Category: software

https://github.com/abgulati/LARS

This grounding helps increase accuracy and reduce the common issue of AI-generated inaccuracies or “hallucinations.” This technique is commonly known as “Retrieval Augmented Generation”, or RAG.

LARS aims to be the ultimate open-source RAG-centric LLM application. Towards this end, LARS takes the concept of RAG much further by adding detailed citations to every response, supplying you with specific document names, page numbers, text-highlighting, and images relevant to your question, and even presenting a document reader right within the response window. While all the citations are not always present for every response, the idea is to have at least some combination of citations brought up for every RAG response and that’s generally found to be the case.

An open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, DeepSeek-Coder-V2 is further pre-trained from an intermediate checkpoint of DeepSeek-V2 with additional 6 trillion tokens. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-V2, while maintaining comparable performance in general language tasks. Compared to DeepSeek-Coder-33B, DeepSeek-Coder-V2 demonstrates significant advancements in various aspects of code-related tasks, as well as reasoning and general capabilities. Additionally, DeepSeek-Coder-V2 expands its support for programming languages from 86 to 338, while extending the context length from 16K to 128K.

https://github.com/deepseek-ai/DeepSeek-Coder-V2

https://venturebeat.com/ai/chinas-deepseek-coder-becomes-first-open-source-coding-model-to-beat-gpt-4-turbo/

https://gapszju.github.io/RTG-SLAM/

https://github.com/MisEty/RTG-SLAM

https://gapszju.github.io/RTG-SLAM/static/pdfs/RTG-SLAM_arxiv.pdf

A Real-time Gaussian SLAM (RTG-SLAM), a real-time 3D reconstruction system with an RGBD camera for large-scale environments using Gaussian splatting.

https://runwayml.com/blog/introducing-gen-3-alpha/

Gen-3 Alpha is the first of an upcoming series of models trained by Runway on a new infrastructure built for large-scale multimodal training. It is a major improvement in fidelity, consistency, and motion over Gen-2, and a step towards building General World Models.

Immersity AI  (formerly LeiaPix), turns 2D illustrations into 3D animation, ideal for bringing a sketch, painting or scene to life.

It converts the video into an animated depth video and uses that to trigger depth in the final output.

https://www.immersity.ai/

https://stability.ai/news/stable-diffusion-3

https://thenextweb.com/news/stability-ai-launches-stable-diffusion-3-image-generator

https://jinnan-chen.github.io/projects/HGM/

https://github.com/jinnan-chen/HGM

https://matchinganything.github.io/

https://github.com/siyuanliii/masa

https://zzzyuqing.github.io/dreammat.github.io

https://jector.ai/

https://github.com/TMElyralab/Comfyui-MusePose

ComfyMusePose