Topics
Results for “transformers”
52 results
- Abiray/MiniMax-H3-Image-GGUF — Hugging Face Models · Seen
- facebook/dinov3-vitl16-pretrain-lvd1689m — Hugging Face Models · Seen
- MiniMaxAI/MiniMax-H3 — Hugging Face Models · Seen
- JVT: Just Video Transformer makes pixel-space video diffusion simple — Hugging Face Papers · Seen · 15 points
- SUPRA-TEX: 3D Generation with Super-Aligned Texture — Hugging Face Papers · Seen · 14 points
- MOSS-Image Technical Report — Hugging Face Papers · Seen · 93 points
- HuggingFace's Transformers: State-of-the-art Natural Language Processing — Hugging Face Papers · Seen · 34 points
- YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality — Hugging Face Papers · Seen · 157 points
- How Open-Source LLMs Differ: Comparing 130+ Model Architectures — DEV Community · Seen
- meta-llama/Meta-Llama-3-8B-Instruct — Hugging Face Models · Seen
- Training-Free Acceleration of Multi-View 3D Transformers via Regime-Aware Attention Approximation — arXiv AI Papers · Seen
- Understanding Positional Embeddings in Modern LLMs — Hacker News · Seen · 241 points
- You could have invented transformers from memory — 2 sources · Seen · 3 points
- Thompson Sampling using Prior-fitted Diffusion Transformers — arXiv AI Papers · Seen
- Token Pooling-Aware Training for Multi-Vector Embedding Models — Hugging Face Blog · Seen
- Show HN: DRS-VPT. Localize a photo in a 3D point cloud without an initial pose — Hacker News · Seen · 9 points
- Decision Models in Hugging Face — Hugging Face Blog · Seen
- Attention to Mamba: A Recipe for Cross-Architecture Distillation — Hacker News · Seen · 74 points
- Can a Linear Program Do Weight-Space Programming? — Hacker News · Seen · 291 points
- 37% on ARC-AGI-2 Kaggle Without LLMs — Hacker News · Seen · 3 points
- Edge0/Audio8-TTS-Realistic-Air — Hugging Face Models · Seen
- Adaptive Depth Aggregation in Graph Transformers for Long-Range Graph Reasoning — arXiv AI Papers · Seen
- sensenova/SenseNova-Loop-9B-Preview — Hugging Face Models · Seen
- Quadrillion-parameter transformers and how to train them — Hacker News · Seen · 64 points
- A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks. — Hugging Face Blog · Seen
- StateBench: Testing how language models track state changes over long documents — Hugging Face Blog · Seen
- Transformers Model Integration Contracts — Hugging Face Blog · Seen
- shiyu-coder/Kronos — GitHub Trending · Seen
- SFA: A Statistical Physics-Inspired Diffusion Transformer for Efficient and High-Quality Image Generation — arXiv AI Papers · Seen
- Output-Aware Block Influence: Jacobian-Lens Weighting for Depth Pruning — arXiv AI Papers · Seen
- LiquidAI/LFM3-1.7B-Base — Hugging Face Models · Seen
- Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers — Hugging Face Papers · Seen · 27 points
- Edge0/Audio8-TTS-Realistic-0.6b — Hugging Face Models · Seen
- Recurrent Looped Transformer — Hugging Face Papers · Seen · 24 points
- mistralai/Timestral-209M — Hugging Face Models · Seen
- tencent/Hy-Nomas — 2 sources · Seen
- Build specialized multimodal models with LFM3 — Hugging Face Blog · Seen
- Aligned Delta-Triplane Transformers as Occupancy World Models — arXiv AI Papers · Seen
- PaECTER: Patent-level Representation Learning using Citation-informed Transformers — arXiv AI Papers · Seen
- Bank alerts to a day-book, with a local Gemma — DEV Community · Seen
- Does Your Model Run on AWS Trainium? Look It Up — Hugging Face Blog · Seen
- STAR-XPC: Set Transformer for Estimating X-ray Transmission in Polymer Composites — arXiv AI Papers · Seen
- Transformers Learn Two Competing Sorting Algorithms, and Only One Length-Generalizes — arXiv AI Papers · Seen
- Your Browser Can Do WHAT?! 5 AI Features That Actually Work — DEV Community · Seen
- Expanding Attention: A Taylor-Series Route to Linear-Time Transformers with a Fixed Number of Recurrent States — arXiv AI Papers · Seen
- PairIT: Autoregressive Transformers for Low-Data Molecule Optimization — arXiv AI Papers · Seen
- Filter, reshape, and redact logs before export with Transformers — Cloudflare Blog · Seen
- Rotate the Loop: Blockwise Conformality for Looped Transformers — arXiv AI Papers · Seen
- How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings — arXiv AI Papers · Seen
- Is 'Attention' the Essence of Intelligence? — Hacker News · Seen · 67 points
- Kevin Kelly's 2016 AI Predictions, 10 Years Later — Hacker News · Seen · 216 points
- Running RAG with a (small) language model in the browser — Lobsters · Seen · 2 points