Fangyuan Li
8 papers · 2016–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (10) πΊοΈ Taxonomy Completionist (19) π§ Keyword Pioneer π Conference Polyglot (6) π Academic Marathon (9)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
β‘
Prolific Year
(5)
β
The Questioner
Conferences
ACL (3)
AAAI (1)
COLING (1)
CVPR (1)
EMNLP (1)
ICCV (1)
Top co-authors
Keywords
reinforcement learning
(2)
model compression
(2)
cross-lingual nlp
(1)
model merging
(1)
multimodal large language model
(1)
neural network optimization
(1)
memory efficiency
(1)
task vector
(1)
language model
(1)
gradient approximation
(1)
tree search
(1)
reward shaping
(1)
credit assignment
(1)
edge computing
(1)
code generation
(1)
mobile deployment
(1)
parameter-efficient finetuning
(1)
key-value cache
(1)
binary neural network
(1)
benchmark evaluation
(1)
Papers
MARS2: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
ACL 2026
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
ACL 2026
Less is More: Efficient Model Merging with Binary Task Switch
CVPR 2025
Fast and Slow Gradient Approximation for Binary Neural Network Optimization
AAAI 2025
GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices
ICCV 2025
SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?
EMNLP 2025
EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices
ACL 2025
Learning Event Expressions via Bilingual Structure Projection
COLING 2016