🔍 Information Retrieval - lincketheo

🔍SPLADE Academic

arxiv.org·

Show HN: LLM memory without context bleed; 100% precision vs. <10% vector search

📌Embedding Retrieval

tenureai.dev··Hacker News, Hacker News

RISE: A Rust Library for Inverted Index Search Engines

🔍Search Indexing Academic

arxiv.org·

Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies

🔍Vector Search Algorithms Academic

arxiv.org·

shoo99/paper-rag: A private, fully-local RAG over your own PDFs: BGE-M3 + embedded Qdrant + a local LLM via Ollama. ~150 lines, nothing leaves your machine.

📌Embedding Retrieval Code

github.com··DEV

Elasticsearch simdvec deep-dive: Walking the memory tightrope to 2x better vector throughput

📇Vector Indexing Blog

elastic.co·

Meaning in Order, Order in Meaning: Semantic R-precision for Keyphrase Evaluation

📌Embedding Retrieval Academic

arxiv.org·

MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings

📉Embeddings Optimization Academic

arxiv.org·

Towards Retrieving Interaction Spaces for Agentic Search

🎯BM25 Academic

arxiv.org·

SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers

📌Embedding Retrieval Academic

arxiv.org·

Detecting Speculative Language in Biomedical Texts using Recurrent Neural Tensor Networks

🎯Embedding Models Academic

arxiv.org·

Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems

💰Cost-Based Optimization Academic

arxiv.org·

Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS)

📌Embedding Retrieval Academic

arxiv.org·

SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval

💰Cost-Based Optimization Academic

arxiv.org·

PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams

📌Embedding Retrieval Academic

arxiv.org·

Gryphon: A Unified Architecture for Semantic-ID Generation and Item-Level Scoring in Industrial Recommendations

🎯BM25 Academic

arxiv.org·

Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting

🎯BM25 Academic

arxiv.org·

Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization

🔍SPLADE Academic

arxiv.org·

ColBERTSaR: Sparsified ColBERT Index via Product Quantization

🔎Inverted Index Academic

arxiv.org·

Understanding HNSW: The Engine Behind Fast Vector Search

Representation Curriculum: Stagewise Training for Robust Ranking and Allocation

Show HN: LLM memory without context bleed; 100% precision vs. <10% vector search

RISE: A Rust Library for Inverted Index Search Engines

Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies

shoo99/paper-rag: A private, fully-local RAG over your own PDFs: BGE-M3 + embedded Qdrant + a local LLM via Ollama. ~150 lines, nothing leaves your machine.

Elasticsearch simdvec deep-dive: Walking the memory tightrope to 2x better vector throughput

Meaning in Order, Order in Meaning: Semantic R-precision for Keyphrase Evaluation

MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings

Towards Retrieving Interaction Spaces for Agentic Search

SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers

Detecting Speculative Language in Biomedical Texts using Recurrent Neural Tensor Networks

Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems

Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS)

SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval

PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams

Gryphon: A Unified Architecture for Semantic-ID Generation and Item-Level Scoring in Industrial Recommendations

Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting

Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization

ColBERTSaR: Sparsified ColBERT Index via Product Quantization