Salman Avestimehr
29 papers · 2017–2026 · 9 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (48) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Grand Slam
π₯
Mega-Team Β· Squad
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
π
Renaissance Researcher
(5)
π
Trend Setter
ποΈ
Keyword Collector
(137)
Top co-authors
Research topics
Machine Learning
(27)
Artificial Intelligence
(21)
Core AI
(14)
Deep Learning
(13)
Optimization & Theory Β· Machine Learning
(13)
Application Areas
(12)
Learning Paradigms Β· Artificial Intelligence
(10)
Learning Types Β· Machine Learning
(10)
Natural Language Processing
(7)
Optimization & Theory Β· Deep Learning
(6)
Resources & Methods
(6)
Learning Paradigms Β· Machine Learning
(5)
Learning Types Β· Deep Learning
(5)
Architectures
(3)
Models
(3)
Keywords
federated learning
(10)
large language model
(6)
uncertainty estimation
(4)
uncertainty quantification
(3)
model compression
(3)
catastrophic forgetting
(3)
generative model
(3)
distributed training
(3)
non-iid data
(2)
edge computing
(2)
token probability
(2)
text classification
(2)
personalized model
(2)
convolutional neural network
(2)
parameter-efficient fine-tuning
(2)
question answering
(2)
knowledge distillation
(2)
distributed learning
(2)
privacy-preserving machine learning
(2)
class-incremental learning
(2)
Papers
GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation
AAAI 2026
Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding
ACL 2025
Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs
NAACL 2025
MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines
EMNLP 2025
Reconsidering LLM Uncertainty Estimation Methods in the Wild
ACL 2025
TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs
EMNLP 2025
All Rivers Run to the Sea: Private Learning with Asymmetric Flows
CVPR 2024
CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning
ECCV 2024
Ethos: Rectifying Language Models in Orthogonal Parameter Space
NAACL 2024
Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
ICLR 2024
MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
ACL 2024
Revisiting OPRO: The Limitations of Small-Scale LLMs as Optimizers
ACL 2024
ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency
EMNLP 2024
TensorOpera Router: A Multi-Model Router for Efficient LLM Inference
EMNLP 2024
A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks
NeurIPS 2023
The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning
CVPR 2023
ActPerFL: Active Personalized Federated Learning
ACL 2022
Federated Learning with Noisy User Feedback
NAACL 2022
FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks
NAACL 2022
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
NeurIPS 2022
Self-Aware Personalized Federated Learning
NeurIPS 2022
SpreadGNN: Decentralized Multi-Task Federated Learning for Graph Neural Networks on Molecular Data
AAAI 2022
PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models
ICML 2021
A Scalable Approach for Privacy-Preserving Collaborative Machine Learning
NeurIPS 2020
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
NeurIPS 2020
Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks
NeurIPS 2020
GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training
NeurIPS 2018
Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training
NeurIPS 2018
Polynomial Codes: an Optimal Design for High-Dimensional Coded Matrix Multiplication
NeurIPS 2017