Topics
Results for “attention”
52 results
- unsloth/Qwen3.8-Flash-Next-GGUF — Hugging Face Models · Seen
- Qwen/Qwen3.8-Flash-Next — Hugging Face Models · Seen
- Flide: Accelerating Decision Inference with Exact State Forking — Hugging Face Papers · Seen · 37 points
- A decoder-only foundation model for time-series forecasting — Hugging Face Papers · Seen · 49 points
- Efficient Memory Management for Large Language Model Serving with PagedAttention — Hugging Face Papers · Seen · 77 points
- Unlimited OCR Works — Hugging Face Papers · Seen · 106 points
- zai-org/GLM-5.3-Flash — Hugging Face Models · Seen
- Training-Free Acceleration of Multi-View 3D Transformers via Regime-Aware Attention Approximation — arXiv AI Papers · Seen
- You could have invented transformers from memory — 2 sources · Seen · 3 points
- Attention to Mamba: A Recipe for Cross-Architecture Distillation — Hacker News · Seen · 74 points
- Zellij 0.46: built-in terminal, attention inbox, session previews — Hacker News · Seen · 29 points
- ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation — arXiv AI Papers · Seen
- Show HN: Aq – an attention queue TUI for Claude Code — Hacker News · Seen · 8 points
- RadAI: Gaze-Intention Fusion Pipeline for Attention-Guided Educational Videos in Chest X-Ray Interpretation — arXiv AI Papers · Seen
- MAGE: Towards Generalizable Multi-timescale EEG Representations — arXiv AI Papers · Seen
- Adaptive Depth Aggregation in Graph Transformers for Long-Range Graph Reasoning — arXiv AI Papers · Seen
- Unlimited-OCR-2: Baidu open-sources an OCR model for unlimited-horizon parsing — 2 sources · Seen
- Octopus: One Brain, Many Branches for Latent-KV Multi-Agent Reinforcement Learning — arXiv AI Papers · Seen
- Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention — arXiv AI Papers · Seen
- Show HN: Interactive notes on RLHF, attention, LoRA and LLM evals — Hacker News · Seen · 40 points
- Diagnosing Zero-Shot Forgetting in CLIP Fine-Tuning: Attention Drift Characterizes Adaptation, Representation Drift Predicts Transfer Degradation — arXiv AI Papers · Seen
- A Trustworthy Clinical Decision Support Framework for Brain Tumor MRI Classification: Integrating Attention-Guided Learning, Explainable AI, and Out-of-Distribution Validation — arXiv AI Papers · Seen
- SFA: A Statistical Physics-Inspired Diffusion Transformer for Efficient and High-Quality Image Generation — arXiv AI Papers · Seen
- Beyond the Last Layer: Global Inter-Layer Aggregation for AI-Generated Image Detection — arXiv AI Papers · Seen
- Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training — Hugging Face Papers · Seen · 17 points
- Kernel-based Interpolatory Methods for Context Compression of Attention Mechanisms — arXiv AI Papers · Seen
- Show HN: Automatic deduction of FlashAttention kernel from ~25 lines of SQL — Hacker News · Seen · 22 points
- Alberta-made low-tech tractor getting attention worldwide — Hacker News · Seen · 15 points
- Buried Reads #1: Five Good Posts That Deserve More Attention — DEV Community · Seen
- World-in-Context: Interactive Video World Modeling with In-Context Conditioning — Hugging Face Papers · Seen · 34 points
- Layerwise Repacking: Variable-Length Hybrid-Attention Training without an Extra Redistribution Pass — arXiv AI Papers · Seen
- Attention Is Not What You Need — Hacker News · Seen · 190 points
- SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer — Hugging Face Papers · Seen · 56 points
- Attention people who think UB is fine — 2 sources · Seen · 77 points
- GANet: A Lightweight Group Attention Network for Plant Disease Identification on Embedded Systems — arXiv AI Papers · Seen
- Mortality Among People with Attention-Deficit/Hyperactivity Disorder — Hacker News · Seen · 131 points
- 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
- vllm-project/vllm — GitHub Trending · Seen
- SZED at ArGuard Shared Tasks: Multi-Task Label-Attention and Cross-Modal Fusion for Arabic Hateful Meme Detection — arXiv AI Papers · Seen
- Multimodal Ambivalence and Hesitancy Recognition with Bidirectional Audio--Text Cross-Attention — arXiv AI Papers · Seen
- Path-Conditioned Attention Mobility: From Depth to Execution Hubs in SegFormer — arXiv AI Papers · Seen
- FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching — Hugging Face Papers · Seen · 44 points
- Multics: Generative Multi-Player World Model with Hierarchical Communication — Hugging Face Papers · Seen · 70 points
- RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention — arXiv AI Papers · Seen
- Expanding Attention: A Taylor-Series Route to Linear-Time Transformers with a Fixed Number of Recurrent States — arXiv AI Papers · Seen
- Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming — arXiv AI Papers · Seen
- Joint Subspace Sparse Attention for Efficient Long-Context Decoding — arXiv AI Papers · Seen
- Multi-Stream Attention Residuals — Hugging Face Papers · Seen · 41 points
- DoSA: Dots Sparse Attention — 2 sources · Seen · 69 points
- Is 'Attention' the Essence of Intelligence? — Hacker News · Seen · 67 points
- Online Pornography Created the Model for Platform Capitalism — Hacker News · Seen · 8 points
- FrancisRing/Prism — Hugging Face Models · Seen