most citedIs Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data

12 citations · 12 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG2026

Aurora: A Leverage-Aware Spectral Optimizer

Alec Dewulf, Dhruv Pai, Li Yang +2

We show that for tall matrix parameters, like projection matrices in the MLP layers, the Muon update can have row norms that are arbitrarily non-uniform. This can lead to a self-re…

cs.LG2026

Parallax: Parameterized Local Linear Attention for Language Modeling

Yifei Zuo, Dhruv Pai, Zhichen Zeng +3

Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remained structurally unchanged. Loc…

cs.LG2026

PreFT: Prefill-only finetuning for efficient inference

Andrew Lanpouthakoun, Aryaman Arora, Zhengxuan Wu +4

Large language models can now be personalised efficiently at scale using parameter efficient finetuning methods (PEFTs), but serving user-specific PEFTs harms throughput, even with…

cs.LG2024

Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations

Rylan Schaeffer, Victor Lecomte, Dhruv Bhandarkar Pai +10

Maximum Manifold Capacity Representations (MMCR) is a recent multi-view self-supervised learning (MVSSL) method that matches or surpasses other leading MVSSL methods. MMCR is intri…

cs.LG202412 cited

Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data

Matthias Gerstgrasser, Rylan Schaeffer, Apratim Dey +11

The proliferation of generative models, combined with pretraining on web-scale data, raises a timely question: what happens when these models are trained on their own generated out…

cs.LG2024

Bridging Associative Memory and Probabilistic Modeling

Rylan Schaeffer, Nika Zahedi, Mikail Khona +9

Associative memory and probabilistic modeling are two fundamental topics in artificial intelligence. The first studies recurrent neural networks designed to denoise, complete and r…