PPaperPicks

Dan Alistarh

IST Austria, Klosterneuburg, Austria

33 papers at tracked venues · 25 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-3650-940X ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×9ICML ×8ICLR ×6AISTATS ×2EMNLP ×2MLSys ×2AAAI ×1ACL ×1EACL ×1NAACL ×1

Frequent coauthors

Elias Frantar
×8
Denis Kuznedelev
×7
Eldar Kurtic
×5
Vage Egiazarian
×5
Mahdi Nikdan
×5
Saleh Ashkboos
×5
Andrei Panferov
×5
Mher Safaryan
×5
Ionut-Vlad Modoranu
×5
Torsten Hoefler
×4
Ilia Markov
×4
Vladimir Malinovskii
×3

Papers

  1. Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks
    EACL 2026 ·
    Sergey Pankratov
    , Dan Alistarh
  2. "Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
    ACL 2025 ·
    Eldar Kurtic
    ,
    Alexandre Noll Marques
    ,
    Shubhra Pandit
    ,
    Mark Kurtz
    , Dan Alistarh
  3. Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models
    ICML 2025 ·
    Alina Shutova
    ,
    Vladimir Malinovskii
    ,
    Vage Egiazarian
    ,
    Denis Kuznedelev
    ,
    Denis Mazur
    ,
    Nikita Surkov
    ,
    Ivan Ermakov
    , Dan Alistarh
  4. Efficient Data Selection at Scale via Influence Distillation
    NeurIPS 2025 ·
    Mahdi Nikdan
    ,
    Vincent Cohen-Addad
    , Dan Alistarh,
    Vahab Mirrokni
  5. EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
    ICML 2025 ·
    Oliver Sieberling
    ,
    Denis Kuznedelev
    ,
    Eldar Kurtic
    , Dan Alistarh
  6. HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
    NeurIPS 2025 ·
    Saleh Ashkboos
    ,
    Mahdi Nikdan
    ,
    Rush Tabesh
    ,
    Roberto L. Castro
    ,
    Torsten Hoefler
    , Dan Alistarh
  7. HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
    NAACL 2025 ·
    Vladimir Malinovskii
    ,
    Andrei Panferov
    ,
    Ivan Ilin
    ,
    Han Guo
    ,
    Peter Richtárik
    , Dan Alistarh
  8. Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
    NeurIPS 2025 ·
    Gleb Rodionov
    ,
    Roman Garipov
    ,
    Alina Shutova
    ,
    George Yakushev
    ,
    Erik Schultheis
    ,
    Vage Egiazarian
    ,
    Anton Sinitsin
    ,
    Denis Kuznedelev
    , Dan Alistarh
  9. Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence
    AAAI 2025 ·
    Shayan Talaei
    ,
    Matin Ansaripour
    ,
    Giorgi Nadiradze
    , Dan Alistarh
  10. LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics
    ICLR 2025 ·
    Thomas Robert
    ,
    Mher Safaryan
    ,
    Ionut-Vlad Modoranu
    , Dan Alistarh
  11. Layer-wise Quantization for Quantized Optimistic Dual Averaging
    ICML 2025 ·
    Anh Duc Nguyen
    ,
    Ilia Markov
    ,
    Frank Zhengqing Wu
    ,
    Ali Ramezani-Kebrya
    ,
    Kimon Antonakopoulos
    , Dan Alistarh,
    Volkan Cevher
  12. QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
    ICML 2025 ·
    Andrei Panferov
    ,
    Jiale Chen
    ,
    Soroush Tabesh
    ,
    Mahdi Nikdan
    , Dan Alistarh
  13. Quartet: Native FP4 Training Can Be Optimal for Large Language Models
    NeurIPS 2025 ·
    Roberto L. Castro
    ,
    Andrei Panferov
    ,
    Rush Tabesh
    ,
    Oliver Sieberling
    ,
    Jiale Chen
    ,
    Mahdi Nikdan
    ,
    Saleh Ashkboos
    , Dan Alistarh
  14. Scalable Mechanistic Neural Networks
    ICLR 2025 ·
    Jiale Chen
    ,
    Dingling Yao
    ,
    Adeel Pervez
    , Dan Alistarh,
    Francesco Locatello
  15. The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
    ICLR 2025 ·
    Tian Jin
    ,
    Ahmed Imtiaz Humayun
    ,
    Utku Evci
    ,
    Suvinay Subramanian
    ,
    Amir Yazdanbakhsh
    , Dan Alistarh,
    Gintare Karolina Dziugaite
  16. Unified Scaling Laws for Compressed Representations
    NeurIPS 2025 ·
    Andrei Panferov
    ,
    Alexandra Volkova
    ,
    Ionut-Vlad Modoranu
    ,
    Vage Egiazarian
    ,
    Mher Safaryan
    , Dan Alistarh
  17. Wasserstein Distances, Neuronal Entanglement, and Sparsity
    ICLR 2025 ·
    Shashata Sawmya
    ,
    Linghao Kong
    ,
    Ilia Markov
    , Dan Alistarh,
    Nir Shavit
  18. AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms
    AISTATS 2024 ·
    Rustem Islamov
    ,
    Mher Safaryan
    , Dan Alistarh
  19. Communication-Efficient Federated Learning With Data and Client Heterogeneity
    AISTATS 2024 ·
    Hossein Zakerinia
    ,
    Shayan Talaei
    ,
    Giorgi Nadiradze
    , Dan Alistarh
  20. Error Feedback Can Accurately Compress Preconditioners
    ICML 2024 ·
    Ionut-Vlad Modoranu
    ,
    Aleksei Kalinov
    ,
    Eldar Kurtic
    ,
    Elias Frantar
    , Dan Alistarh
  21. Extreme Compression of Large Language Models via Additive Quantization
    ICML 2024 ·
    Vage Egiazarian
    ,
    Andrei Panferov
    ,
    Denis Kuznedelev
    ,
    Elias Frantar
    ,
    Artem Babenko
    , Dan Alistarh
  22. L-GreCo: Layerwise-adaptive Gradient Compression For Efficient Data-parallel Deep Learning
    MLSys 2024 ·
    Ilia Markov
    ,
    Kaveh Alim
    ,
    Elias Frantar
    , Dan Alistarh
  23. Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models
    EMNLP 2024 ·
    Eldar Kurtic
    ,
    Amir Moeini
    , Dan Alistarh
  24. MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
    NeurIPS 2024 ·
    Ionut-Vlad Modoranu
    ,
    Mher Safaryan
    ,
    Grigory Malinovsky
    ,
    Eldar Kurtic
    ,
    Thomas Robert
    ,
    Peter Richtárik
    , Dan Alistarh
  25. PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
    NeurIPS 2024 ·
    Vladimir Malinovskii
    ,
    Denis Mazur
    ,
    Ivan Ilin
    ,
    Denis Kuznedelev
    ,
    Konstantin Burlachenko
    ,
    Kai Yi
    , Dan Alistarh,
    Peter Richtárik
  26. QMoE: Sub-1-Bit Compression of Trillion Parameter Models
    MLSys 2024 ·
    Elias Frantar
    , Dan Alistarh
  27. QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models
    EMNLP 2024 ·
    Saleh Ashkboos
    ,
    Ilia Markov
    ,
    Elias Frantar
    ,
    Tingxuan Zhong
    ,
    Xincheng Wang
    ,
    Jie Ren
    ,
    Torsten Hoefler
    , Dan Alistarh
  28. QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
    NeurIPS 2024 ·
    Saleh Ashkboos
    ,
    Amirkeivan Mohtashami
    ,
    Maximilian L. Croci
    ,
    Bo Li
    ,
    Pashmina Cameron
    ,
    Martin Jaggi
    , Dan Alistarh,
    Torsten Hoefler
    ,
    James Hensman
  29. RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation
    ICML 2024 ·
    Mahdi Nikdan
    ,
    Soroush Tabesh
    ,
    Elvir Crncevic
    , Dan Alistarh
  30. SPADE: Sparsity-Guided Debugging for Deep Neural Networks
    ICML 2024 ·
    Arshia Soltani Moakhar
    ,
    Eugenia Iofinova
    ,
    Elias Frantar
    , Dan Alistarh
  31. Scaling Laws for Sparsely-Connected Foundation Models
    ICLR 2024 ·
    Elias Frantar
    ,
    Carlos Riquelme Ruiz
    ,
    Neil Houlsby
    , Dan Alistarh,
    Utku Evci
  32. SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
    ICLR 2024 ·
    Tim Dettmers
    ,
    Ruslan Svirschevski
    ,
    Vage Egiazarian
    ,
    Denis Kuznedelev
    ,
    Elias Frantar
    ,
    Saleh Ashkboos
    ,
    Alexander Borzunov
    ,
    Torsten Hoefler
    , Dan Alistarh
  33. The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
    NeurIPS 2024 ·
    Diyuan Wu
    ,
    Ionut-Vlad Modoranu
    ,
    Mher Safaryan
    ,
    Denis Kuznedelev
    , Dan Alistarh