This media is not supported in your browser
VIEW IN TELEGRAM
Adding TTT layers into a pre-trained Transformer enables generating a one-minute clip from text storyboards.
Videos, code & annotations released
#AI #VideoGeneration #MachineLearning #DeepLearning #Transformers #TTT #GenerativeAI
Please open Telegram to view this post
VIEW IN TELEGRAM
👍3🥰2
🚀 The new HQ-SAM (High-Quality Segment Anything Model) has just been added to the Hugging Face Transformers library!
This is an enhanced version of the original SAM (Segment Anything Model) introduced by Meta in 2023. HQ-SAM significantly improves the segmentation of fine and detailed objects, while preserving all the powerful features of SAM — including prompt-based interaction, fast inference, and strong zero-shot performance. That means you can easily switch to HQ-SAM wherever you used SAM!
The improvements come from just a few additional learnable parameters. The authors collected a high-quality dataset with 44,000 fine-grained masks from various sources, and impressively trained the model in just 4 hours using 8 GPUs — all while keeping the core SAM weights frozen.
The newly introduced parameters include:
* A High-Quality Token
* A Global-Local Feature Fusion mechanism
This work was presented at NeurIPS 2023 and still holds state-of-the-art performance in zero-shot segmentation on the SGinW benchmark.
📄 Documentation: https://lnkd.in/e5iDT6Tf
🧠 Model Access: https://lnkd.in/ehS6ZUyv
💻 Source Code: https://lnkd.in/eg5qiKC2
#ArtificialIntelligence #ComputerVision #Transformers #Segmentation #DeepLearning #PretrainedModels #ResearchAndDevelopment #AdvancedModels #ImageAnalysis #HQ_SAM #SegmentAnything #SAMmodel #ZeroShotSegmentation #NeurIPS2023 #AIresearch #FoundationModels #OpenSourceAI #SOTA
🌟https://t.me/DataScienceN
This is an enhanced version of the original SAM (Segment Anything Model) introduced by Meta in 2023. HQ-SAM significantly improves the segmentation of fine and detailed objects, while preserving all the powerful features of SAM — including prompt-based interaction, fast inference, and strong zero-shot performance. That means you can easily switch to HQ-SAM wherever you used SAM!
The improvements come from just a few additional learnable parameters. The authors collected a high-quality dataset with 44,000 fine-grained masks from various sources, and impressively trained the model in just 4 hours using 8 GPUs — all while keeping the core SAM weights frozen.
The newly introduced parameters include:
* A High-Quality Token
* A Global-Local Feature Fusion mechanism
This work was presented at NeurIPS 2023 and still holds state-of-the-art performance in zero-shot segmentation on the SGinW benchmark.
📄 Documentation: https://lnkd.in/e5iDT6Tf
🧠 Model Access: https://lnkd.in/ehS6ZUyv
💻 Source Code: https://lnkd.in/eg5qiKC2
#ArtificialIntelligence #ComputerVision #Transformers #Segmentation #DeepLearning #PretrainedModels #ResearchAndDevelopment #AdvancedModels #ImageAnalysis #HQ_SAM #SegmentAnything #SAMmodel #ZeroShotSegmentation #NeurIPS2023 #AIresearch #FoundationModels #OpenSourceAI #SOTA
🌟https://t.me/DataScienceN
lnkd.in
LinkedIn
This link will take you to a page that’s not on LinkedIn
❤2👍2🔥1
🔥 Trending Repository: haystack
📝 Description: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
🔗 Repository URL: https://github.com/deepset-ai/haystack
🌐 Website: https://haystack.deepset.ai
📖 Readme: https://github.com/deepset-ai/haystack#readme
📊 Statistics:
🌟 Stars: 22.3K stars
👀 Watchers: 158
🍴 Forks: 2.3K forks
💻 Programming Languages: Python - HTML
🏷️ Related Topics:
==================================
🧠 By: https://t.me/DataScienceM
📝 Description: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
🔗 Repository URL: https://github.com/deepset-ai/haystack
🌐 Website: https://haystack.deepset.ai
📖 Readme: https://github.com/deepset-ai/haystack#readme
📊 Statistics:
🌟 Stars: 22.3K stars
👀 Watchers: 158
🍴 Forks: 2.3K forks
💻 Programming Languages: Python - HTML
🏷️ Related Topics:
#python #nlp #agent #machine_learning #information_retrieval #ai #transformers #orchestration #pytorch #gemini #question_answering #summarization #agents #semantic_search #rag #gpt_4 #large_language_models #llm #generative_ai #retrieval_augmented_generation
==================================
🧠 By: https://t.me/DataScienceM
🔥 Trending Repository: LLaMA-Factory
📝 Description: Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
🔗 Repository URL: https://github.com/hiyouga/LLaMA-Factory
🌐 Website: https://llamafactory.readthedocs.io
📖 Readme: https://github.com/hiyouga/LLaMA-Factory#readme
📊 Statistics:
🌟 Stars: 61.3K stars
👀 Watchers: 295
🍴 Forks: 7.4K forks
💻 Programming Languages: Python
🏷️ Related Topics:
==================================
🧠 By: https://t.me/DataScienceM
📝 Description: Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
🔗 Repository URL: https://github.com/hiyouga/LLaMA-Factory
🌐 Website: https://llamafactory.readthedocs.io
📖 Readme: https://github.com/hiyouga/LLaMA-Factory#readme
📊 Statistics:
🌟 Stars: 61.3K stars
👀 Watchers: 295
🍴 Forks: 7.4K forks
💻 Programming Languages: Python
🏷️ Related Topics:
#nlp #agent #ai #transformers #moe #llama #gpt #lora #quantization #gemma #fine_tuning #peft #large_language_models #llm #rlhf #instruction_tuning #qlora #qwen #deepseek #llama3
==================================
🧠 By: https://t.me/DataScienceM
🔥 Trending Repository: mlx-audio
📝 Description: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
🔗 Repository URL: https://github.com/Blaizzy/mlx-audio
📖 Readme: https://github.com/Blaizzy/mlx-audio#readme
📊 Statistics:
🌟 Stars: 3.4K stars
👀 Watchers: 32
🍴 Forks: 285 forks
💻 Programming Languages: Python - TypeScript
🏷️ Related Topics:
==================================
🧠 By: https://t.me/DataScienceM
📝 Description: A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
🔗 Repository URL: https://github.com/Blaizzy/mlx-audio
📖 Readme: https://github.com/Blaizzy/mlx-audio#readme
📊 Statistics:
🌟 Stars: 3.4K stars
👀 Watchers: 32
🍴 Forks: 285 forks
💻 Programming Languages: Python - TypeScript
🏷️ Related Topics:
#text_to_speech #transformers #speech_synthesis #speech_recognition #speech_to_text #audio_processing #mlx #multimodal #apple_silicon
==================================
🧠 By: https://t.me/DataScienceM
🔥 Trending Repository: Megatron-LM
📝 Description: Ongoing research training transformer models at scale
🔗 Repository URL: https://github.com/NVIDIA/Megatron-LM
🌐 Website: https://docs.nvidia.com/megatron-core/developer-guide/latest/get-started/quickstart.html
📖 Readme: https://github.com/NVIDIA/Megatron-LM#readme
📊 Statistics:
🌟 Stars: 15.3K stars
👀 Watchers: 174
🍴 Forks: 3.6K forks
💻 Programming Languages: Python
🏷️ Related Topics:
==================================
🧠 By: https://t.me/DataScienceM
📝 Description: Ongoing research training transformer models at scale
🔗 Repository URL: https://github.com/NVIDIA/Megatron-LM
🌐 Website: https://docs.nvidia.com/megatron-core/developer-guide/latest/get-started/quickstart.html
📖 Readme: https://github.com/NVIDIA/Megatron-LM#readme
📊 Statistics:
🌟 Stars: 15.3K stars
👀 Watchers: 174
🍴 Forks: 3.6K forks
💻 Programming Languages: Python
🏷️ Related Topics:
#transformers #model_para #large_language_models
==================================
🧠 By: https://t.me/DataScienceM