collaborators

7 papers

cs.LG2025

Sculpting Latent Spaces With MMD: Disentanglement With Programmable Priors

Quentin Fruytier, Akshay Malhotra, Shahab Hamidi-Rad +3

Learning disentangled representations, where distinct factors of variation are captured by independent latent variables, is a central goal in machine learning. The dominant approac…

cs.CL2025

Enabling Approximate Joint Sampling in Diffusion LMs

Parikshit Bansal, Sujay Sanghavi

In autoregressive language models, each token is sampled by conditioning on all the past tokens; the overall string has thus been sampled from the correct underlying joint distribu…

cs.CL2025

SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs

Jiacheng Lin, Zhongruo Wang, Kun Qian +14

Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their gene…

cs.LG2025

Context-Free Synthetic Data Mitigates Forgetting

Parikshit Bansal, Sujay Sanghavi

Fine-tuning a language model often results in a degradation of its existing performance on other tasks, due to a shift in the model parameters; this phenomenon is often referred to…

cs.LG2025

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

Sunny Sanyal, Hayden Prairie, Rudrajit Das +2

Fine-tuning a pre-trained model on a downstream task often degrades its original capabilities, a phenomenon known as "catastrophic forgetting". This is especially an issue when one…

cs.LG2024

Learning Mixtures of Experts with EM: A Mirror Descent Perspective

Quentin Fruytier, Aryan Mokhtari, Sujay Sanghavi

Classical Mixtures of Experts (MoE) are Machine Learning models that involve partitioning the input space, with a separate "expert" model trained on each partition. Recently, MoE-b…