How I Study AI - Learn AI Papers & Lectures the Easy Way

Query-focused and Memory-aware Reranker for Long Context Processing

Intermediate

Yuqing Li, Jiangnan Li et al.Feb 12arXiv

QRRanker is a lightweight way to sort many long text chunks by how helpful they are to a question, using the model’s own attention to score relevance.

#query-focused retrieval heads#attention-based reranking#listwise ranking

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

Intermediate

Haozhen Zhang, Quanyu Long et al.Feb 2arXiv

MemSkill turns memory operations for AI agents into learnable skills instead of fixed, hand-made rules.

#memory skills#LLM agents#skill bank

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

Intermediate

Mingxin Li, Yanzhao Zhang et al.Jan 8arXiv

This paper builds two teamwork models, Qwen3-VL-Embedding and Qwen3-VL-Reranker, that understand text, images, visual documents, and videos in one shared space so search works across all of them.

#multimodal retrieval#unified embedding space#cross-encoder reranker

Papers3

Query-focused and Memory-aware Reranker for Long Context Processing

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking