Hongxiang Fan
5 papers · 2024–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
Venues
Top co-authors
Research topics
Machine Learning
(5)
Artificial Intelligence
(4)
Application Areas
(4)
Core AI
(3)
Deep Learning
(2)
Learning Paradigms · Artificial Intelligence
(2)
Optimization & Theory · Deep Learning
(2)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Learning Paradigms · Machine Learning
(1)
Learning Types
(1)
Optimization
(1)
Optimization & Theory · Machine Learning
(1)
Resources & Methods
(1)
Keywords
model merging
(2)
federated learning
(2)
multi-task learning
(1)
knowledge distillation
(1)
cross-lingual transfer
(1)
constrained optimization
(1)
continuous optimization
(1)
model inference
(1)
low-resource language
(1)
memory efficiency
(1)
data selection
(1)
parameter-efficient fine-tuning
(1)
training dynamics
(1)
data quality
(1)
inference optimization
(1)
speculative decoding
(1)
prompt tuning
(1)
mixed precision
(1)
parallel decoding
(1)
hardware optimization
(1)
Papers
FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization
ICCV 2025
Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference
EMNLP 2025
Progressive Mixed-Precision Decoding for Efficient LLM Inference
ICLR 2025
Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
ICLR 2024
CLUES: Collaborative Private-domain High-quality Data Selection for LLMs via Training Dynamics
NeurIPS 2024