Shuyang Yu
9 papers · 2023–2026 · 7 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (28) 🏆 Grand Slam 🏆 Keyword Champion (2)
🗃️
Keyword Collector
(50)
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(6)
Application Areas
(6)
Deep Learning
(5)
Learning Paradigms · Artificial Intelligence
(4)
Learning Types · Machine Learning
(4)
Learning Types · Deep Learning
(3)
Optimization & Theory
(3)
Natural Language Processing
(2)
Core AI
(2)
Applications
(1)
Core Methods
(1)
Learning Paradigms · Machine Learning
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
model merging
(4)
model compression
(3)
transfer learning
(3)
backdoor attack
(2)
knowledge fusion
(2)
out-of-distribution detection
(2)
parameter sharing
(1)
domain generalization
(1)
reinforcement learning
(1)
question answering
(1)
in-context learning
(1)
neural network optimization
(1)
model security
(1)
model pruning
(1)
knowledge transfer
(1)
monte carlo tree search
(1)
parameter optimization
(1)
data heterogeneity
(1)
language model
(1)
uncertainty quantification
(1)
Papers
ToC: Tree-of-Claims Search with Multi-Agent Language Models
AAAI 2026
Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs
NAACL 2025
Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer
ACL 2025
To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Merging
EMNLP 2025
Knowledge Fusion By Evolving Weights of Language Models
ACL 2024
Parameter Competition Balancing for Model Merging
NeurIPS 2024
Safe and Robust Watermark Injection with a Single OoD Image
ICLR 2024
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
ICML 2023
Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection
ICLR 2023