Haokun Lin
13 papers · 2023–2026 · 6 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (28) 🗃️ Keyword Collector (66)
💎
Century Club · Bronze
❓
The Questioner
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI · Artificial Intelligence
(9)
Deep Learning
(6)
Machine Learning
(6)
Application Areas
(6)
Natural Language Processing
(3)
Models
(3)
Optimization & Theory
(3)
Computer Vision
(2)
Architectures
(2)
Generation
(2)
Healthcare & Medicine
(1)
Applications
(1)
Clinical
(1)
Core AI · Computer Vision
(1)
Keywords
model compression
(5)
large language model
(4)
multimodal large language model
(2)
model quantization
(2)
contrastive learning
(2)
model pruning
(2)
knowledge distillation
(1)
instruction tuning
(1)
attention mechanism
(1)
medical report generation
(1)
parameter efficiency
(1)
referring expression
(1)
semantic information
(1)
knowledge graph
(1)
vision-language model
(1)
code generation
(1)
dynamic graph
(1)
diffusion model
(1)
multimodal learning
(1)
medical imaging
(1)
Papers
CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning
CVPR 2026
EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Compact Language Models
ACL 2026
QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
CVPR 2026
DOGR: Towards Versatile Visual Document Grounding and Referring
ICCV 2025
Image-level Memorization Detection via Inversion-based Inference Perturbation
ICLR 2025
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
NeurIPS 2024
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
ACL 2024
Learning with Counterfactual Explanations for Radiology Report Generation
ECCV 2024
MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
ECCV 2024
MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric
CVPR 2024
Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models
ICLR 2024
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
NeurIPS 2024
Dynamic Graph Enhanced Contrastive Learning for Chest X-Ray Report Generation
CVPR 2023