Show newer

Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain arxiv.org/abs/2603.02218 .IT .LG .AI .CL .IT

NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels arxiv.org/abs/2603.02219 .LG .AI

Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting arxiv.org/abs/2603.02220 .LG .AI .CV

MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Clinical Tabular Prediction arxiv.org/abs/2603.02221 .LG .AI

Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation arxiv.org/abs/2603.00546 .AI .CV

PM2Lat: Highly Accurate and Generalized Prediction of DNN Execution Latency on GPUs arxiv.org/abs/2603.00549 .PF

Serendipity with Generative AI: Repurposing knowledge components during polycrisis with a Viable Systems Model approach arxiv.org/abs/2602.23365 .HC .CL .IR

Doc To The Future: Infomorphs for Interactive, Multimodal Document Transformation and Generation arxiv.org/abs/2602.23366 .HC .IR

HumanMCP: A Human-Like Query Dataset for Evaluating MCP Tool Retrieval Performance arxiv.org/abs/2602.23367 .AI .IR

Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use arxiv.org/abs/2602.23368 .IR .AI

Toward General Semantic Chunking: A Discriminative Framework for Ultra-Long Documents arxiv.org/abs/2602.23370 .CL .AI .IR

Domain-Partitioned Hybrid RAG for Legal Reasoning: Toward Modular and Explainable Legal AI for India arxiv.org/abs/2602.23371 .IR .AI .CL

Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA arxiv.org/abs/2602.23372 .IR .AI .CL

An Agentic LLM Framework for Adverse Media Screening in AML Compliance arxiv.org/abs/2602.23373 .AI .CL .IR

Higress-RAG: A Holistic Optimization Framework for Enterprise Retrieval-Augmented Generation via Dual Hybrid Retrieval, Adaptive Routing, and CRAG arxiv.org/abs/2602.23374 .IR .AI .CL

Adaptive Prefiltering for High-Dimensional Similarity Search: A Frequency-Aware Approach arxiv.org/abs/2602.22214 .IR .CV

Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation arxiv.org/abs/2602.22215 .AI .CL .IR

Retrieval-Augmented Generation Assistant for Anatomical Pathology Laboratories arxiv.org/abs/2602.22216 .IR .AI

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.