICML (1)
JMLR (1)
Top co-authors
Keywords
transformer model
(2)
deep neural network
(2)
sample complexity
(1)
neural network optimization
(1)
loss landscape
(1)
optimization theory
(1)
network optimization
(1)
information seeking
(1)
parameter initialization
(1)
reasoning ability
(1)
compositional reasoning
(1)
theoretical guarantee
(1)
information flow
(1)
critical point
(1)
multi-step reasoning
(1)
large language model
(1)
buffer mechanism
(1)
embedding principle
(1)
local linear recovery
(1)
browser-use learning
(1)
Papers
Nested Browser-Use Learning for Agentic Information Seeking
ACL 2026
An Analysis for Reasoning Bias of Language Models with Small Initialization
ICML 2025
Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
JMLR 2025
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
EMNLP 2025
Stochastic Modified Equations and Dynamics of Dropout Algorithm
ICLR 2024
Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
NIPS 2024
Embedding Principle of Loss Landscape of Deep Neural Networks
NIPS 2021