Kezhi Mao
17 papers · 2019–2026 · 9 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 ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (35) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Academic Marathon Β· Sprint
π€
Dynamic Duo
(11)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(81)
Top co-authors
Research topics
Machine Learning
(13)
Natural Language Processing
(11)
Artificial Intelligence
(8)
Core AI
(7)
Deep Learning
(6)
Application Areas
(6)
Applications
(6)
Learning Types Β· Machine Learning
(6)
Core Methods
(5)
Resources & Methods
(4)
Architectures
(3)
Learning Types Β· Deep Learning
(3)
Computer Vision
(2)
Data Science & Analytics
(2)
Methods
(2)
Keywords
text classification
(4)
knowledge distillation
(3)
in-context learning
(3)
domain adaptation
(2)
model compression
(2)
document-level extraction
(2)
large language model
(2)
time series
(2)
event argument extraction
(2)
universum class
(2)
adversarial learning
(2)
attention mechanism
(2)
lightweight model
(2)
model interpretability
(2)
few-shot learning
(1)
model robustness
(1)
causal inference
(1)
scene understanding
(1)
prompt-based learning
(1)
reinforcement learning
(1)
Papers
Rethinking Prompt Optimizers: From Prompt Merits to Optimization
EACL 2026
Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction
NAACL 2025
HFD-Teacher: High-Frequency Depth Distillation from Depth Foundation Models for Enhanced Depth Completion
ICCV 2025
Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning
NAACL 2025
EDEntail: An Entailment-based Few-shot Text Classification with Extensional Definition
NAACL 2024
FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation
ACL 2024
LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction
ACL 2024
PromptExplainer: Explaining Language Models through Prompt-based Learning
EACL 2024
Reinforced Cross-Domain Knowledge Distillation on Time Series Data
NeurIPS 2024
UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
NeurIPS 2024
Unveiling and Manipulating Prompt Influence in Large Language Models
ICLR 2024
Closed Boundary Learning for Classification Tasks with the Universum Class
EMNLP 2023
Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data
IJCAI 2023
Document-Level Event Argument Extraction by Leveraging Redundant Information and Closed Boundary Loss
NAACL 2022
ACT: an Attentive Convolutional Transformer for Efficient Text Classification
AAAI 2021
Partial Video Domain Adaptation With Partial Adversarial Temporal Attentive Network
ICCV 2021
Improving Relation Extraction with Knowledge-attention
EMNLP 2019