Author

Ali Abbasi

h-index 6 View on Semantic Scholar

We have 3 of 22 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.

#machine learning Feb 2026

Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression

Zero Sum SVD (ZS-SVD) is proposed, a post-training method that performs global singular component selection using activation whitening and first-order calibration loss estimates in whitened coordinates, automatically yielding heterogeneous ranks without solving a rank allocation optimization.

Ali Abbasi, Chayne Thrash, Hao-Ran Qin et al. · arXiv.org · 9 citations · ⚡1

#machine learning Preprint Sep 2026

BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding

Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferring model weights from accelerator high-bandwidth memory into on-chip SRAM. Mixture-of-experts (MoE) models reduce computation by activating only a small subset of experts...

Ali Abbasi, Justin Shi, Soheil Kolouri · 0 citations

Preprint Aug 2026

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

CircuitSteer is introduced, a novel framework that leverages Sparse Autoencoders (SAEs) to identify and manipulate coherent semantic circuits distributed across multiple layers that yields strictly more robust and effective behavioral control than static single-point interventions.

Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad et al. · 1 citation