activity
20242026
most citedTwo Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2025

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…

cs.CL2025

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…

cs.CL2025

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…

cs.CL2025

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…

cs.CL2025

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…

cs.CL2025

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…