Avi Schwarzschild

schwarzschild's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 28 days ago

Has My System Prompt Been Used? Large Language Model Prompt Membership Inference

Paper • 2502.09974 • Published Feb 14 • 10

upvoted 2 papers about 2 months ago

Gemstones: A Model Suite for Multi-Faceted Scaling Laws

Paper • 2502.06857 • Published Feb 7 • 25

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 136

authored a paper 9 months ago

Benchmarking ChatGPT on Algorithmic Reasoning

Paper • 2404.03441 • Published Apr 4, 2024

updated a dataset 9 months ago

schwarzschild/fictitious-qa

Updated Jul 2, 2024 • 4

upvoted a paper 11 months ago

Transformers Can Do Arithmetic with the Right Embeddings

Paper • 2405.17399 • Published May 27, 2024 • 54

authored a paper 11 months ago

Transformers Can Do Arithmetic with the Right Embeddings

Paper • 2405.17399 • Published May 27, 2024 • 54

authored 3 papers 12 months ago

Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Paper • 2309.00614 • Published Sep 1, 2023 • 2

Universal Guidance for Diffusion Models

Paper • 2302.07121 • Published Feb 14, 2023

Rethinking LLM Memorization through the Lens of Adversarial Compression

Paper • 2404.15146 • Published Apr 23, 2024

authored 4 papers about 1 year ago

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

Paper • 2401.12070 • Published Jan 22, 2024 • 45

A Cookbook of Self-Supervised Learning

Paper • 2304.12210 • Published Apr 24, 2023 • 3

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Paper • 2310.05914 • Published Oct 9, 2023 • 14

TOFU: A Task of Fictitious Unlearning for LLMs

Paper • 2401.06121 • Published Jan 11, 2024 • 21