Mundo: From seeing a place to simulating what happens there
Luo-Yihang
• • 66Community Blog & Articles
Community Articles
view all
Granite Switch 4.1.1 — Update models like you update software
2
October 29, 2026 
swiftmlxcoreml
Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms
1
October 29, 2026 
NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
67
October 28, 2026 
Build specialized multimodal models with LFM3
72
October 27, 2026 
Can we trust LLMs to judge whether a research idea is novel?
13
October 27, 2026 
neurontorchtransformers
Does Your Model Run on AWS Trainium? Look It Up
31
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 
pytorchmpsapple
MPS in PyTorch 2.15
32
October 20, 2026 
open-sourcetorchneuron
TorchNeuron: running HF models on AWS Trainium is easier than ever
- +3
32
October 19, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Mundo: From seeing a place to simulating what happens there
Luo-Yihang
• • 66A curriculum for post-training agents
huggingface
• • 60Announcing SimReady Central: An Open Library of Simulation-Ready 3D Assets for Robotics and AI Factories
nvidia
• • 53LitPivot: Developing research ideas through dynamic contextualization within the literature landscape
allenai
• • 38NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models
nvidia
• • 60Introducing A5: Proactive Personal Agent in Your Life-Long Context
KYLN24
• • 25NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required
nvidia
• • 34Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster
ibm-granite
• • 34OlmoEarth v1.3: State-of-the-art embeddings for the whole planet
allenai
• • 15Train in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0
nvidia
• • 21What's new in the hf CLI and huggingface_hub library
huggingface
• • 12Pretraining a 325M Language Model from Zero on an Inference-Only NPU
FINAL-Bench
• • 9In financial services, the AI question is moving from the model to where it runs
Farsight-AI
• • 9Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint
ibm-granite
• • 78DecisionFormer
FrontiersMind
• • 8Two Pure-Vision Pipelines at the Top of ViDoRe V3
Ryenhails
• • 7Uncensor any LLM with abliteration
mlabonne
• • 943bekko-static-embedding-v1: State-of-the-Art Retrieval for Multilingual Static Embeddings
hotchpotch
• • 17SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers
lightonai
• • 27Do LLM Routers Actually Route? Quick answer: Not much!
PeterKruger
• • 5