Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence
cs.IR, cs.CL
Submitted: 2026-10-09
Updated: 2026-10-09
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- jina-embeddings-v5-text: Task-Targeted Embedding Distillation
- Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks
- Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
- Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search
- REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation
- ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval
- Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval
- NV-Retriever: Improving text embedding models with effective hard-negative mining
- EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory
- Multi-Vector Index Compression in Any Modality
- EmbeddingGemma: Powerful and Lightweight Text Representations
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- Improving Long-Context Retrieval with Multi-Prefix Embedding
- Your Embedding Model is SMARTer Than You Think
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- LMEB: Long-horizon Memory Embedding Benchmark
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
- MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
- Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition