← Authors

Salman Avestimehr

29 papers · 2017–2026 · 9 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (7) 🐝 Cross-Pollinator (14) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (9) πŸƒ Academic Marathon (8) πŸ—ΊοΈ Taxonomy Completionist (52) πŸ‘₯ Mega-Team (24) πŸ† Grand Slam πŸ† Keyword Champion (2) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (6) πŸ’Ž Century Club (28) πŸ—ƒοΈ Keyword Collector (130) ⚑ Prolific Year (5)

Conferences

NIPS (9) ACL (5) EMNLP (4) NAACL (4) AAAI (2) CVPR (2) ECCV (1) ICLR (1) ICML (1)

Top co-authors

Chaoyang He (8) Yavuz Faruk Bakman (6) Duygu Nur Yaldiz (6) Murali Annavaram (5) Mahdi Soltanolkotabi (4) Sungmin Kang (3) Yue Niu (3) Jie Ding (3) Tuo Zhang (3) Chenyang Tao (3)

Research topics

Differential Privacy (1)

Keywords

federated learning (9) large language model (6) uncertainty estimation (4) distributed training (3) uncertainty quantification (3) model compression (3) generative model (3) bayesian hierarchical model (2) non-iid datum (2) decentralized training (2) text classification (2) edge computing (2) personalized model (2) token probability (2) parameter-efficient fine-tuning (2) question answering (2) knowledge distillation (2) distributed learning (2) privacy-preserving machine learning (2) convolutional neural network (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
Reconsidering LLM Uncertainty Estimation Methods in the Wild ACL 2025
MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines EMNLP 2025
TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs EMNLP 2025
Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs NAACL 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
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
Ethos: Rectifying Language Models in Orthogonal Parameter Space NAACL 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
Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning ICLR 2024
The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning CVPR 2023
A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks NIPS 2023
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings NIPS 2022
Self-Aware Personalized Federated Learning NIPS 2022
SpreadGNN: Decentralized Multi-Task Federated Learning for Graph Neural Networks on Molecular Data AAAI 2022
ActPerFL: Active Personalized Federated Learning ACL 2022
FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks NAACL 2022
Federated Learning with Noisy User Feedback NAACL 2022
PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models ICML 2021
Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks NIPS 2020
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge NIPS 2020
A Scalable Approach for Privacy-Preserving Collaborative Machine Learning NIPS 2020
GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training NIPS 2018
Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training NIPS 2018
Polynomial Codes: an Optimal Design for High-Dimensional Coded Matrix Multiplication NIPS 2017