Contrastive Weak-to-strong Generalization
arxiv.orgยท15h
โง—Information Bottleneck
Efficient and accurate search in petabase-scale sequence repositories
nature.comยท2dยท
Discuss: Hacker News
๐Ÿ”„Burrows-Wheeler
Doing Math with Embeddings for Better AI Ad Targeting
ethicalads.ioยท1dยท
Discuss: Hacker News
๐Ÿ“ŠFeed Optimization
Beyond Vector Search: Building a RAG That *Actually* Understands Your Data
dev.toยท1dยท
Discuss: DEV
๐Ÿ—‚๏ธVector Databases
Mind the Gap: Quantifying Vocabulary Mismatch in E-Commerce Site Search
searchhub.ioยท1dยท
Discuss: Hacker News
๐Ÿ“ˆSearch Quality
Addressing the ID-Matching Challenge in Long Video Captioning
arxiv.orgยท1d
๐Ÿค–Advanced OCR
An enough week
blog.mitrichev.chยท23hยท
๐ŸงฎZ3 Solver
Homomorphism Problems in Graph Databases and Automatic Structures
arxiv.orgยท15h
๐Ÿ”—Graph Isomorphism
In-Depth Analysis: "Attention Is All You Need"
dev.toยท4hยท
Discuss: DEV
๐Ÿง Intelligence Compression
CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning
arxiv.orgยท15h
๐ŸงฎVector Embeddings
Nearest Neighbor CCP-Based Molecular Sequence Analysis
arxiv.orgยท15h
๐Ÿ”„Burrows-Wheeler
From Keywords to Clusters: AI-Driven Analysis of YouTube Comments to Reveal Election Issue Salience in 2024
arxiv.orgยท15h
๐Ÿ“ŠFeed Optimization
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
huggingface.coยท1dยท
Discuss: Hacker News
๐Ÿ“ŠLearned Metrics
Fast-Convergent Proximity Graphs for Approximate Nearest Neighbor Search
arxiv.orgยท2d
๐Ÿ“Range Queries
Parameterized Complexity of s-Club Cluster Edge Deletion
arxiv.orgยท1d
๐ŸงฎKolmogorov Complexity
Estimating Fair Graphs from Graph-Stationary Data
arxiv.orgยท15h
๐ŸŒˆSpectral Methods
Exponential Error Bounds for Information Bottleneck Source Coding Problems
arxiv.orgยท15h
๐Ÿ“Compression Bounds
DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
arxiv.orgยท15h
๐ŸŒ€Differential Geometry
SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
arxiv.orgยท15h
๐Ÿง Neural Codecs
MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
arxiv.orgยท15h
๐Ÿง Learned Codecs