Skip to content

Author

Salman Avestimehr

We have 5 of 77 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Aligned Data Can Induce Misalignment via Context Confusion

It is argued that it is difficult to predict the alignment state of a model after training by inspecting the training data alone, which highlights the importance of comprehensive post-training alignment evaluations.

Yavuz Faruk Bakman, D. Yaldiz, Baris Askin et al. · 1 citation
Preprint Aug 2026

Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms

This paper derives closed-form optimal transforms for keys and values from calibration statistics, under a high-resolution model, and shows that the optimal key transform is not orthogonal and satisfies a generalized Parseval relation: the attention-aware distortion becomes mean-squared error in the transform domain.

Samuel Fernández-Menduiña, Amir Ziashahabi, Eduardo Pavez et al. · 2 citations
#machine learning Preprint Sep 2026

Decoding Extrahepatic Targeting of Lipid Nanoparticles with Interpretable Machine Learning

An interpretable machine learning framework is developed to predict hepatic versus extrahepatic LNP accumulation and identify molecular design rules for extrahepatic RNA delivery and provides actionable design principles for engineering LNPs beyond the liver.

Asal Mehradfar, M. Sepehri, Owen Antholine et al. · 0 citations
#machine learning Preprint Sep 2026

ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference

This work proposes ASPIRE, a non-synchronized batched self-speculative decoding framework built on three components, which achieves speedup in decoding throughput over autoregressive baselines and improves average speedup by approximately $27\% over the strongest prior self-speculative baselines.

Amir Ziashahabi, Hossein Entezari Zarch, Lei Gao et al. · 1 citation
Book Open access Aug 2026

FedKDD/FedMAS 2026: The 2026 International Joint Workshop on Federated Learning for Multi-agent Systems and Data Mining

This workshop seeks to bring together researchers and practitioners from academia and industry to explore the convergence of federated learning and multi-agent systems, with a focus on scalability, trustworthiness, adaptive coordination, and the broader societal impact of federated multi-agent intelligence.

Hao-Zhao Wang, Zhuangdi Zhu, Zheng Xu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.