Prism-Reranker models output relevance, contribution statements, and evidence passages to support agentic retrieval beyond scalar scoring.
xRAG: Extreme context compression for retrieval-augmented generation with one token
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation. xRAG reinterprets document embeddings in dense retrieval--traditionally used solely for retrieval--as features from the retrieval modality. By employing a modality fusion methodology, xRAG seamlessly integrates these embeddings into the language model representation space, effectively eliminating the need for their textual counterparts and achieving an extreme compression rate. In xRAG, the only trainable component is the modality bridge, while both the retriever and the language model remain frozen. This design choice allows for the reuse of offline-constructed document embeddings and preserves the plug-and-play nature of retrieval augmentation. Experimental results demonstrate that xRAG achieves an average improvement of over 10% across six knowledge-intensive tasks, adaptable to various language model backbones, ranging from a dense 7B model to an 8x7B Mixture of Experts configuration. xRAG not only significantly outperforms previous context compression methods but also matches the performance of uncompressed models on several datasets, while reducing overall FLOPs by a factor of 3.53. Our work pioneers new directions in retrieval-augmented generation from the perspective of multimodality fusion, and we hope it lays the foundation for future efficient and scalable retrieval-augmented systems
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 6representative citing papers
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.
RRK compresses documents to multi-token embeddings for efficient listwise reranking, enabling an 8B model to achieve 3x-18x speedups over smaller models with comparable or better effectiveness.
ZONOS2 8B is a scaled MoE TTS model with 900M active parameters trained on 6M hours of data that reports competitive SOTA results on naturalness, speaker similarity, WER, and a new ZTTS1-Eval benchmark while releasing weights and code.
A survey of large-model inference optimization, organized as a four-layer 'token-operations' taxonomy: multi-model fusion, model optimization, compute-model fusion, and compute-network-model fusion.
citing papers explorer
-
Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval
Prism-Reranker models output relevance, contribution statements, and evidence passages to support agentic retrieval beyond scalar scoring.
-
What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
-
ZAYA1-8B Technical Report
ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.
-
Efficient Listwise Reranking with Compressed Document Representations
RRK compresses documents to multi-token embeddings for efficient listwise reranking, enabling an 8B model to achieve 3x-18x speedups over smaller models with comparable or better effectiveness.
-
ZONOS2 Technical Report
ZONOS2 8B is a scaled MoE TTS model with 900M active parameters trained on 6M hours of data that reports competitive SOTA results on naturalness, speaker similarity, WER, and a new ZTTS1-Eval benchmark while releasing weights and code.
-
Token-Operations-Oriented Inference Optimization Techniques for Large Models
A survey of large-model inference optimization, organized as a four-layer 'token-operations' taxonomy: multi-model fusion, model optimization, compute-model fusion, and compute-network-model fusion.