[EMNLP 25] An effective and interpretable weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study uncovering how reasoning length is encoded in the model’s representation space.
☆19Dec 17, 2025Updated 5 months ago
Alternatives and similar repositories for ThinkEdit
Users that are interested in ThinkEdit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆58Apr 6, 2025Updated last year
- ☆15Feb 26, 2025Updated last year
- Inverse Scaling in Test-Time Compute☆25Dec 3, 2025Updated 6 months ago
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆19Oct 21, 2024Updated last year
- Official implementation for "Mixture of In-Context Experts Enhance LLMs’ Awareness of Long Contexts" (Accepted by Neurips2024)☆14Jan 7, 2025Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆14Oct 30, 2024Updated last year
- [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliabilit…☆33Feb 5, 2026Updated 4 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆92Feb 14, 2025Updated last year
- [NeurIPS 2024 Main Track] Code for the paper titled "Instruction Tuning With Loss Over Instructions"☆38May 24, 2024Updated 2 years ago
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- ☆82Nov 11, 2024Updated last year
- ☆10Jul 8, 2021Updated 4 years ago
- ☆32Aug 21, 2025Updated 9 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆70Oct 2, 2025Updated 8 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [NAACL 2025 Main] Official Implementation of MLLMU-Bench☆53Mar 13, 2025Updated last year
- ☆33Nov 11, 2024Updated last year
- Official codes for COLING 2024 paper "Robust and Scalable Model Editing for Large Language Models": https://arxiv.org/abs/2403.17431v1☆14Mar 27, 2024Updated 2 years ago
- Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)☆12Oct 31, 2024Updated last year
- Code for "Reasoning to Learn from Latent Thoughts"☆131Mar 28, 2025Updated last year
- PyTorch implementation of delayed-feedback-model (DFM)☆15Feb 7, 2022Updated 4 years ago
- [ICML 2025] Official PyTorch implementation of "NegMerge: Sign-Consensual Weight Merging for Machine Unlearning"☆16Nov 25, 2025Updated 6 months ago
- ☆56Jul 7, 2025Updated 11 months ago
- [EMNLP 2024] Quantize LLM to extremely low-bit, and finetune the quantized LLMs☆15Jul 18, 2024Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆20Feb 2, 2026Updated 4 months ago
- Experiments for our CLEAR benchmark of unlearning methods in a multimodal setup☆23Aug 6, 2025Updated 10 months ago
- ☆11Oct 25, 2024Updated last year
- Github repository for "Internalizing World Models via Self-Play Finetuning for Agentic RL"☆35Nov 1, 2025Updated 7 months ago
- ☆10Oct 29, 2020Updated 5 years ago
- Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision☆19Apr 1, 2025Updated last year
- Code for paper "Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion"☆14Mar 28, 2024Updated 2 years ago
- [NeurIPS25] RULE: Reinforcement UnLEarning Achieves Forge-retain Pareto Optimality☆21Oct 22, 2025Updated 7 months ago
- ☆10Apr 16, 2024Updated 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.
- Efficient Scaling laws and collaborative pretraining.☆22Sep 18, 2025Updated 8 months ago
- Code for "Neural Speed Reading with Structural-Jump-LSTM" ICLR 2019☆25Feb 22, 2019Updated 7 years ago
- ☆15Jun 25, 2025Updated 11 months ago
- Code for paper "Towards Efficient Pareto Set Approximation via Weight-Ensembling Mixture of Experts"☆11Sep 13, 2024Updated last year
- Preparing for ML Interviews.☆53Jan 12, 2026Updated 4 months ago
- [NeurIPS 2025] Bag of Tricks for Inference-time Computation of LLM Reasoning☆16Sep 20, 2025Updated 8 months ago
- How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning☆26Aug 29, 2024Updated last year