← Back to all news

Retrieval-augmented generation

Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.

6,299 stories · RSS feed

arXiv Computer Vision
Sep 16

SPEAR NeXT Causal Latent Forecasting Across Multiple Horizons for Spectral Temporal Earth Representation Learning

SPEAR NeXT is a compact, pixel‑wise multimodal spectral‑temporal foundation model that learns temporal self‑supervision by predicting future latent Earth states from past observations. It encodes instantaneous states from optical, radar, and environmental data into 32‑dimensional embeddings, then models their evolution with a causally masked transformer that forecasts multiple future horizons. The model uses Rotary Position Embeddings to capture relative temporal order and month/year embeddings to encode seasonal and interannual context.

By Rajiv Ranjan, Udaiveer Singh, Shashank Tamaskar, Dharmendra Saraswat
ragnlpmultimodal
More like this →
arXiv AI
Sep 16

Ave: Guiding Agentic GPU Optimization Using Data-Flow Invariants

arXiv:2604.18616v2 Announce Type: replace-cross Abstract: LLM coding agents can generate correct GPU kernels, but their performance still trails expert libraries. Reaching peak throughput requires co...

By Haohui Mai, Xiaoyan Guo, Xiangyun Ding, Daifeng Li, Qiuchu Yu, Chenzhun Guo, Cong Wang, Jiacheng Zhao, Christos Kozyrakis, Binhang Yuan
llmsragagentsreinforcement-learningefficiencybenchmarkssafety
More like this →
arXiv Computer Vision
Sep 16

Unifying Semantic Priors and High-Frequency Traces: Enhancing V-JEPA with Mixture-of-Experts for Robust Synthetic Image Forensics

The paper introduces MoE-JEPA, a dual‑stream deepfake detection model that combines a V‑JEPA backbone with a Residual Mixture‑of‑Experts mechanism and a noise stream branch. It further incorporates a Gated Attention Multiple Instance Learning module to refine spatial semantic understanding. On the SID‑Set benchmark, MoE‑JEPA achieves a new state‑of‑the‑art accuracy of 95.54%, outperforming much larger models.

By Simone Teglia, Irene Amerini
llmsragbenchmarks
More like this →
arXiv AI
Sep 16

AntennaFlow: A Generative Flow Model for Offset Correction in Phaseless Antenna Testing

AntennaFlow is a three‑stage generative flow model that jointly addresses costly phase acquisition and offset‑mounting violations in near‑field to far‑field antenna testing. It learns an offset‑invariant embedding of amplitude fields, transports offset amplitudes to a center‑aligned field, and applies a simplified extrapolation technique valid only for centered fields. Experiments demonstrate fast, phaseless, offset‑vector‑free NF–FF reconstruction from sparse amplitude‑only measurements, outperforming existing baselines while preserving physical consistency.

By Yongzhi Li, Chongting Shen, Menglin Chen, Xun Jiang, Zhengpeng Wang
rag
More like this →
arXiv Machine Learning
Sep 16

LLM Inference in a Flash!

The paper "LLM Inference in a Flash!" proposes an integer‑only quantization scheme and a dictionary‑based KV cache compression technique to enable large language model inference on compute‑in‑flash (CIF) devices. By eliminating floating‑point operations and reducing KV cache traffic through sparse dictionary coding, the authors achieve minimal accuracy loss while cutting dynamic KV cache traffic by 15× on Llama‑3.1‑8B and Qwen‑2.5‑7B models.

By Sebastian Zhao, Minseo Kim, Coleman Hooper, Luca Manolache, Michael W. Mahoney, Yakun Sophia Shao, Kurt Keutzer, Amir Gholami
llmsragnlpefficiency
More like this →
arXiv AI
Sep 16

CLIP Embeddings for AI-Generated Image Detection: A Few-Shot Study with Lightweight Classifier

The paper explores whether CLIP embeddings can detect AI-generated images by using a frozen CLIP model to extract visual embeddings and training lightweight classifiers on top. On the CIFAKE benchmark, the approach achieves 95% accuracy without language reasoning, and 85% accuracy after few-shot adaptation with 20% of the data. Certain image types, such as wide-angle photographs and oil paintings, remain challenging, highlighting unexplored difficulties in AI-generated image classification.

By Ziyang Ou
llmsragcomputer-visionmultimodalbenchmarks
More like this →
arXiv Computer Vision
Sep 16

Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation

arXiv:2609.16874v1 Announce Type: new Abstract: Beyond model inference, the decoding stage, which converts raw network outputs into task-level representations, constitutes a significant portion of th...

By Carmelo Scribano, Filippo Muzzini, Nedyalko Prisadnikov, Mohammad Mahdi, Yuqian Fu, Giorgia Franchini, Danda Pani Paudel, Marko Bertogna, Luc Van Gool
ragcomputer-visionefficiency
More like this →
arXiv Machine Learning
Sep 16

Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety

arXiv:2609.15997v1 Announce Type: cross Abstract: Improving safety at intersections requires identifying crash mechanisms and recommending appropriate countermeasures. However, this process tradition...

By Abu Saif Md Nasim Uddin, Mohamed Abdel-Aty, Zubayer Islam, Parvez Anowar, Chenzhu Wang
llmsragsafety
More like this →
arXiv AI
Sep 16

Multimodal Cultural Heritage Architectural Style Classification for Residential Buildings in the UAE Based on CLIP Embeddings and SVM

The paper presents a multimodal machine learning framework that classifies Emirati residential architectural styles by combining visual features from images and textual descriptions using OpenAI's CLIP model. The unified 512‑dimensional embeddings are reduced with UMAP, clustered with K‑Means, and then used to train an SVM classifier, achieving a 98% accuracy across eight style clusters. This approach outperforms previous studies and demonstrates the value of integrating visual and textual data for cultural heritage analysis.

By Ahmed Ammar Kubba, Manar Abu Talib, Iman Ibrahim, Qassim Nasir
ragmultimodal
More like this →