342285bb2a8cadef22f667eeb6a63732-Paper.pdf
proceedings.neurips.cc · 7,658 words · saved by 1 readers
N/A
Learning Differentiable Programs with Admissible Neural Heuristics Ameesh Shah⇤ Eric Zhan⇤ Jennifer J. Sun UC Berkeley Caltech Caltech ameesh@berkeley.edu ezhan@caltech.edu jjsun@caltech.edu Abhinav Verma Yisong Yue Swarat Chaudhuri UT Austin Caltech UT Austin verma@utexas.edu…
related reading
- NL.pdfabehrouz.github.io
- pdfopenreview.net
- arxiv.org/pdf/1805.08522arxiv.org
- Language Model Circuits Are Sparse in the Neuron Basis | Transluce AItransluce.org
- [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
- Stream of Search (SoS): Learning to Search in Languagearxiv.org
- [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
- Towards Automated Circuit Discovery for Mechanistic Interpretabilityarxiv.org
- arxiv.org/pdf/2512.24880#page=3.56arxiv.org
- 2006.08381arxiv.org
- [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
- Dynamic Inference with Neural Interpretersarxiv.org