Research & Papers

Latest AI research

Meta AI Releases EUPE: A Compact Vision Encoder Family Under 100M Parameters That Rivals Specialist Models Across Image Understanding, Dense Prediction, and VLM Tasks
Research & PapersMeta

Meta AI Releases EUPE: A Compact Vision Encoder Family Under 100M Parameters That Rivals Specialist Models Across Image Understanding, Dense Prediction, and VLM Tasks

Meta AI has released EUPE, a compact vision encoder family with under 100M parameters designed for edge devices that...

MarkTechPost
An Implementation Guide to Running NVIDIA Transformer Engine with Mixed Precision, FP8 Checks, Benchmarking, and Fallback Execution
Research & Papers

An Implementation Guide to Running NVIDIA Transformer Engine with Mixed Precision, FP8 Checks, Benchmarking, and Fallback Execution

This tutorial provides a practical implementation guide for NVIDIA Transformer Engine, focusing on mixed-precision...

MarkTechPost
Import AI 452: Scaling laws for cyberwar; rising tides of AI automation; and a puzzle over gDP forecasting
Research & Papers

Import AI 452: Scaling laws for cyberwar; rising tides of AI automation; and a puzzle over gDP forecasting

The article discusses scaling laws for cyberwarfare applications of AI, explores the rising tide of AI automation's...

Import AI
Alibaba's Qwen team built HopChain to fix how AI vision models fall apart during multi-step reasoning
Research & Papers

Alibaba's Qwen team built HopChain to fix how AI vision models fall apart during multi-step reasoning

Alibaba's Qwen team developed HopChain, a framework that improves AI vision models' multi-step reasoning by breaking...

The Decoder
How to Build a Netflix VOID Video Object Removal and Inpainting Pipeline with CogVideoX, Custom Prompting, and End-to-End Sample Inference
Research & Papers

How to Build a Netflix VOID Video Object Removal and Inpainting Pipeline with CogVideoX, Custom Prompting, and End-to-End Sample Inference

This tutorial demonstrates how to build and implement Netflix's VOID model, an advanced video object removal and...

MarkTechPost
Inside the Creative Artificial Intelligence (AI) Stack: Where Human Vision and Artificial Intelligence Meet to Design Future Fashion
Research & Papers

Inside the Creative Artificial Intelligence (AI) Stack: Where Human Vision and Artificial Intelligence Meet to Design Future Fashion

The article discusses how artificial intelligence, including algorithms, neural networks, and machine learning, is...

MarkTechPost
Netflix open-sources VOID, an AI framework that erases video objects and rewrites the physics they left behind
Research & Papers

Netflix open-sources VOID, an AI framework that erases video objects and rewrites the physics they left behind

Netflix has open-sourced VOID, an AI framework capable of removing objects from videos while automatically adjusting...

The Decoder
Know3D lets users control the hidden back side of 3D objects with text prompts
Research & Papers

Know3D lets users control the hidden back side of 3D objects with text prompts

Know3D is a research project that uses large language models to enable users to control the appearance of hidden...

The Decoder
Netflix AI Team Just Open-Sourced VOID: an AI Model That Erases Objects From Videos — Physics and All
Research & Papers

Netflix AI Team Just Open-Sourced VOID: an AI Model That Erases Objects From Videos — Physics and All

Netflix's AI team has open-sourced VOID, an AI model capable of removing objects from videos while maintaining...

MarkTechPost
Working to advance the nuclear renaissance
Research & Papers

Working to advance the nuclear renaissance

Dean Price, an assistant professor in Nuclear Science and Engineering, believes AI can play a significant role in...

MIT News AI
TII Releases Falcon Perception: A 0.6B-Parameter Early-Fusion Transformer for Open-Vocabulary Grounding and Segmentation from Natural Language Prompts
Research & Papers

TII Releases Falcon Perception: A 0.6B-Parameter Early-Fusion Transformer for Open-Vocabulary Grounding and Segmentation from Natural Language Prompts

TII has released Falcon Perception, a 0.6B-parameter early-fusion transformer model designed for open-vocabulary visual...

MarkTechPost
Step by Step Guide to Build an End-to-End Model Optimization Pipeline with NVIDIA Model Optimizer Using FastNAS Pruning and Fine-Tuning
Research & Papers

Step by Step Guide to Build an End-to-End Model Optimization Pipeline with NVIDIA Model Optimizer Using FastNAS Pruning and Fine-Tuning

A tutorial on building an end-to-end model optimization pipeline using NVIDIA Model Optimizer, covering training,...

MarkTechPost
MIT researchers use AI to uncover atomic defects in materials
Research & Papers

MIT researchers use AI to uncover atomic defects in materials

MIT researchers developed an AI model that identifies and measures atomic defects in materials to improve their...

MIT News AI
Seeing sounds
Research & Papers

Seeing sounds

Mariano Salcedo, a master's student in a new Music Technology and Computation Graduate Program, is developing an AI...

MIT News AI
Augmenting citizen science with computer vision for fish monitoring
Research & Papers

Augmenting citizen science with computer vision for fish monitoring

MIT Sea Grant collaborates with Woodwell Climate Research Center to develop a deep learning-based computer vision...

MIT News AI
Import AI 450: China's electronic warfare model; traumatized LLMs; and a scaling law for cyberattacks
Research & Papers

Import AI 450: China's electronic warfare model; traumatized LLMs; and a scaling law for cyberattacks

The article discusses China's electronic warfare AI model, the effects of trauma on large language models, and a...

Import AI
Measuring progress toward AGI: A cognitive framework
Research & Papers

Measuring progress toward AGI: A cognitive framework

A framework has been introduced to measure progress toward Artificial General Intelligence (AGI), with a Kaggle...

DeepMind Blog
From games to biology and beyond: 10 years of AlphaGo’s impact
Research & PapersGoogle

From games to biology and beyond: 10 years of AlphaGo’s impact

The article commemorates the 10-year anniversary of AlphaGo and examines its lasting impact on scientific discovery...

DeepMind Blog
Import AI 445: Timing superintelligence; AIs solve frontier math proofs; a new ML research benchmark
Research & Papers

Import AI 445: Timing superintelligence; AIs solve frontier math proofs; a new ML research benchmark

The article discusses timing considerations for superintelligence development, with AI systems achieving breakthroughs...

Import AI