Knowledge Pull Requests for Continual Document Authoring
The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora
Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
Linkup Research Releases SPARSEUP: A 149M-Parameter Open-Source Sparse Embedding Model
4 min1
Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention
CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents
1
Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems
RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
1
Google Research Introduces Retrieve-for-Train (R4T): An RL-Compiled Diffusion Retriever for 12× to 20× Faster Query Fan-Out
4 min1
Self-Evolving Search Index
Autonomous Research for Open-Ended Problems: A Case Study on Telecom Ticket Retrieval
Atlas: Efficient Verifiable Semantic Search
4
Generative Late-Interaction Embeddings For Visual Document Retrieval
1
Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking
1
MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory Systems
Perplexity Details Its GPU Embedding Stack: How Ivy, Tulip and ROSE Serve pplx-embed
5 min2
PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents
1
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
1
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
1