Ermo Hua
10 papers · 2024–2026 · 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 ↓+5 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (31) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🤝 Dynamic Duo (10)
🏆
Grand Slam
⚡
Prolific Year · Productive
❓
The Questioner
💎
Century Club · Bronze
🗃️
Keyword Collector
(57)
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(8)
Machine Learning
(7)
Deep Learning
(5)
Natural Language Processing
(4)
Optimization & Theory
(4)
Application Areas
(3)
Learning Types · Deep Learning
(3)
Healthcare & Medicine
(2)
Clinical
(2)
Generation
(2)
Learning Types · Machine Learning
(2)
Computer Vision
(1)
Applications · Natural Language Processing
(1)
Applications · Computer Vision
(1)
Keywords
language model
(3)
large language model
(2)
reward model
(2)
preference optimization
(2)
instruction following
(2)
reinforcement learning from human feedback
(2)
supervised fine-tuning
(2)
question answering
(1)
attention mechanism
(1)
efficient training
(1)
language model alignment
(1)
policy learning
(1)
markov decision process
(1)
magnetic resonance imaging
(1)
preference learning
(1)
model collapse
(1)
multimodal learning
(1)
scalable training
(1)
biomedical domain
(1)
visual question answering
(1)
Papers
Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism
ACL 2026
Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization
ICML 2025
How to Synthesize Text Data without Model Collapse?
ICML 2025
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process
ACL 2025
MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
ICML 2025
OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees
ICLR 2025
Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines
AAAI 2025
CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
ACL 2024
Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention
EMNLP 2024
UltraMedical: Building Specialized Generalists in Biomedicine
NeurIPS 2024