Wei Tao
11 papers · 2021–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🗺️ Taxonomy Completionist (33) 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver
👥
Mega-Team · Squad
🌈
Renaissance Researcher
(5)
💎
Century Club · Bronze
🗃️
Keyword Collector
(71)
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(7)
Deep Learning
(6)
Core AI
(6)
Optimization & Theory · Machine Learning
(4)
Mathematics & Optimization
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Optimization
(3)
Optimization & Theory · Deep Learning
(3)
Computer Science
(2)
Natural Language Processing
(2)
Application Areas
(2)
Applications · Natural Language Processing
(2)
Applications · Computer Science
(2)
Keywords
code generation
(3)
large language model
(2)
momentum method
(2)
convergence analysis
(2)
llm agent
(2)
video understanding
(1)
semantic similarity
(1)
convex optimization
(1)
strongly convex optimization
(1)
software engineering
(1)
gradient descent
(1)
adversarial attack
(1)
support vector machine
(1)
regret bound
(1)
benchmark dataset
(1)
convergence rate
(1)
mixture of expert
(1)
multimodal large language model
(1)
constrained optimization
(1)
speech processing
(1)
Papers
The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers
CVPR 2026
Vista: Scene-Aware Optimization for Streaming Video Question Answering Under Post-Hoc Queries
AAAI 2026
C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations
EMNLP 2025
Data Interpreter: An LLM Agent for Data Science
ACL 2025
MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts
ACL 2025
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
NeurIPS 2024
On the Convergence of an Adaptive Momentum Method for Adversarial Attacks
AAAI 2024
Provable Acceleration of Nesterov’s Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks
IJCAI 2024
RACE: Retrieval-augmented Commit Message Generation
EMNLP 2022
Gradient Descent Averaging and Primal-dual Averaging for Strongly Convex Optimization
AAAI 2021
The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods
ICLR 2021