1 citations · 2 across the 11 of their papers we have counts for
11 papers
PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks
Claas Beger, Ryan Yi, Melanie Mitchell
The Abstraction and Reasoning Corpus (ARC) has become a prominent benchmark for evaluating general abstract reasoning and fluid intelligence in AI models. Yet standard ARC evaluati…
Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks
Adrien Deliège, Claas Beger, Marc Van Droogenbroeck +1
The Abstraction and Reasoning Corpus and related benchmarks evaluate whether AI models can solve novel reasoning tasks, but often leave unclear whether success reflects inference o…
SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks
Claas Beger, Florian Walter, Alois Knoll
The Transformer architecture is widely regarded as the most powerful tool for natural language processing, but due to a high number of complex operations, it inherently faces the i…
Bongards at the Boundary of Perception and Reasoning: Programs or Language?
Cassidy Langenfeld, Claas Beger, Gloria Geng +4
Vision-Language Models (VLMs) have made great strides in everyday visual tasks, such as captioning a natural image, or answering commonsense questions about such images. But humans…
OmniCode: A Benchmark for Evaluating Software Engineering Agents
Atharv Sonwane, Eng-Shen Tu, Wei-Chung Lu +11
LLM-powered coding agents are redefining how real-world software is developed. To drive the research towards better coding agents, we require challenging benchmarks that can rigoro…
Distinguishing Performance From Competence in Evaluations of Humanlike Abstract Reasoning
Claas Beger, Ryan Yi, Shuhao Fu +5
AI reasoning models have exceeded human performance on the ARC-AGI-1 benchmark, but does that mean state-of-the-art models have the underlying competence (humanlike abstract reason…
A Neuroscience-Inspired Dual-Process Model of Compositional Generalization
Alex Noviello, Claas Beger, Jacob Groner +2
Deep learning models struggle with systematic compositional generalization, a hallmark of human cognition. We propose \textsc{Mirage}, a neuro-inspired dual-process model that offe…
-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering
Chao Wan, Albert Gong, Mihir Mishra +3
Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with complex multi-hop questions, often fall…
CoCoNUT: Structural Code Understanding does not fall out of a tree
Claas Beger, Saikat Dutta
Large Language Models (LLMs) have shown impressive performance across a wide array of tasks involving both structured and unstructured textual data. Recent results on various bench…
Citegeist: Automated Generation of Related Work Analysis on the arXiv Corpus
Claas Beger, Carl-Leander Henneking
Large Language Models provide significant new opportunities for the generation of high-quality written works. However, their employment in the research community is inhibited by th…
Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AI
Carl-Leander Henneking, Claas Beger
Traditional methods for aligning Large Language Models (LLMs), such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on implicit…