Haowei Lin
14 papers · 2022–2025 · 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 ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (39) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Bronze π Keyword Champion
π
Triple Crown
π
Trend Setter
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(72)
Top co-authors
Research topics
Artificial Intelligence
(10)
Machine Learning
(9)
Core AI
(8)
Deep Learning
(7)
Learning Types Β· Machine Learning
(5)
Natural Language Processing
(4)
Learning Types Β· Deep Learning
(4)
Resources & Methods
(4)
Application Areas
(3)
Learning Paradigms
(3)
Models
(3)
Core Methods
(2)
Techniques
(2)
Computer Vision
(1)
Robotics
(1)
Keywords
language model
(3)
instruction following
(2)
representation learning
(2)
likelihood ratio
(2)
catastrophic forgetting
(2)
out-of-distribution detection
(2)
domain-adaptive pre-training
(2)
training-free guidance
(2)
autoregressive transformer
(1)
sampling strategy
(1)
image generation
(1)
knowledge transfer
(1)
constrained generation
(1)
weakly supervised learning
(1)
hyperparameter optimization
(1)
domain adaptation
(1)
few-shot learning
(1)
conditional generation
(1)
flow matching
(1)
transfer learning
(1)
Papers
ADA: An Adaptive Augmentation Framework for Single-Source Domain Generalization in Medical Image Segmentation
MICCAI 2025
Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models
AISTATS 2025
GROOT-2: Weakly Supervised Multimodal Instruction Following Agents
ICLR 2025
Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows
ICLR 2025
MCU: An Evaluation Framework for Open-Ended Game Agents
ICML 2025
TFG-Flow: Training-free Guidance in Multimodal Generative Flow
ICLR 2025
Class Incremental Learning via Likelihood Ratio Based Task Prediction
ICLR 2024
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
NeurIPS 2024
Selecting Large Language Model to Fine-tune via Rectified Scaling Law
ICML 2024
TFG: Unified Training-Free Guidance for Diffusion Models
NeurIPS 2024
Continual Pre-training of Language Models
ICLR 2023
FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score
EMNLP 2023
Adapting a Language Model While Preserving its General Knowledge
EMNLP 2022
Continual Training of Language Models for Few-Shot Learning
EMNLP 2022