Code for our ACL '23 paper titled "Grokking of Hierarchical Structure in Vanilla Transformers"
☆26Oct 8, 2023Updated 2 years ago
Alternatives and similar repositories for structural-grokking
Users that are interested in structural-grokking are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for "Does syntax need to grow on trees? Sources of inductive bias in sequence to sequence networks"☆24Jan 14, 2020Updated 6 years ago
- Code for Pushdown Layers from our EMNLP 2023 paper☆29Dec 3, 2023Updated 2 years ago
- Repository for the code and dataset for the paper: "Have LLMs Advanced enough? Towards Harder Problem Solving Benchmarks For Large Langu…☆39Dec 18, 2023Updated 2 years ago
- ☆23Apr 5, 2026Updated 4 months ago
- TyDiP Multilingual Politeness dataset and code☆12Oct 15, 2023Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Models and code from Learning to Predict Denotational Probabilities For Modeling Entailment☆14Feb 1, 2018Updated 8 years ago
- Word acquisition in neural language models (TACL 2022).☆21Jan 30, 2025Updated last year
- Tasks for describing differences between text distributions.☆17Aug 9, 2024Updated 2 years ago
- [ACM MM 2025] Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception☆14Aug 5, 2026Updated last week
- Code for EMNLP 2022 Paper: On the Calibration of Massively Multilingual Language Models☆15Jun 12, 2023Updated 3 years ago
- The KiloGram Tangrams dataset☆60Apr 25, 2025Updated last year
- Simple and extensible hypergradient for PyTorch☆18Feb 23, 2023Updated 3 years ago
- Code for our ACL '20 paper "Representation Engineering with Natural Language Explanations"☆30Jun 15, 2020Updated 6 years ago
- ☆13Oct 18, 2023Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Interaction-first method for generating demonstrations for web-agents on any website☆57Apr 29, 2025Updated last year
- 論文執筆チェックリスト☆22Jul 3, 2026Updated last month
- FaiRR: Faithful and Robust Deductive Reasoning over Natural Language (ACL 2022)☆14May 19, 2022Updated 4 years ago
- A dataset of 80 millon constraint preserving transformations of CAD sketches☆17Nov 22, 2024Updated last year
- Discovering Universal Geometry in Embeddings with ICA (Published in EMNLP 2023)☆22Jun 17, 2025Updated last year
- ☆23Nov 8, 2023Updated 2 years ago
- Multimodal extreme classification☆21May 1, 2024Updated 2 years ago
- ☆18Jan 17, 2024Updated 2 years ago
- Official Implementation of UA^{2}-Agent and other baseline algorithms of "Towards Unified Alignment Between Agents, Humans, and Environme…☆20Nov 12, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts☆16Jul 27, 2026Updated 2 weeks ago
- ☆35Jan 29, 2023Updated 3 years ago
- Official Implementation of ACL2023: Don't Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span …☆14Aug 25, 2023Updated 2 years ago
- Official implementation of MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learning☆19Jan 27, 2024Updated 2 years ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆240Jul 19, 2025Updated last year
- [NeurIPS-2023] The PyTorch Implementation of MoSo. The algorithms are based on our paper: "Data Pruning via Moving-one-Sample-out". MoSo …☆10May 21, 2026Updated 2 months ago
- Code and Data for all experiments from our ACL 2018 paper "Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linki…☆42Aug 5, 2019Updated 7 years ago
- (NeurIPS 2024) What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights☆27Oct 28, 2024Updated last year
- Code for "Multi-scale Abstract Reasoning" paper☆11Oct 17, 2022Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Menagerie of video models trained on various video datasets☆10Oct 13, 2024Updated last year
- ☆25Apr 13, 2025Updated last year
- ☆14May 3, 2022Updated 4 years ago
- TACL 2020: Syntax-Guided Controlled Generation of Paraphrases☆72Mar 16, 2024Updated 2 years ago
- The original Backpack Language Model implementation, a fork of FlashAttention☆71May 29, 2023Updated 3 years ago
- [NeurIPS 2023] Learning Energy-Based Prior Model with Diffusion-Amortized MCMC☆14Mar 1, 2026Updated 5 months ago
- ☆11Sep 16, 2024Updated last year