Topics
Results for “ai model training”
23 results
- Chinese frontier AI models carry the fingerprint of export-controlled GPUs — Hacker News · Seen · 450 points
- MinimaLabs/KLM-1.6 — Hugging Face Models · Seen
- ricursiveAI/Ripple-65B-Preview — Hugging Face Models · Seen
- Token Pooling-Aware Training for Multi-Vector Embedding Models — Hugging Face Blog · Seen
- TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing — Hugging Face Papers · Seen · 43 points
- DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models — Hugging Face Papers · Seen · 248 points
- CoworkOS:Scaling Agent Coworkers for Real-world Automation — Hugging Face Papers · Seen · 100 points
- Role-based Effectiveness of an Epistemic Uncertainty Estimate in Training Models for Semantic Segmentation of 3D LiDAR Point Clouds — arXiv AI Papers · Seen
- We're Training a Figma-Fluent Editing Model — Hacker News · Seen · 149 points
- Auditing a Model-Hub Benchmark: Data Quality, Training Budgets, and Side Information in HuggingBench — arXiv AI Papers · Seen
- OpenAI seems to be silently re-enabling model training on Codex chats — Hacker News · Seen · 514 points
- Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training — Hugging Face Papers · Seen · 17 points
- Anthropic blocks users for anything touching training larger models — Hacker News · Seen · 487 points
- Heretic 2.0 Released: Training-free language model modification — Hacker News · Seen · 15 points
- Locating Sycophancy Across Training Stages in Open Language Models — arXiv AI Papers · Seen
- Artifact Distillation: Training-Free Transfer from Frontier to Small Language Models — arXiv AI Papers · Seen
- OpenAI: Securing our frontier model training environment — 2 sources · Seen
- Beyond the KV cache: Training and serving i14’s Laplace 3B linear attention model on AWS Trainium2 with native PyTorch — AWS Machine Learning Blog · Seen
- Speedrunning Relational Foundation Model Pretraining — arXiv AI Papers · Seen
- TRACE: Training-aware Robustness and Challenge Evaluation for Text-Vision Embedding Models — arXiv AI Papers · Seen
- FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models — arXiv AI Papers · Seen
- Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data — arXiv AI Papers · Seen
- SpatialLM: Training Large Language Models for Structured Indoor Modeling — Hugging Face Papers · Seen · 54 points