The Best TResNet: High Performance GPU-Dedicated Architecture Alternatives in 2026

OpenVLA provides an open-source vision-language-action model for robotic manipulation tasks.

DeepSeek-VL2 supports multimodal understanding through a mixture-of-experts vision-language model.

timm provides PyTorch image encoders and backbones along with training, evaluation, inference, and export scripts.

The learn2learn library supports meta learning experiments and research with PyTorch.

MobiLlama is a small language model designed for edge devices, according to its repository description.

This repository contains the DeepSeek-V3 language model project and related source files.

This repository contains Google Research code for the Flan-T5 language model project.

Janus combines multimodal understanding and image generation models in a unified model series.

Point·E is a research project that generates 3D point clouds using diffusion models.

CodeGen provides open-source models for program synthesis and code generation.

This research project presents an open platform for language agents in real-world settings.

DeepSeek Coder is a language model project for code generation and programming tasks.

DeepSWE benchmarks coding agents on original, long-horizon software engineering tasks.

Code and documentation to train Stanford's Alpaca models, and generate the data.

ChatGLM-6B is an open bilingual dialogue language model described in English and Chinese.

Microsoft’s loralib implements low rank adaptation for large language models.

MetaWorld provides robotics environments for benchmarking multi task and meta reinforcement learning.

NuPIC implements Hierarchical Temporal Memory, a model of intelligence based on neocortical theory.

xTuring supports personalizing open source language models through preprocessing and fine tuning.

This repository provides a PyTorch implementation of a CVPR paper on high resolution representations for human pose estimation.

This repository accompanies research on improving language model factuality and reasoning through multi-agent debate.

This repository implements a GPT-4 agent for playing imperfect information games with theory of mind.

ImageBind explores a shared embedding space that connects different kinds of data.

The Qwen3 model series was developed by the Qwen team at Alibaba Cloud.