Contrastive Weak-to-strong Generalization
arxiv.org·15h
⧗Information Bottleneck
Efficient and accurate search in petabase-scale sequence repositories
nature.com·2d·
Discuss: Hacker News
🔄Burrows-Wheeler
Doing Math with Embeddings for Better AI Ad Targeting
ethicalads.io·1d·
Discuss: Hacker News
📊Feed Optimization
Beyond Vector Search: Building a RAG That *Actually* Understands Your Data
dev.to·1d·
Discuss: DEV
🗂️Vector Databases
Mind the Gap: Quantifying Vocabulary Mismatch in E-Commerce Site Search
searchhub.io·1d·
Discuss: Hacker News
📈Search Quality
Addressing the ID-Matching Challenge in Long Video Captioning
arxiv.org·1d
🤖Advanced OCR
An enough week
blog.mitrichev.ch·23h·
Discuss: blog.mitrichev.ch
🧮Z3 Solver
Homomorphism Problems in Graph Databases and Automatic Structures
arxiv.org·15h
🔗Graph Isomorphism
In-Depth Analysis: "Attention Is All You Need"
dev.to·4h·
Discuss: DEV
🧠Intelligence Compression
CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning
arxiv.org·15h
🧮Vector Embeddings
Nearest Neighbor CCP-Based Molecular Sequence Analysis
arxiv.org·15h
🔄Burrows-Wheeler
From Keywords to Clusters: AI-Driven Analysis of YouTube Comments to Reveal Election Issue Salience in 2024
arxiv.org·15h
📊Feed Optimization
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
huggingface.co·1d·
Discuss: Hacker News
📊Learned Metrics
Fast-Convergent Proximity Graphs for Approximate Nearest Neighbor Search
arxiv.org·2d
📏Range Queries
Parameterized Complexity of s-Club Cluster Edge Deletion
arxiv.org·1d
🧮Kolmogorov Complexity
Estimating Fair Graphs from Graph-Stationary Data
arxiv.org·15h
🌈Spectral Methods
Exponential Error Bounds for Information Bottleneck Source Coding Problems
arxiv.org·15h
📐Compression Bounds
DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
arxiv.org·15h
🌀Differential Geometry
SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
arxiv.org·15h
🧠Neural Codecs
MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
arxiv.org·15h
🧠Learned Codecs