About

Salman Avestimehr is associated with the vITAL Lab, which focuses on foundational problems in information theory, machine learning, and data sciences. The lab's research directions include trustworthy and scalable federated learning, security and privacy in large-scale distributed systems, transfer learning, and coded computing. His work is centered on advancing understanding and solutions in these key areas of information theory and machine learning, contributing to the development of secure, efficient, and scalable data science methodologies.

Research topics

• Computer science
• Artificial intelligence
• Machine learning
• Distributed computing
• Theoretical computer science

Selected publications

• GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation

  Proceedings of the AAAI Conference on Artificial Intelligence · 2026-03-14

  articleOpen access

  Parameter-efficient fine-tuning (PEFT) has become a popular way to adapt large pre-trained models to new tasks. Most PEFT methods update only a small subset of parameters while freezing the rest, avoiding redundant computation. As they maximize the absolute size of the updates without regard to the parameters’ original scale, the resulting changes in model behavior can be minimal. In contrast, we maximize updates relative to each parameter’s scale, yielding more meaningful downstream adaptation. We propose Gradient-to-Weight Ratio and Entropy-guided Masking (GEM), a parameter scale-aware, distribution-sensitive sparse fine-tuning framework. GEM prioritizes parameters whose updates are significant in proportion to their initial pre-trained values. It also adaptively determines how many parameters to tune at each layer based on the entropy of parameter values, thereby making the most effective use of the computational budget in PEFT. Our empirical study demonstrates the efficacy of GEM on both general-domain tasks (GLUE and SuperGLUE) and domain-specific tasks (GSM8k and MBPP), achieving up to a 1.6% improvement in fine-tuning accuracy over full fine-tuning while updating only 0.1% of model parameters.

  PublisherOA PDFDOI

• Understanding Communication Backends in Cross-Silo Federated Learning

  arXiv (Cornell University) · 2026-04-12

  articleOpen accessSenior author

  Federated learning (FL) has emerged as a practical means for privacy-preserving distributed machine learning. FL's versatile design makes it suitable for various training settings, from IoT edge devices in cross-device FL to powerful servers in cross-silo FL. A key consequence of this versatility is the high level of diversity found in the networking configuration of FL applications. Coupled with the rising demand for large-scale models such as large language models, well-informed selection and configuration of communication backends become crucial for ensuring optimal performance in FL systems. This work focuses on cross-silo federated learning, presenting in-depth benchmarks of various communication backends, including MPI, gRPC, and PyTorch RPC. In addition, we introduce gRPC+S3, a hybrid backend designed to overcome the limitations of existing approaches, particularly for transmitting large models across geo-distributed deployments, achieving up to $3.8\times$ end-to-end speedup over gRPC. Our benchmarks examine point-to-point and end-to-end performance for a broad range of model sizes running under realistic network conditions. Our findings provide practical insights for selecting and configuring suitable communication backends tailored to the specific federated learning tasks and network configurations.

  PublisherOA PDF

• Understanding Communication Backends in Cross-Silo Federated Learning

  arXiv (Cornell University) · 2026-04-12

  preprintOpen accessSenior author

  Federated learning (FL) has emerged as a practical means for privacy-preserving distributed machine learning. FL's versatile design makes it suitable for various training settings, from IoT edge devices in cross-device FL to powerful servers in cross-silo FL. A key consequence of this versatility is the high level of diversity found in the networking configuration of FL applications. Coupled with the rising demand for large-scale models such as large language models, well-informed selection and configuration of communication backends become crucial for ensuring optimal performance in FL systems. This work focuses on cross-silo federated learning, presenting in-depth benchmarks of various communication backends, including MPI, gRPC, and PyTorch RPC. In addition, we introduce gRPC+S3, a hybrid backend designed to overcome the limitations of existing approaches, particularly for transmitting large models across geo-distributed deployments, achieving up to $3.8\times$ end-to-end speedup over gRPC. Our benchmarks examine point-to-point and end-to-end performance for a broad range of model sizes running under realistic network conditions. Our findings provide practical insights for selecting and configuring suitable communication backends tailored to the specific federated learning tasks and network configurations.

  PublisherDOI

• ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models

  arXiv (Cornell University) · 2026-03-20

  preprintOpen access

  Text-to-image diffusion models achieve high visual fidelity but surprisingly exhibit systematic failures in numerical control when prompts specify explicit object counts. To address this limitation, we introduce ATHENA, a model-agnostic, test-time adaptive steering framework that improves object count fidelity without modifying model architectures or requiring retraining. ATHENA leverages intermediate representations during sampling to estimate object counts and applies count-aware noise corrections early in the denoising process, steering the generation trajectory before structural errors become difficult to revise. We present three progressively more advanced variants of ATHENA that trade additional computation for improved numerical accuracy, ranging from static prompt-based steering to dynamically adjusted count-aware control. Experiments on established benchmarks and a new visually and semantically complex dataset show that ATHENA consistently improves count fidelity, particularly at higher target counts, while maintaining favorable accuracy-runtime trade-offs across multiple diffusion backbones.

  PublisherDOI

• Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions

  IEEE BITS the Information Theory Magazine · 2026-01-01

  articleOpen accessSenior author

  The rapid advancement of large language models (LLMs) has transformed the landscape of natural language processing, enabling breakthroughs across a wide range of areas including question answering, machine translation, and text summarization. Yet, their deployment in real-world applications has raised concerns over reliability and trustworthiness, as LLMs remain prone to hallucinations that produce plausible but factually incorrect outputs. Uncertainty quantification (UQ) has emerged as a central research direction to address this issue, offering principled measures for assessing the trustworthiness of model generations. We begin by introducing the foundations of UQ, from its formal definition to the traditional distinction between epistemic and aleatoric uncertainty, and then highlight how these concepts have been adapted to the context of LLMs. Building on this, we examine the role of UQ in hallucination detection, where quantifying uncertainty provides a mechanism for identifying unreliable generations and improving reliability. We systematically categorize a wide spectrum of existing methods along multiple dimensions and present empirical results for several representative approaches. Finally, we discuss current limitations and outline promising future research directions, providing a clearer picture of the current landscape of LLM UQ for hallucination detection.

  PublisherOA PDFDOI

• Reconsidering LLM Uncertainty Estimation Methods in the Wild

  ArXiv.org · 2025-06-01

  preprintOpen access

  Large Language Model (LLM) Uncertainty Estimation (UE) methods have become a crucial tool for detecting hallucinations in recent years. While numerous UE methods have been proposed, most existing studies evaluate them in isolated short-form QA settings using threshold-independent metrics such as AUROC or PRR. However, real-world deployment of UE methods introduces several challenges. In this work, we systematically examine four key aspects of deploying UE methods in practical settings. Specifically, we assess (1) the sensitivity of UE methods to decision threshold selection, (2) their robustness to query transformations such as typos, adversarial prompts, and prior chat history, (3) their applicability to long-form generation, and (4) strategies for handling multiple UE scores for a single query. Our evaluations on 19 UE methods reveal that most of them are highly sensitive to threshold selection when there is a distribution shift in the calibration dataset. While these methods generally exhibit robustness against previous chat history and typos, they are significantly vulnerable to adversarial prompts. Additionally, while existing UE methods can be adapted for long-form generation through various strategies, there remains considerable room for improvement. Lastly, ensembling multiple UE scores at test time provides a notable performance boost, which highlights its potential as a practical improvement strategy. Code is available at: https://github.com/duygunuryldz/uncertainty_in_the_wild.

  PublisherOA PDFDOI

• FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling

  ArXiv.org · 2025-01-22

  preprintOpen accessSenior author

  Graphs are crucial for modeling relational and biological data. As datasets grow larger in real-world scenarios, the risk of exposing sensitive information increases, making privacy-preserving training methods like federated learning (FL) essential to ensure data security and compliance with privacy regulations. Recently proposed personalized subgraph FL methods have become the de-facto standard for training personalized Graph Neural Networks (GNNs) in a federated manner while dealing with the missing links across clients' subgraphs due to privacy restrictions. However, personalized subgraph FL faces significant challenges due to the heterogeneity in client subgraphs, such as degree distributions among the nodes, which complicate federated training of graph models. To address these challenges, we propose \textit{FedGrAINS}, a novel data-adaptive and sampling-based regularization method for subgraph FL. FedGrAINS leverages generative flow networks (GFlowNets) to evaluate node importance concerning clients' tasks, dynamically adjusting the message-passing step in clients' GNNs. This adaptation reflects task-optimized sampling aligned with a trajectory balance objective. Experimental results demonstrate that the inclusion of \textit{FedGrAINS} as a regularizer consistently improves the FL performance compared to baselines that do not leverage such regularization.

  PublisherOA PDFDOI

• Clustering and Median Aggregation Improve Differentially Private Inference

  ArXiv.org · 2025-06-05

  preprintOpen access

  Differentially private (DP) language model inference is an approach for generating private synthetic text. A sensitive input example is used to prompt an off-the-shelf large language model (LLM) to produce a similar example. Multiple examples can be aggregated together to formally satisfy the DP guarantee. Prior work creates inference batches by sampling sensitive inputs uniformly at random. We show that uniform sampling degrades the quality of privately generated text, especially when the sensitive examples concern heterogeneous topics. We remedy this problem by clustering the input data before selecting inference batches. Next, we observe that clustering also leads to more similar next-token predictions across inferences. We use this insight to introduce a new algorithm that aggregates next token statistics by privately computing medians instead of averages. This approach leverages the fact that the median has decreased local sensitivity when next token predictions are similar, allowing us to state a data-dependent and ex-post DP guarantee about the privacy properties of this algorithm. Finally, we demonstrate improvements in terms of representativeness metrics (e.g., MAUVE) as well as downstream task performance. We show that our method produces high-quality synthetic data at significantly lower privacy cost than a previous state-of-the-art method.

  PublisherOA PDFDOI

• CryptoMamba: Leveraging State Space Models for Accurate Bitcoin Price Prediction

  arXiv (Cornell University) · 2025-01-02 · 1 citations

  preprintOpen accessSenior author

  Predicting Bitcoin price remains a challenging problem due to the high volatility and complex non-linear dynamics of cryptocurrency markets. Traditional time-series models, such as ARIMA and GARCH, and recurrent neural networks, like LSTMs, have been widely applied to this task but struggle to capture the regime shifts and long-range dependencies inherent in the data. In this work, we propose CryptoMamba, a novel Mamba-based State Space Model (SSM) architecture designed to effectively capture long-range dependencies in financial time-series data. Our experiments show that CryptoMamba not only provides more accurate predictions but also offers enhanced generalizability across different market conditions, surpassing the limitations of previous models. Coupled with trading algorithms for real-world scenarios, CryptoMamba demonstrates its practical utility by translating accurate forecasts into financial outcomes. Our findings signal a huge advantage for SSMs in stock and cryptocurrency price forecasting tasks.

  PublisherOA PDFDOI

• Supervised Learning for Analog and RF Circuit Design: Benchmarks and Comparative Insights

  ArXiv.org · 2025-01-21

  preprintOpen accessSenior author

  Automating analog and radio-frequency (RF) circuit design using machine learning (ML) significantly reduces the time and effort required for parameter optimization. This study explores supervised ML-based approaches for designing circuit parameters from performance specifications across various circuit types, including homogeneous and heterogeneous designs. By evaluating diverse ML models, from neural networks like transformers to traditional methods like random forests, we identify the best-performing models for each circuit. Our results show that simpler circuits, such as low-noise amplifiers, achieve exceptional accuracy with mean relative errors as low as 0.3% due to their linear parameter-performance relationships. In contrast, complex circuits, like power amplifiers and voltage-controlled oscillators, present challenges due to their non-linear interactions and larger design spaces. For heterogeneous circuits, our approach achieves an 88% reduction in errors with increased training data, with the receiver achieving a mean relative error as low as 0.23%, showcasing the scalability and accuracy of the proposed methodology. Additionally, we provide insights into model strengths, with transformers excelling in capturing non-linear mappings and k-nearest neighbors performing robustly in moderately linear parameter spaces, especially in heterogeneous circuits with larger datasets. This work establishes a foundation for extending ML-driven design automation, enabling more efficient and scalable circuit design workflows.

  PublisherOA PDFDOI

Frequent coauthors

• Murali Annavaram

  60 shared

• Chaoyang He

  57 shared

• Songze Li

  35 shared

• Mahdi Soltanolkotabi

  27 shared

• Zhifeng Lin

  Fuzhou University

  26 shared

• Yahya H. Ezzeldin

  22 shared

• Krishna Giri Narra

  22 shared

• Ahmed Roushdy Elkordy

  21 shared

Awards & honors

• The 2019 IEEE Information Theory Society James L. Massey Res…
• an Information Theory Society and Communication Society Join…
• a Presidential Early Career Award for Scientists and Enginee…
• a Young Investigator Program (YIP) award from the U. S. Air…
• a National Science Foundation CAREER award