Zekai Shao
4 papers · 2025–2026 · 3 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 ↓
π
Conference Polyglot Β· Bronze
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(13)
Top co-authors
Research topics
Artificial Intelligence
(3)
Deep Learning
(3)
Machine Learning
(2)
Reinforcement Learning
(2)
Application Areas
(2)
Core AI Β· Artificial Intelligence
(2)
Learning Types
(2)
Methods
(2)
Computer Vision
(1)
Analysis
(1)
Core AI Β· Computer Vision
(1)
Learning Paradigms
(1)
Optimization & Theory
(1)
Techniques
(1)
Keywords
large language model
(2)
policy optimization
(2)
rgb-t tracking
(2)
reinforcement learning
(2)
visual tracking
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
parameter update
(1)
domain shift
(1)
gradient-free optimization
(1)
online adaptation
(1)
orthogonal constraint
(1)
online model adaptation
(1)
probability mass
(1)
rank decomposition
(1)
multi-modal tracking
(1)
parameter decomposition
(1)
probability gradient
(1)
gradient utilization
(1)
test-time adaptation
(1)
Papers
From log π to π: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
ACL 2026
Group Orthogonal Low-Rank Adaptation for RGB-T Tracking
AAAI 2026
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
ACL 2026
PURA: Parameter Update-Recovery Test-Time Adaption for RGB-T Tracking
CVPR 2025