Hugging Face Blog
Granite 4.2 LLMs: How They're Built
Granite 4.2 LLMs: How They're Built
// espacio-latente.com / radar
Píldora diaria de lo que se mueve en IA: laboratorios, papers, blogs de referencia y releases relevantes, resumido y con link al original. Se actualiza dos veces al día. · ← volver a espacio-latente.com · archivo · RSS
Granite 4.2 LLMs: How They're Built
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
World humanoid robot games show runners breaking records, bursting into flames
AI won’t replace radiologists, but it will dramatically change their jobs
Apple's new desktop computers are designed specifically for local AI development
I spent a day at a robot “carnival” in Shanghai. Here’s what I saw.
Taming Visual Neglect: A Variational Information Bottleneck Framework for Adaptive Attention in Multimodal In-Context Learning
From Triage to Discharge: A Survey of NLP Tasks, Methods, and Open Challenges in the Emergency Department
Contextual Embedding Evidence for Main--Light Verb Distinctions in Urdu
The Limits of Automatic Evaluation of Creativity in Large Language Models
ADE: Agentic Data Evolution Framework for Human-Centered Objectives
What Reaches Expert Review? Representation, Structural Screening, and Candidate-Form Dependence in AI-Assisted Item Development
When Youth Enter The Chat: An Epistemic Shift in the Validation of LLM-Based Measures of Student Talk
Inter-dimension Dependence for Multi-Dimensional Evaluation of Open-Ended Text
Giga-Embeddings: Mixture-of-Experts Encoders for High-Throughput Text Embeddings
From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers
Beyond Static and Linear: What Attention Constraints Best Fit Human Reading Times?
Mitigating Exploration Bias in RL for Multi-Instruction Following
Does Episodic Memory Help Close the Lexical Frequency Gap in Sensitivity to Syntactic Contrasts? A Test Using Retrieval-Augmented Language Models
Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs
Investigating Knowledge Transfer Across Interactive Dialogue Games
AgentSpec: Speculative Decoding for Batch Inference of LLM Agents
SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding
Curved Inference II: Sleeper Agent Geometry - Extending Interpretability Beyond Probes
The full stack behind abundant intelligence
Jalapeño’s first results show industry-leading speed and efficiency in AI inference
AgentHands: Generating interactive hand gestures for spatially grounded agent conversations in XR
EVE Online: The Move to Python 3 Begins!
GLM-5.3-Flash
An ongoing 3D-printer AGPL violation
AWS Acquires DuckLabs
Study Reveals UnitedHealth's Profit Margins Four Times What It Claimed [pdf]
Tailcat
Disruption with Some GitHub Services
Qwen3.8-Flash-Next
Nebula Sans
Taylor Farms: How One Company's Reach Became a National Risk
Tim Curry has died
The Tariff Cost: analysis of the costs to Americans from new tariffs on Canada
CoMaps: The Offline App That Guided Rescuers Without a Signal in Venezuela
v0.33.0
Intelligent transcription with Gemini 3.5 Transcribe
The Future of SaaS Is Apps That Agents Can Use
🔬“We have foundation models for language, not for physics” — Anima Anandkumar, Bren Professor of Computing
Google’s new AI transcription edits out your ‘ums’ and ‘ahs’
Bill Gates is deeply worried about AI, and he’s no longer staying quiet
Radar makes podcasts searchable — and usable by AI agents
Ex-Meta scientists want to bring visual AI to the factory floor
Bill Gates wants to see a robot tax and ‘Human Reserved’ jobs to mitigate harms from AI
Surprise: Z.ai is the AI lab behind the mysterious Ox Alpha model
Robot brain builders are pushing out of their GPT-2 era
QueryStory wants you to believe what AI is telling you
Arga Labs is building a better way to train enterprise AI agents
Hearing tech startup Legato emerges from stealth with $12M and a peek at its AI hearing glasses
Runable hits $21M to bet AI agents can go from building businesses to growing them
India’s Ringg gets backing from Peak XV as it pushes voice AI past the phone call
Robotics startup Generalist reaches $3B valuation, sources say
OpenAI loses a top data center exec as stream of high-profile departures continues
Stability AI, maker of image generator Stable Diffusion, raises $76 million in fresh funding
Equivariant Cellular Sheaves for Molecular Electronic Structure: Bridging Sheaf Cohomology and E(3)-Equivariant Hamiltonian Learning
Data Predictability Shapes Weibull Weight-Scale Growth in Transformer Training
From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers
Renormalization Group Flow Matching for Scalable Local Generative Modeling
Construir este día costó 57.295 tokens de entrada y 0 de salida en 63 llamadas a modelos — unos 0,0573 $.