Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers Crowson et al.: https://
arxiv.org/abs/2401.11605 #ArtificialIntelligence #DeepLearning #MachineLearning
MULTIMODAL AI
-
Hourglass Diffusion Transformers Enable Scalable High-Resolution Image
By
–
-
AI-Powered Film Scene Creation Using ChatGPT and Runway
By
–
📽️ Parlons de la création de scène en réalisation de films avec l'IA
— VISION IA (@vision_ia) 12 avril 2025
Maintenant que la technologie progresse de manière exponentielle, je pense qu’il est temps d’améliorer notre rigueur.
Outils utilisés :
ChatGPT // pour la conception des plans et le world building
Runway… pic.twitter.com/0hDNLghDcuParlons de la création de scène en réalisation de films avec l'IA Maintenant que la technologie progresse de manière exponentielle, je pense qu’il est temps d’améliorer notre rigueur. Outils utilisés : ChatGPT // pour la conception des plans et le world building
Runway -
CodeLLM Advances: Image Upload, Grok 3 Integration, Autocomplete Improvements
By
–
New CodeLLM Release – Upload images in Agents and generate code
– Grok 3 and Grok-3 mini in CodeLLM agents
– One more step change in Autocomplete Coming soon – Rich prompting
– Large code bases
– Better human-in-the-loop management -
VideoChat-R1: Spatio-Temporal Perception via Reinforcement Fine-Tuning
By
–
Chat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning This paper explores the use of Reinforcement Fine-Tuning (RFT) with Group Relative Policy Optimization (GRPO) to enhance spatio-temporal perception in video multimodal large language models (MLLMs),
-
MedSAM2: Foundation Model for 3D Medical Image Segmentation
By
–
MedSAM2: Segment Anything in 3D Medical Images and Videos MedSAM2 is a foundation model for 3D medical image and video segmentation, extending SAM2 to support volumetric and temporal data across diverse clinical tasks. Problem: Existing segmentation models are mostly limited to
-
SmolVLM: Efficient Vision-Language Models for Edge Devices
By
–
SmolVLM: Redefining small and efficient multimodal models SmolVLM is a family of highly efficient, small-scale vision-language models (VLMs) engineered for low-memory, real-time multimodal inference on mobile and edge devices. These models achieve competitive or even superior
-
Test-Time Training Enables One-Minute Video Generation
By
–
One-Minute Generation with Test-Time Training This paper augments Transformers with Test-Time Training (TTT) layers—neural networks used as hidden states—to generate coherent one-minute videos from text storyboards. Problem: Long video generation is bottlenecked by
-
Top 10 Papers: Video Generation and Multimodal AI Models
By
–
Huge week for video generation and multimodal models, with detailed one-minute video generation and more efficient approaches to multimodality Check out the top 10 papers for the week – Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
– One-Minute -
Gemini 2.0 Flash Enables Native Image Generation on Poe
By
–
Native image generation is available in Gemini 2.0 Flash Experimental at https://
poe.com/Gemini-2.0-Fla
sh-Exp
… and on all platforms where Poe is available. (3/3) -
Generate Text and Images Together in Single Request
By
–
You can also generate text and images together in one request. For example, it can create a short story about a topic while generating images for each scene based on your direction. (2/3) pic.twitter.com/KKbcfiz8Z1
— Poe (@poe_platform) 12 avril 2025You can also generate text and images together in one request. For example, it can create a short story about a topic while generating images for each scene based on your direction. (2/3)