Binhang Yuan
13 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (4) π Cross-Pollinator (7)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(26)
π
Century Club
(13)
Conferences
ICML (7)
NIPS (3)
ICLR (2)
ACL (1)
Top co-authors
Keywords
model compression
(4)
large language model
(3)
distributed learning
(3)
foundation model
(2)
language model
(2)
communication compression
(2)
inference optimization
(2)
model merging
(1)
distributed machine learning
(1)
stochastic gradient descent
(1)
distributed training
(1)
batch processing
(1)
gradient compression
(1)
sparse approximation
(1)
in-context learning
(1)
model convergence
(1)
parameter efficient
(1)
relational database
(1)
mixture of expert
(1)
model parallelism
(1)
Papers
DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
ICLR 2025
HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment
ICLR 2025
Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration
ACL 2025
Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
ICML 2025
HexGen: Generative Inference of Large Language Model over Heterogeneous Environment
ICML 2024
$\texttt{Model-GLUE}$: Democratized LLM Scaling for A Large Model Zoo in the Wild
NIPS 2024
Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training
ICML 2024
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
ICML 2023
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
ICML 2023
Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning
ICML 2023
CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks
ICML 2023
Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees
NIPS 2022
Decentralized Training of Foundation Models in Heterogeneous Environments
NIPS 2022