Jonas Geiping

JonasGeiping's activity

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

upvoted a paper 5 days ago

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence

Paper • 2511.07384 • Published 7 days ago • 15

upvoted a collection 6 days ago

Retrofitting Recurrence

Collection

40 items • Updated 6 days ago • 6

upvoted 2 papers about 1 month ago

Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models

Paper • 2510.14961 • Published Oct 16 • 7

Training Dynamics Impact Post-Training Quantization Robustness

Paper • 2510.06213 • Published Oct 7 • 3

upvoted a paper about 2 months ago

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM

Paper • 2509.18058 • Published Sep 22 • 12

upvoted 2 papers 2 months ago

FAST: Factorizable Attention for Speeding up Transformers

Paper • 2402.07901 • Published Feb 12, 2024 • 3

DynaGuard: A Dynamic Guardrail Model With User-Defined Policies

Paper • 2509.02563 • Published Sep 2 • 20

upvoted a collection 5 months ago

answer-matching

Collection

Free-form datasets, human annotations, and sample-level model outputs for "Answer Matching Outperforms Multiple Choice for Language Model Evaluation" • 2 items • Updated Jul 3 • 2

upvoted 3 papers 5 months ago

Answer Matching Outperforms Multiple Choice for Language Model Evaluation

Paper • 2507.02856 • Published Jul 3 • 8

GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching

Paper • 2506.20480 • Published Jun 25 • 7

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

Paper • 2506.05523 • Published Jun 5 • 34

upvoted a paper 6 months ago

Zero-Shot Vision Encoder Grafting via LLM Surrogates

Paper • 2505.22664 • Published May 28 • 7

upvoted a paper 8 months ago

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

Paper • 2502.09974 • Published Feb 14 • 9

upvoted 2 papers 9 months ago

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation

Paper • 2502.19414 • Published Feb 26 • 20

Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving

Paper • 2502.07640 • Published Feb 11 • 10

upvoted 2 collections 9 months ago

Recurrent Models

Collection

These are checkpoints for recurrent LLMs developed to scale test-time compute by recurring in latent space. • 15 items • Updated May 21 • 11

Gemstone Models

Collection

Our 22 open source Gemstone models for scaling laws range from 50M to 2B parameters, spanning 11 widths from 256 to 3072 and 18 depths from 3 to 80. • 69 items • Updated Jul 4 • 10

upvoted 3 papers 9 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 • 151

Great Models Think Alike and this Undermines AI Oversight

Paper • 2502.04313 • Published Feb 6 • 33