How To Scale Your Model, by DeepMind
Explorar
Noticias de IA
21861 elementos — filtrados, clasificados y sin duplicados
DABStep: Data Agent Benchmark for Multi-step Reasoning
π0 and π0-FAST: Vision-Language-Action Models for General Robot Control
What Is Retrieval-Augmented Generation, aka RAG?
Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial
Open-R1: a fully open reproduction of DeepSeek-R1
State of open video generation models in Diffusers
TinyZero: Reproduce DeepSeek R1-Zero for $30
AI Maps Titan’s Methane Clouds in Record Time
Mastering Long Contexts in LLMs with KVPress
Trading inference-time compute for adversarial robustness
Titans: Learning to Memorize at Test Time
Visual Document Retrieval Goes Multilingual
not much happened today
CO₂ Emissions and Models Performance: Insights from the Open LLM Leaderboard
PRIME: Process Reinforcement through Implicit Rewards
not much happened to end the year
Deliberative alignment: reasoning enables safer language models
Evaluating Audio Reasoning with Big Bench Audio
Genesis: Generative Physics Engine for Robotics (o1-2024-12-17)
Benchmarking Language Model Performance on 5th Gen Xeon at GCP
LeMaterial: an open source initiative to accelerate materials discovery and research
Open Preference Dataset for Text-to-Image Generation by the 🤗 Community
How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUs
Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard
Investing in Performance: Fine-tune small models with LLM insights - a CFM case study
You could have designed state of the art positional encoding
Faster Text Generation with Self-Speculative Decoding
Letting Large Models Debate: The First Multilingual LLM Debate Competition
Judge Arena: Benchmarking LLMs as Evaluators