Pixtral models are performing well on LMsys:
– Pixtral 12B is on par with Llama 3.2 90B
– Pixtral Large 123B is the best open-weight vision model by a large margin
MULTIMODAL AI
-
Pixtral Models Achieve Top Performance on LMsys Benchmark
By
–
-
Unsupervised model training before Whisper
By
–
You need to train an unsupervised voice classification model on the fly before sending it to Whisper.
-
Indic-Parler TTS: 20 Indian Languages Speech Synthesis Model
By
–
Introducing Indic-Parler TTS – Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! 🔥
— Vaibhav (VB) Srivastav (@reach_vb) 3 décembre 2024
A collaboration w/ @ai4bharat & @huggingface – w/ fully customisable speech and voice personas!
Try it out directly below or use… pic.twitter.com/8aagHcCT61Introducing Indic-Parler TTS – Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! A collaboration w/ @ai4bharat & @huggingface – w/ fully customisable speech and voice personas! Try it out directly below or use
-
WordPress categories for AI topics
By
–
Haven't tested myself but it should still work if you remake it with other (ideally several) censored names:
-
Contrastive Learning: Foundational Works in Self-Supervised Pre-Training
By
–
Self-supervision emerges as a common pre-training strategy in foundation models like DINO, CLIP, and Sapiens. A key approach within self-supervision is Contrastive Learning (CL).
— Satya Mallick (@LearnOpenCV) 3 décembre 2024
In this week's blog, the focus is on notable works that have shaped the early development of CL.… pic.twitter.com/AX8nLpL1CeSelf-supervision emerges as a common pre-training strategy in foundation models like DINO, CLIP, and Sapiens. A key approach within self-supervision is Contrastive Learning (CL). In this week's blog, the focus is on notable works that have shaped the early development of CL.
-
Google tests PDF to podcast conversion in Gemini
By
–
Google is working on a possibility to convert PDFs into podcasts within the Gemini app NotebookLM everywhere!
-
AI Pro Upgrade: Advanced Models and Reasoning at Coffee Price
By
–
If you’ve been waiting for a sign to go Pro, here it is. Upgrade today for 75% off your first month.
— Perplexity (@perplexity_ai) 2 décembre 2024
Access the latest AI models, file search, advanced reasoning, and one-click shopping — all for the price of a coffee. pic.twitter.com/epDZhhEbRTIf you’ve been waiting for a sign to go Pro, here it is. Upgrade today for 75% off your first month. Access the latest AI models, file search, advanced reasoning, and one-click shopping — all for the price of a coffee.
-
Make-It-Animatable: Automated 3D Character Rigging Framework
By
–
Make-It-Animatable Efficient framework for converting any 3D humanoid character into animation-ready form in under one second. Problem:
Rigging and skinning 3D characters are labor-intensive and existing methods fail to generalize across diverse shapes and poses. Method: -
Unified Diffusion Model for Image Generation and Understanding
By
–
One Diffusion to Generate Them All A unified diffusion model that can perform both image generation and understanding tasks through a simple sequence-based approach. Problem:
Diffusion models are task-specific, lacking the universality and flexibility seen in large language -
ShowUI: Lightweight Vision-Language Model for GUI Automation
By
–
ShowUI A lightweight vision-language model for efficient GUI automation that achieves SOTA performance while using fewer parameters and less training data. Problem:
GUI automation relying on APIs and metadata struggles with real-world visual scenarios requiring efficient,