Liam Collins
8 papers · 2020–2026 · 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (27) 🐣 Hot Topic Early Bird
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(7)
Artificial Intelligence
(5)
Core Methods
(5)
Optimization & Theory
(5)
Learning Paradigms · Artificial Intelligence
(4)
Learning Types · Machine Learning
(4)
Deep Learning
(3)
Learning Paradigms · Machine Learning
(3)
Architectures
(2)
Learning Types · Deep Learning
(2)
Natural Language Processing
(1)
Application Areas
(1)
Core AI
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
representation learning
(4)
few-shot learning
(2)
multi-task learning
(2)
unsupervised learning
(1)
neural network optimization
(1)
worst-case performance
(1)
contrastive learning
(1)
in-context learning
(1)
information retrieval
(1)
distributed learning
(1)
multi-task regression
(1)
feature representation
(1)
self-supervised learning
(1)
local updates
(1)
federated learning
(1)
heterogeneous data
(1)
text embedding
(1)
regression task
(1)
non-i.i.d. data
(1)
model-agnostic meta-learning
(1)
Papers
Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings
ACL 2026
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
NeurIPS 2024
Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
ICML 2024
InfoNCE Loss Provably Learns Cluster-Preserving Representations
COLT 2023
FedAvg with Fine Tuning: Local Updates Lead to Representation Learning
NeurIPS 2022
MAML and ANIL Provably Learn Representations
ICML 2022
Exploiting Shared Representations for Personalized Federated Learning
ICML 2021
Task-Robust Model-Agnostic Meta-Learning
NeurIPS 2020