8 citations · 12 across the 12 of their papers we have counts for
13 papers
Agents of Chaos
Natalie Shapira, Chris Wendler, Avery Yen +35
We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord acc…
Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
Kevin Lu, Jannik Brinkmann, Stefan Huber +4
How do protein structure prediction models fold proteins? We investigate this question through causal interventions on the folding trunks of ESMFold, OpenFold, and Boltz-1. Across…
Internal states before wait modulate reasoning patterns
Dmitrii Troitskii, Koyena Pal, Chris Wendler +2
Prior work has shown that a significant driver of performance in reasoning models is their ability to reason and self-correct. A distinctive marker in these reasoning traces is the…
Discovering Forbidden Topics in Language Models
Can Rager, Chris Wendler, Rohit Gandikota +1
Refusal discovery is the task of identifying the full set of topics that a language model refuses to discuss. We introduce this new problem setting and develop a refusal discovery…
zip2zip: Inference-Time Adaptive Tokenization via Online Compression
Saibo Geng, Nathan Ranchin, Yunzhen yao +4
Tokenization efficiency plays a critical role in the performance and cost of large language models (LLMs), yet most models rely on static tokenizers optimized on general-purpose co…
The Geometry of Self-Verification in a Task-Specific Reasoning Model
Andrew Lee, Lihao Sun, Chris Wendler +2
How do reasoning models verify their own answers? We study this question by training a model using DeepSeek R1's recipe on the CountDown task. We leverage the fact that preference…
Localized Cultural Knowledge is Conserved and Controllable in Large Language Models
Veniamin Veselovsky, Berke Argin, Benedikt Stroebl +5
Just as humans display language patterns influenced by their native tongue when speaking new languages, LLMs often default to English-centric responses even when generating in othe…
Controlling Latent Diffusion Using Latent CLIP
Jason Becker, Chris Wendler, Peter Baylies +2
Instead of performing text-conditioned denoising in the image domain, latent diffusion models (LDMs) operate in latent space of a variational autoencoder (VAE), enabling more effic…
Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
Jannik Brinkmann, Chris Wendler, Christian Bartelt +1
Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models…
Byte BPE Tokenization as an Inverse string Homomorphism
Saibo Geng, Sankalp Gambhir, Chris Wendler +1
Tokenization is an important preprocessing step in the training and inference of large language models (LLMs). While there has been extensive research on the expressive power of th…
Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
Clément Dumas, Chris Wendler, Veniamin Veselovsky +2
A central question in multilingual language modeling is whether large language models (LLMs) develop a universal concept representation, disentangled from specific languages. In th…
Controllable Context Sensitivity and the Knob Behind It
Julian Minder, Kevin Du, Niklas Stoehr +4
When making predictions, a language model must trade off how much it relies on its context vs. its prior knowledge. Choosing how sensitive the model is to its context is a fundamen…
One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models
Viacheslav Surkov, Chris Wendler, Antonio Mari +5
For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of…