NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
nvidia
• • 82Community Blog & Articles
Community Articles
view all
nemotron-halloween
1
October 30, 2026 
Granite Switch 4.1.1 — Update models like you update software
17
October 29, 2026 
open-sourcesciencedatasets
Announcing Project ProtoStar: Making Publicly Funded Science AI-Ready
- +3
16
October 29, 2026 
transformersmistralvllm
Welcome Le Chonk: Mistral Large 4 on Hugging Face
- +7
47
October 29, 2026 
swiftmlxcoreml
Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms
10
October 29, 2026 
Build specialized multimodal models with LFM3
77
October 27, 2026 
Can we trust LLMs to judge whether a research idea is novel?
14
October 27, 2026 
neurontorchtransformers
Does Your Model Run on AWS Trainium? Look It Up
32
October 23, 2026 
Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
22
October 22, 2026 
Ensemble forecasting with IBM Granite time-series models
25
October 22, 2026 
How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications
37
October 21, 2026 
Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.
13
October 21, 2026 
tpugooglegcp
Hugging Face ❤️ TorchTPU: TPUs, Natively
- +1
51
October 20, 2026 
swiftllmmlx
AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms
6
October 20, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
nvidia
• • 82A curriculum for post-training agents
huggingface
• • 82Mundo: From seeing a place to simulating what happens there
Luo-Yihang
• • 74LitPivot: Developing research ideas through dynamic contextualization within the literature landscape
allenai
• • 39Announcing SimReady Central: An Open Library of Simulation-Ready 3D Assets for Robotics and AI Factories
nvidia
• • 55Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster
ibm-granite
• • 36Introducing A5: Proactive Personal Agent in Your Life-Long Context
KYLN24
• • 27NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required
nvidia
• • 35Introducing Lumma-Fev-v2
FrontiersMind
• • 14NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models
nvidia
• • 63What's new in the hf CLI and huggingface_hub library
huggingface
• • 13Train in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0
nvidia
• • 23Clover\-35B\-A3B\-Preview: A New Way for Intelligence
Diffuspace
• • 9DecisionFormer
FrontiersMind
• • 9Pretraining a 325M Language Model from Zero on an Inference-Only NPU
FINAL-Bench
• • 9Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint
ibm-granite
• • 79Uncensor any LLM with abliteration
mlabonne
• • 944Do LLM Routers Actually Route? Quick answer: Not much!
PeterKruger
• • 6A Low-Cost Decision Model on CPU: Optimizing DiffusionGemma with vLLM - Part I
LeagueLabs
• • 5Try an LLM Router That Actually Routes ($1 free credit)
PeterKruger
• • 5