Summary This article was for the VISION-21 Symposium sponsored by NASA Lewis Research Center and the Ohio Aerospace Institute, March 30-31, 1993. It is also retrievable from the NASA technical reports server as part of NASA CP-10129. A slightly changed version appeared in the Winter 1993 issue of Whole Earth Review. Abstract Within thirty years, …
Summary 4DHumans tracks human poses in videos and can reconstruct their shape in 3D. The team behind it sees many applications and publishes the model. At the heart of 4DHumans is HMR 2.0, an evolution of an older method (HMR / Human Mesh Recovery) that follows the trend of using transformer architectures for computer vision. …
4D Humans reconstructs and tracks humans from video Read More »
Summary Snapchat’s researchers have developed a new method for AI images on smartphones. This should allow users to eliminate the hardware that would otherwise be required and enjoy greater privacy. Recent versions of image AI, such as Midjourney 5.1, Stable Diffusion XL, and Adobe Firefly, have raised the quality of generated graphics to a new …
New method generates AI images on iPhone in less than 2 seconds Read More »
Summary Nvidia’s Neuralangelo sets a new standard for 3D reconstruction of 2D video clips using neural networks. Neuralangelo is a new AI model from Nvidia and Johns Hopkins University that learns 3D reconstructions from video footage and can output and render them as 3D objects. Compared to previous methods, Neuralangelo captures far more surface detail …
Summary OpenAI shows an AI model that achieves SOTA in solving some mathematical problems. The underlying process could lead to better language models in general. In the Let’s Verify Step by Step paper, the OpenAI team trained several models based on GPT-4 to solve problems in the MATH dataset. The goal was to compare two …
OpenAI improves GPT-4’s mathematical reasoning with a new form of supervision Read More »
Summary Video-ChatGPT can describe video over time, solving textual tasks such as describing safety risks in a scene, highlighting humorous aspects, or generating matching ad copy. While companies like Runway ML are making strides in converting text to video, Video-ChatGPT goes the other way, giving a language model the ability to analyze video. Video-ChatGPT can …
Video-ChatGPT analyzes videos and explains why they might be funny Read More »
Summary Voyager uses GPT-4 to guide a learning Minecraft agent through the pixel world. Instead of reinforcement learning, Voyager relies on code generation. Researchers from Nvidia, Caltech, UT Austin, Stanford, and ASU introduce Voyager, the first lifelong learning agent that plays Minecraft. Unlike other Minecraft agents that use classic reinforcement learning techniques, for example, Voyager …
Minecraft bot Voyager programs itself using GPT-4 Read More »
Summary The progress of open-source language models is undisputed. But can they really compete with the much pricier, heavily trained language models from OpenAI, Google, and others? Sounds too good to be true: With little training effort and almost no money, open-source language models trained using the Alpaca Formula have set new benchmarks recently, reaching …
Open-source language models are no match for GPT-4 and co, study says Read More »
Summary The progress of open-source language models is undisputed. But can they really compete with the much pricier, heavily trained language models from OpenAI, Google, and others? Sounds too good to be true: With little training effort and almost no money, open-source language models trained using the Alpaca Formula have set new benchmarks recently, reaching …
Summary A new method named QLoRA enables the fine-tuning of large language models on a single GPU. Researchers used it to train Guanaco, a chatbot that reaches 99% of ChatGPTs performance. Researchers at the University of Washington present QLoRA (Quantized Low Rank Adapters), a method for fine-tuning large language models. Along with QLoRA, the team …
Guanaco is a ChatGPT competitor trained on a single GPU in one day Read More »
