3 papers
cs.LG2026
Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training
Artyom Sorokin, Nazar Buzun, Alexander Anokhin +7
Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most e…
cs.CV2026
One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessment
Wen Yin, Cencen Liu, Dingrui Liu +3
Unifying Image Quality Assessment (IQA) and Image Aesthetic Assessment (IAA) in a single multimodal large language model is appealing, yet existing methods adopt a task-agnostic re…
hep-ph2025
Quantum and Material Effects in Undulator-Based LSW Searches for Dark Photons
Wen Yin
The dark photon is one of the simplest extensions of the Standard Model and provides a minimal laboratory for quantum-mechanical phenomena. Light-shining-through-a-wall (LSW) searc…