Stars
Representation Surgery for Multi-Task Model Merging. ICML, 2024.
Lean 4 programming language and theorem prover
A series of math-specific large language models of our Qwen2 series.
State-of-the-art bilingual open-sourced Math reasoning LLMs.
A High-efficiency Open-source Toolkit for Table-to-Latex Task
Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)
AlignCLIP: Improving Cross-Modal Alignment in CLIP
Official implementation for MorphGrower (ICML2024 Oral)
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
An evaluation benchmark for undergraduate competition math in Lean4, Isabelle, Coq, and natural language.
DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models
The is the official implementation of "Lyra: Orchestrating Dual Correction in Automated Theorem Proving"
Machine Learning Engineering Open Book
[ICCV 2023] Black Box Few-Shot Adaptation for Vision-Language models
General technology for enabling AI capabilities w/ LLMs and MLLMs
[COLM 2024] A Survey on Deep Learning for Theorem Proving
An open source implementation of CLIP.
Neural theorem proving tutorial, version II
LM based automatic theorem prover that can write code, respond to error messages, and look up docs.
codebase for the SIMAT dataset and evaluation
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers in this list investigate the learning behavior, generalizat…
[ICML 2024] Code release for "On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm"
The open-source tool for building high-quality datasets and computer vision models