Haoran Yang
20 papers · 2021–2026 · 11 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· Silver πΊοΈ Taxonomy Completionist (41) π£ Hot Topic Early Bird π Conference Polyglot Β· Gold π Academic Marathon Β· Sprint
π€
Dynamic Duo
(11)
π
Renaissance Researcher
(5)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(94)
Venues
Top co-authors
Research topics
Artificial Intelligence
(12)
Machine Learning
(11)
Natural Language Processing
(9)
Core AI
(9)
Deep Learning
(7)
Learning Types
(7)
Generation
(6)
Learning Paradigms
(4)
Resources & Methods
(4)
Architectures
(3)
Core Methods
(3)
Models
(3)
Optimization & Theory
(3)
Computer Science
(2)
Computer Vision
(2)
Keywords
large language model
(6)
text generation
(3)
graph neural network
(3)
transfer learning
(3)
graph convolution
(2)
feature extraction
(2)
model compression
(2)
decoding method
(2)
contrastive learning
(2)
in-context learning
(2)
parameter-efficient fine-tuning
(2)
paraphrase generation
(2)
token selection
(1)
dialogue generation
(1)
prompt engineering
(1)
conversational ai
(1)
lottery ticket hypothesis
(1)
efficient computing
(1)
machine translation
(1)
neural text generation
(1)
Papers
HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds
NSDI 2026
Fast Image Super-Resolution via Consistency Rectified Flow
ICCV 2025
Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks
AAAI 2025
Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition
AAAI 2025
Meta-Learning-Driven CT Morphology Disentangled Diffusion Model for Multi-Region SPECT Attenuation Correction
MICCAI 2025
Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations
NAACL 2025
TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning
ICCV 2025
UltraModel: A Modeling Paradigm for Industrial Objects
IJCAI 2025
A Frustratingly Simple Decoding Method for Neural Text Generation
COLING 2024
A Thorough Examination of Decoding Methods in the Era of LLMs
EMNLP 2024
Chain-of-Dictionary Prompting Elicits Translation in Large Language Models
EMNLP 2024
Exploring Compositional Generalization of Large Language Models
NAACL 2024
Rephrasing Invokes Better Generations for Large Language Models
NAACL 2024
Unifying Homophily and Heterophily for Spectral Graph Neural Networks via Triple Filter Ensembles
NeurIPS 2024
Unveiling the Generalization Power of Fine-Tuned Large Language Models
NAACL 2024
An Empirical Study Towards Prompt-Tuning for Graph Contrastive Pre-Training in Recommendations
NeurIPS 2023
Bridging the Gap between Pre-Training and Fine-Tuning for Commonsense Generation
EACL 2023
On the Effectiveness of Parameter-Efficient Fine-Tuning
AAAI 2023
A Two-Stage Training Framework with Feature-Label Matching Mechanism for Learning from Label Proportions
ACML 2021
Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation
EMNLP 2021