Homepage

I am a member of technical staff at Microsoft Research working on language models.

Before, my research was mostly focused on sampling, optimization and proximal methods. Here is a paper at the intersection of these topics.

CV

News

• We released phi-4.

• I co-organize a Machine Learning Summer School (MLSS) in Senegal in 2025. Please apply! MLSS 2025.

• I am a workshop chair at NeurIPS 2024.

• Anna Korba and I have presented a tutorial on Sampling as Optimization at ICML 2022. Here are our slides. You can watch the video here.

Some papers

LLMs

• Marah Abdin et al., “Phi-4 Technical Report”, December 2024.

• Marah Abdin et al., “Phi-3 Technical Report”, April 2024.

• Suriya Gunasekar, Yi Zhang et al., “Textbooks Are All You Need”, June 2023.

Diffusion models and sampling

• Sitan Chen, Sinho Chewi, Holden Lee, Yuanzhi Li, Jianfeng Lu and Adil Salim, “The probability flow ODE is provably fast”, NeurIPS 2023.

• Sitan Chen, Sinho Chewi, Jerry Li, Yuanzhi Li, Adil Salim and Anru R. Zhang, “Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions”, Notable top 5% paper @ ICLR 2023, Kigali, Rwanda.

• Adil Salim, Lukang Sun, Peter Richtárik, “A Convergence Theory for SVGD in the Population Limit under Talagrand’s Inequality T1”, ICML 2022.

• Anna Korba, Adil Salim, Michael Arbel, Giulia Luise and Arthur Gretton, “A Non-Asymptotic Analysis for Stein Variational Gradient Descent”, NeurIPS 2020.

Proximal methods in optimization and sampling

• Michael Diao, Krishnakumar Balasubramanian, Sinho Chewi, Adil Salim, “Forward-Backward Gaussian Variational Inference via JKO in the Bures–Wasserstein Space”, ICML 2023.

• Yongxin Chen, Sinho Chewi, Adil Salim, Andre Wibisono, “Improved analysis for a proximal algorithm for sampling”, COLT 2022.

• Adil Salim, Laurent Condat, Dmitry Kovalev and Peter Richtárik, “An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints”, AISTATS 2022.

• Adil Salim and Peter Richtárik, “Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm”, NeurIPS 2020.

• Dmitry Kovalev, Adil Salim and Peter Richtárik, “Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization”, NeurIPS 2020.

• Adil Salim, Anna Korba and Giulia Luise, “The Wasserstein Proximal Gradient Algorithm”, NeurIPS 2020.