📄 Text Chunking

Semantic Segmentation, Context Windows, Document Boundaries, Retrieval Units

A.I. Is Homogenizing Our Thoughts
newyorker.com·13h
🏛Digital humanities
Detect Narrative Threats with AI Personas
askrally.com·2d·
Discuss: Hacker News
📡Feed Archaeology
ReFrame: Rectification Framework for Image Explaining Architectures
arxiv.org·2d
📊Learned Metrics
Powering Smarter AI with Precision — Image Data Annotation at AkbhcodeAI
dev.to·1d·
Discuss: DEV
🤖Advanced OCR
Context Consistency Learning via Sentence Removal for Semi-Supervised Video Paragraph Grounding
arxiv.org·2d
📝Document Chunking
Learning-based safety lifting monitoring system for cranes on construction sites
arxiv.org·35m
📄Document Digitization
Conversational Intent-Driven GraphRAG: Enhancing Multi-Turn Dialogue Systems through Adaptive Dual-Retrieval of Flow Patterns and Context Semantics
arxiv.org·1d
🧮Prolog Parsing
Referring Expression Instance Retrieval and A Strong End-to-End Baseline
arxiv.org·2d
🔍Semantic Search
Machine Learning Fundamentals: active learning tutorial
dev.to·12h·
Discuss: DEV
🎛️Feed Filtering
Semantic Outlier Removal with Embedding Models and LLMs
arxiv.org·3d
🔍Information Retrieval
Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation
arxiv.org·1d
🤖Advanced OCR
Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems
arxiv.org·35m
📚Digital Humanities
Multimodal Political Bias Identification and Neutralization
arxiv.org·2d
🤖Advanced OCR
Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR
arxiv.org·35m
🎙️Whisper
Retrieval-Augmented Generation (RAG) System Architecture and Workflow
dev.to·1d·
Discuss: DEV
🔍Information Retrieval
NaviAgent: Bilevel Planning on Tool Dependency Graphs for Function Calling
arxiv.org·1d
🔗Topological Sorting
Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
arxiv.org·35m
🤖Advanced OCR
CLGRPO: Reasoning Ability Enhancement for Small VLMs
arxiv.org·2d
📏Linear Logic
ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
arxiv.org·2d
💻Local LLMs
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
arxiv.org·2d
📝Concrete Syntax