papers
abstracts and summaries from arXiv and other sources
- A Divide-Align-Conquer Strategy for Program Synthesis
- Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation
- Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models
- 1 Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
- ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning
- Attention Heads of Large Language Models: A Survey
- Automated Design of Agentic Systems
- Combining Induction and Transduction for Abstract Reasoning
- Communicating Natural Programs to Humans and Machines
- Diffusion for World Modeling: Visual Details Matter in Atari
- Diffusion On Syntax Trees For Program Synthesis
- DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
- Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
- Generative Agent Simulations of 1,000 People
- H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark
- Learning to (Learn at Test Time): RNNs with Expressive Hidden States
- On the Measure of Intelligence
- 1 Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens
- Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
- Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
- Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus
- 1 1 Relational decomposition for program synthesis
- Searching Latent Program Spaces
- Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle
- Training Language Models to Self-Correct via Reinforcement Learning
- Tree of Problems: Improving structured problem solving with compositionality
- Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer
- When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1