[NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection

Code release for Best-of-N Jailbreaking

Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains papers, codes, datasets, evaluations, and analyses.

Code for 'Robust Rank-One Matrix Completion via Explicit Regularizer' accepted by TNNLS 2025

An open source implementation of CLIP.

CKA (Centered Kernel Alignment) implemented in PyTorch

Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]

[ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2

AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.

Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"

Editing Models with Task Arithmetic

Model Merging with SVD to Tie the KnOTS [ICLR 2025]

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.

Codebase for Merging Language Models (ICML 2024)

Model merging is a highly efficient approach for long-to-short reasoning.

Tools for merging pretrained large language models.

Code for AROMA: Autonomous Rank-one Matrix Adaptation

Latest Advances on System-2 Reasoning

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Paper list for Efficient Reasoning.

Official style files for papers submitted to venues of the Association for Computational Linguistics

AI handwriting recognition for emojis 😃

Emoji for everyone. https://twemoji.twitter.com/

Emoji support in (Lua)LaTeX

A collection of code snippets from the publication Daily Dose of Data Science on Substack: http://www.dailydoseofds.com/

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

[NeurIPS 2022, T-PAMI 2023] Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]