Zifeng Cheng
12 papers · 2020–2026 · 4 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 ↑
πΊοΈ Taxonomy Completionist (35) π Academic Marathon Β· Sprint π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze
π€
Dynamic Duo
(11)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(62)
Venues
Top co-authors
Research topics
Deep Learning
(9)
Machine Learning
(9)
Artificial Intelligence
(7)
Natural Language Processing
(7)
Core Methods
(7)
Learning Types Β· Deep Learning
(7)
Core AI
(6)
Resources & Methods
(5)
Application Areas
(3)
Applications
(3)
Learning Types Β· Machine Learning
(3)
Interdisciplinary
(1)
Generation
(1)
Learning Paradigms
(1)
Models
(1)
Keywords
prompt engineering
(4)
semantic textual similarity
(3)
sentence embedding
(3)
neural network
(2)
large language model
(2)
feature learning
(1)
metric learning
(1)
representation learning
(1)
model calibration
(1)
natural language processing
(1)
optimal transport
(1)
attention mechanism
(1)
contrastive learning
(1)
text-to-image generation
(1)
deep learning
(1)
domain generalization
(1)
natural language understanding
(1)
language understanding
(1)
clause representation
(1)
semantic representation
(1)
Papers
AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM
ACL 2026
Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs
ACL 2026
RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection
AAAI 2026
Rethinking BCE Loss for Multi-Label Image Recognition with Fine-Tuning
CVPR 2026
Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation
CVPR 2026
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
ACL 2025
Multi-Prompting Decoder Helps Better Language Understanding
ACL 2025
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
ACL 2025
Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring
ACL 2023
Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning
AAAI 2023
Improving Domain Generalization for Prompt-Aware Essay Scoring via Disentangled Representation Learning
ACL 2023
A Symmetric Local Search Network for Emotion-Cause Pair Extraction
COLING 2020