13 papers
Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3
Jens Lehmann, Sahar Vahdati
A generally intelligent system acquires new skills efficiently without requiring humans to redesign its software scaffold for every new task. Yet language models rarely act alone.…
A Systematic Study of Small Language Models on Abstract Reasoning Tasks
Nur A Zarin Nishat, Jens Lehmann, Andrei Aioanei +1
Endpoint accuracy on abstract-reasoning benchmarks does not reveal whether a language model has acquired a transferable rule or fit distribution-specific regularities. We study thi…
When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation
Susu Hu, Preetam Gattogi, Jens Lehmann +3
Bidirectional discrete diffusion model appears naturally suited to genomic modeling because it can reconstruct missing sequence from both flanks. We developed GenDA (Genomic Densit…
Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
Jens Lehmann, Andrei Aioanei, Sahar Vahdati
ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal while maintaining action effici…
Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models
Kossi Amouzouvi, Robert Wardenga, Jens Lehmann +1
Foundation models excel at language, where sentences become tokens, and vision, where images become pixels, because both reduce to discrete symbols on a shared, fixed grid. Knowled…
Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference
Cornelius Kummer, Lena Jurkschat, Michael Färber +1
With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retri…
Process Rewards for Outcome-Guided Reasoning Steps in LLM Reinforcement Learning
Mohammad Rezaei, Jens Lehmann, Sahar Vahdati
Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checked automatically an…
The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning
Sahar Vahdati, Andrei Aioanei, Haridhra Suresh +1
The Abstraction and Reasoning Corpus (ARC-AGI) has become a key benchmark for fluid intelligence in AI. This survey presents the first cross-generation analysis of 82 approaches ac…
ARC-TGI: Human-Validated Task Generators with Reasoning Chain Templates for ARC-AGI
Jens Lehmann, Syeda Khushbakht, Nikoo Salehfard +4
The Abstraction and Reasoning Corpus (ARC-AGI) probes few-shot abstraction and rule induction on small visual grids, but progress is difficult to measure on static collections of h…
ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation
Riccardo Pozzi, Matteo Palmonari, Andrea Coletta +3
Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill…
Aligning Knowledge Graphs and Language Models for Factual Accuracy
Nur A Zarin Nishat, Andrea Coletta, Luigi Bellomarini +3
Large language models like GPT-4, Gemini, and Claude have transformed natural language processing (NLP) tasks such as question answering, dialogue generation, summarization, and so…
SMART: Relation-Aware Learning of Geometric Representations for Knowledge Graphs
Kossi Amouzouvi, Bowen Song, Andrea Coletta +3
Knowledge graph representation learning approaches provide a mapping between symbolic knowledge in the form of triples in a knowledge graph (KG) and their feature vectors. Knowledg…
Advancing Safe Mechanical Ventilation Using Offline RL With Hybrid Actions and Clinically Aligned Rewards
Muhammad Hamza Yousuf, Jason Li, Sahar Vahdati +3
Invasive mechanical ventilation (MV) is a life-sustaining therapy commonly used in the intensive care unit (ICU) for patients with severe and acute conditions. These patients frequ…