This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Janus-Series: Unified Multimodal Understanding and Generation Models

CoRL2024 | Hint-AD: Holistically Aligned Interpretability for End-to-End Autonomous Driving

DriveBench: A Comprehensive Benchmark for Evaluating Large Vision-Language Models on Autonomous Driving

[NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Waymo Open Dataset

OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…

[ECCV 2024] Embodied Understanding of Driving Scenarios

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

A recipe for online RLHF and online iterative DPO.

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

LLM inference in C/C++

RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness

VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

Reference implementation for DPO (Direct Preference Optimization)

Bridging Large Vision-Language Models and End-to-End Autonomous Driving

Composable building blocks to build Llama Apps

O1 Replication Journey

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models