🔪 Knife Skills - emschwartz · Scour

Now 🎯Deep Work

murugappan.com·2d

Hikarigami Lighting Forges New Finishing Techniques 💎EUV Lithography

design-milk.com·4d

A lost 1812 wristwatch sparked a 200-year race in precision engineering ⏳Tech History

scientificamerican.com

·20h

Tipiano: Cascaded Piano Hand Motion Synthesis via Fingertip Priors 🐘pgvector

arxiv.org·1d

Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees 🧠LLM Inference

arxiv.org·6d

Dual-Branch Remote Sensing Infrared Image Super-Resolution 🚀Astral

arxiv.org·1d

CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts 🧠LLM Inference

arxiv.org·1d

WebExpert: domain-aware web agents with critic-guided expert experience for high-precision search 🕷️Web Crawling

arxiv.org·6d

FineEdit: Fine-Grained Image Edit with Bounding Box Guidance 👨‍💻AI Coding

arxiv.org·1d

A H.265/HEVC Fine-Grained ROI Video Encryption Algorithm Based on Coding Unit and Prompt Segmentation 🗜️Vector Compression

arxiv.org·5d

Quantization Dominates Rank Reduction for KV-Cache Compression 🗜️Vector Compression

arxiv.org·1d

Points-to Analysis Using MDE: A Multi-level Deduplication Engine for Repetitive Data and Operations 💾Binary Formats

arxiv.org·1d

DietDelta: A Vision-Language Approach for Dietary Assessment via Before-and-After Images 🎯Semantic Tokens

arxiv.org·6d

PASTA: Vision Transformer Patch Aggregation for Weakly Supervised Target and Anomaly Segmentation 📊Embeddings

arxiv.org·1d

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch 🧠LLM Inference

arxiv.org·5d

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing 🧠LLM Inference

arxiv.org·5d

TAMEn: Tactile-Aware Manipulation Engine for Closed-Loop Data Collection in Contact-Rich Tasks ✨Gemini

arxiv.org·6d

Score Shocks: The Burgers Equation Structure of Diffusion Generative Models 📊Embeddings

arxiv.org·5d

Initialisation Determines the Basin: Efficient Codebook Optimisation for Extreme LLM Quantization 🧠LLM Inference

arxiv.org·5d

STQuant: Spatio-Temporal Adaptive Framework for Optimizer Quantization in Large Multimodal Model Training 📦Batch Embeddings

arxiv.org·6d

No more posts from emschwartz's subscribed feeds.

Scour all 23985 feeds Learn more about Feeds