Announcing the 2025 NDSA Excellence Award Winners
ndsa.org·10h
🏛️PREMIS Metadata
Welcome to LIL’s Data.gov Archive Search
lil.law.harvard.edu·3h
💾Data Preservation
Paper2Agent: Research Papers as Interactive AI Agents
huggingface.co·7h·
Discuss: Hacker News
🤖AI Curation
Speed Matters: How We Achieve the Fastest Web Agent
browser-use.com·1d·
Discuss: Hacker News
🎬WebCodecs
Improving Temporal Understanding Logic Consistency in Video-Language Models via Attention Enhancement
arxiv.org·19h
📊Learned Metrics
Customizing text content moderation with Amazon Nova
aws.amazon.com·1d
📊Feed Optimization
Meet Amazon Quick Suite: The agentic AI application reshaping how work gets done
aboutamazon.com·1d·
Discuss: Hacker News
🌊Streaming Systems
CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning
arxiv.org·19h
🧮Vector Embeddings
10 Data + AI Observations for Fall 2025
towardsdatascience.com·9h
🌊Stream Processing
Automated Copyright Infringement Detection via Semantic Fingerprinting and Dynamic Thresholding
dev.to·2d·
Discuss: DEV
👁️Perceptual Hashing
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
arxiv.org·1d
💻Local LLMs
Retentive Relevance: Capturing Long-Term User Value in Recommendation Systems
arxiv.org·19h
🎯Content Recommendation
Instance Relation Learning Network with Label Knowledge Propagation for Few-shot Multi-label Intent Detection
arxiv.org·19h
🤖Grammar Induction
Inconsistent Affective Reaction: Sentiment of Perception and Opinion in Urban Environments
arxiv.org·19h
🎛️Feed Filtering
ACMID: Automatic Curation of Musical Instrument Dataset for 7-Stem Music Source Separation
arxiv.org·19h
🎵Audio Formats
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
arxiv.org·19h
💻Local LLMs
MetaGraph: Scalable annotated de Bruijn graphs for DNA indexing and alignment
github.com·1d·
Discuss: Hacker News
🔄Burrows-Wheeler
Scalable Semantic Map Generation via Hierarchical Graph Optimization
dev.to·3h·
Discuss: DEV
⚡Incremental Computation
Is Architectural Complexity Always the Answer? A Case Study on SwinIR vs. an Efficient CNN
arxiv.org·19h
🤖Advanced OCR
Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
arxiv.org·1d
🧠Learned Indexes