Sachin Goyal

7

Papers

332

Total Citations

Papers (7)

Think before you speak: Training Language Models With Pause Tokens

Scaling Laws for Data Filtering— Data Curation cannot be Compute Agnostic

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

Overtrained Language Models Are Harder to Fine-Tune

Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance

Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models

Test Time Adaptation via Conjugate Pseudo-labels