7 citations · 26 across the 34 of their papers we have counts for
19 papers · 1 filter
Benchmarks Are Surprisingly Compaction-Friendly
Jeanne Salle, Hardik Bhatnagar, Matthias Bethge +2
Long horizon agentic tasks are now pushing LLM agents past their context window. To continue the task, the agent scaffold has to free up the context window, a process known as cont…
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina +3
LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-only rewards provide too sparse g…
Intrinsic Credit Assignment for Long Horizon Interaction
Ilze Amanda Auzina, Joschka Strüber, Sergio Hernández-Gutiérrez +3
How can we train agents to navigate uncertainty over long horizons? In this work, we propose ΔBelief-RL, which leverages a language model's own intrinsic beliefs to reward intermed…
Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
Tobias Schmidt, Steffen Schneider, Matthias Bethge
We propose Equivariance by Contrast (EbC) to learn equivariant embeddings from observation pairs , where is drawn from a finite group acting o…
Mapping Post-Training Forgetting in Language Models at Scale
Jackson Harmon, Andreas Hochlehnert, Matthias Bethge +1
Scaled post-training now drives many of the largest capability gains in language models (LMs), yet its effect on pretrained knowledge remains poorly understood. Not all forgetting…
LLM generation novelty through the lens of semantic similarity
Philipp Davydov, Ameya Prabhu, Matthias Bethge +2
Generation novelty is a key indicator of an LLM's ability to generalize, yet measuring it against full pretraining corpora is computationally challenging. Existing evaluations ofte…
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
Alexander Panfilov, Evgenii Kortukov, Kristina Nikolić +6
Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrifici…
A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
Andreas Hochlehnert, Hardik Bhatnagar, Vishaal Udandarao +3
Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces method…
Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation
Shiven Sinha, Shashwat Goel, Ponnurangam Kumaraguru +3
There is growing excitement about the potential of Language Models (LMs) to accelerate scientific discovery. Falsifying hypotheses is key to scientific progress, as it allows claim…
Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks
Thaddäus Wiedemer, Yash Sharma, Ameya Prabhu +2
We investigate the success conditions for compositional generalization of CLIP models on real-world data through performance prediction. Prior work shows that CLIP requires exponen…
Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs
Christoph Schuhmann, Gollam Rabby, Ameya Prabhu +9
Paywalls, licenses and copyright rules often restrict the broad dissemination and reuse of scientific knowledge. We take the position that it is both legally and technically feasib…
Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models
Luca M. Schulze Buschoff, Konstantinos Voudouris, Elif Akata +3
Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual st…
Great Models Think Alike and this Undermines AI Oversight
Shashwat Goel, Joschka Struber, Ilze Amanda Auzina +6
As Language Model (LM) capabilities advance, evaluating and supervising them at scale is getting harder for humans. There is hope that other language models can automate both these…
How to Merge Your Multimodal Models Over Time?
Sebastian Dziadzio, Vishaal Udandarao, Karsten Roth +4
Model merging combines multiple expert models - finetuned from a base foundation model on diverse tasks and domains - into a single, more capable model. However, most existing mode…
ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities
Adhiraj Ghosh, Sebastian Dziadzio, Ameya Prabhu +3
Traditional fixed test sets fall short in evaluating open-ended capabilities of foundation models. To address this, we propose ONEBench(OpeN-Ended Benchmarking), a new testing para…
Centaur: a foundation model of human cognition
Marcel Binz, Elif Akata, Matthias Bethge +37
Establishing a unified theory of cognition has been a major goal of psychology. While there have been previous attempts to instantiate such theories by building computational model…
Efficient Lifelong Model Evaluation in an Era of Rapid Progress
Ameya Prabhu, Vishaal Udandarao, Philip Torr +3
Standardized benchmarks drive progress in machine learning. However, with repeated testing, the risk of overfitting grows as algorithms over-exploit benchmark idiosyncrasies. In ou…
Visual cognition in multimodal large language models
Luca M. Schulze Buschoff, Elif Akata, Matthias Bethge +1
A chief goal of artificial intelligence is to build machines that think like people. Yet it has been argued that deep neural network architectures fail to accomplish this. Research…
Provable Compositional Generalization for Object-Centric Learning
Thaddäus Wiedemer, Jack Brady, Alexander Panfilov +3
Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learn…