activity
20232026
collaborators

6 papers

cs.CL2026

LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure

Fanfei Li, Jana Zeller, Manuel Prada-Corral +4

Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to related conten…

cs.AI2026

MentisOculi: Revealing the Limits of Reasoning with Mental Imagery

Jana Zeller, Thaddäus Wiedemer, Fanfei Li +6

Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capable of native interlea…

cs.LG2025

MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model

Prasanna Mayilvahanan, Ricardo Dominguez-Olmedo, Thaddäus Wiedemer +1

With the advent of DeepSeek-R1, a new wave of reinforcement learning (RL) methods has emerged that seem to unlock stronger mathematical reasoning. However, a closer look at the ope…

cs.LG2025

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws

Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick +2

Scaling laws guide the development of large language models (LLMs) by offering estimates for the optimal balance of model size, tokens, and compute. More recently, loss-to-loss sca…

cs.CV2024

In Search of Forgotten Domain Generalization

Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer +4

Out-of-Domain (OOD) generalization is the ability of a model trained on one or more domains to generalize to unseen domains. In the ImageNet era of computer vision, evaluation sets…

cs.CV2023

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?

Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak +2

Foundation models like CLIP are trained on hundreds of millions of samples and effortlessly generalize to new tasks and inputs. Out of the box, CLIP shows stellar zero-shot and few…