MagicMix: Semantic Mixing with Diffusion Models - PrO_RaZe Bookmarks #391
MagicMix: Semantic Mixing with Diffusion Models - PrO_RaZe Bookmarks #391
Posts
Continual-T0 (CT0) displays Continual Learning capabilities via self-supervision - PrO_RaZe Bookmarks #389
Continual-T0 (CT0) displays Continual Learning capabilities via self-supervision - PrO_RaZe Bookmarks #389
Transformers have shown remarkable capabilities - but can they improve themselves autonomously from trial and error? - PrO_RaZe Bookmarks #388
Transformers have shown remarkable capabilities - but can they improve themselves autonomously from trial and error? - PrO_RaZe Bookmarks #388
DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality - PrO_RaZe Bookmarks #387
DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality - PrO_RaZe Bookmarks #387
Meta AI's AI-powered hypercompression of audio - PrO_RaZe Bookmarks #386
Meta AI's AI-powered hypercompression of audio - PrO_RaZe Bookmarks #386
Large Language Models Can Self-improve - PrO_RaZe Bookmarks #385
Large Language Models Can Self-improve - PrO_RaZe Bookmarks #385
New open-source language model from Google AI: Flan-T5 - PrO_RaZe Bookmarks #384
New open-source language model from Google AI: Flan-T5 - PrO_RaZe Bookmarks #384
(Google AI) Introducing U-PaLM 540B! - PrO_RaZe Bookmarks #383
(Google AI) Introducing U-PaLM 540B! - PrO_RaZe Bookmarks #383
MUSIQ: Assessing Image Aesthetic and Technical Quality with Multi-scale Transformers - PrO_RaZe Bookmarks #382
MUSIQ: Assessing Image Aesthetic and Technical Quality with Multi-scale Transformers - PrO_RaZe Bookmarks #382
Language models beat (average) humans in challenging BIG-Bench tasks when using a large enough model and Chain-of-Thought prompting - PrO_RaZe Bookmarks #381
Language models beat (average) humans in challenging BIG-Bench tasks when using a large enough model and Chain-of-Thought prompting - PrO_RaZe Bookmarks #381
Mind's Eye: Grounded Language Model Reasoning through Simulation - PrO_RaZe Bookmarks #380
Mind's Eye: Grounded Language Model Reasoning through Simulation - PrO_RaZe Bookmarks #380
Imagic: Text-Based Real Image Editing with Diffusion Models - PrO_RaZe Bookmarks #379
Imagic: Text-Based Real Image Editing with Diffusion Models - PrO_RaZe Bookmarks #379
COMPRESSED VISION FOREFFICIENT VIDEO UNDERSTANDING (Deepmind AI) - PrO_RaZe Bookmarks #378
COMPRESSED VISION FOREFFICIENT VIDEO UNDERSTANDING (Deepmind AI) - PrO_RaZe Bookmarks #378
DeepMind breaks 50-year math record using AI; new record falls a week later - PrO_RaZe Bookmarks #377
DeepMind breaks 50-year math record using AI; new record falls a week later - PrO_RaZe Bookmarks #377
Google AI Crossmodal 3600 dataset - PrO_RaZe Bookmarks #375
Google AI Crossmodal 3600 dataset - PrO_RaZe Bookmarks #375
Habitat-Matterport 3D Semantics dataset - PrO_RaZe Bookmarks #373
Habitat-Matterport 3D Semantics dataset - PrO_RaZe Bookmarks #373
Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning - PrO_RaZe Bookmarks #372
Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning - PrO_RaZe Bookmarks #372
ReAct: Synergizing Reasoning and Acting in Language Models - PrO_RaZe Bookmarks #371
ReAct: Synergizing Reasoning and Acting in Language Models - PrO_RaZe Bookmarks #371
On distillation of guided diffusion models (AI) - PrO_RaZe Bookmarks #370
On distillation of guided diffusion models (AI) - PrO_RaZe Bookmarks #370
Implementing Stable Diffusion in VR - PrO_RaZe Bookmarks #369
Implementing Stable Diffusion in VR - PrO_RaZe Bookmarks #369
TECO, an efficient video prediction model that can generate long, temporally consistent video - PrO_RaZe Bookmarks #368
TECO, an efficient video prediction model that can generate long, temporally consistent video - PrO_RaZe Bookmarks #368
Carper AI FIM-NeoX-1.3B Language Model - PrO_RaZe Bookmarks #367
Carper AI FIM-NeoX-1.3B Language Model - PrO_RaZe Bookmarks #367
How undesired goals can arise with correct rewards (Deepmind AI) - PrO_RaZe Bookmarks #366
How undesired goals can arise with correct rewards (Deepmind AI) - PrO_RaZe Bookmarks #366
Beyond Bayes-optimality: meta-learning what you know you don't know (Deepmind AI) - PrO_RaZe Bookmarks #365
Beyond Bayes-optimality: meta-learning what you know you don't know (Deepmind AI) - PrO_RaZe Bookmarks #365
Novel View Synthesis with Diffusion Models - PrO_RaZe Bookmarks #364
Novel View Synthesis with Diffusion Models - PrO_RaZe Bookmarks #364
~75% chance of AGI by 2032 - PrO_RaZe Bookmarks #363
~75% chance of AGI by 2032 - PrO_RaZe Bookmarks #363
Imagen Video Text-to-video Diffusion AI - PrO_RaZe Bookmarks #362
Imagen Video Text-to-video Diffusion AI - PrO_RaZe Bookmarks #362
Google AI FILM, a novel neural network architecture that can be used to create high-quality slow motion videos - PrO_RaZe Bookmarks #361
Google AI FILM, a novel neural network architecture that can be used to create high-quality slow motion videos - PrO_RaZe Bookmarks #361
Large Language Models Can Self-improve - PrO_RaZe Bookmarks #360
Large Language Models Can Self-improve - PrO_RaZe Bookmarks #360
Dramatron is system that enables writers to co-create theatre / film scripts (Deepmind) - PrO_RaZe Bookmarks #359
Dramatron is system that enables writers to co-create theatre / film scripts - PrO_RaZe Bookmarks #359