MiG-NJU/EvoEmbedding

Official repository for the ICLR 2026 Oral Paper🔥 “Q-RAG: Long Context Multi-Step Retrieval via Value-Based Embedder Training”

Empowering RAG with a memory-based data interface for all-purpose applications!

Retrieval and Retrieval-augmented LLMs

Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.

State-of-the-Art Embeddings, Retrieval, and Reranking

Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Remory: Learning Residual Memory for Context Compaction

https://arxiv.org/abs/2610.26754 Process all your context faster with LLMs that can skim and selectively read what matters