Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2609.05919v1 Announce Type: new Abstract: We propose a graph dictionary learning (GDL) framework where each graph is represented as a zero-mean Gaussian distribution derived from its filtered L...
arXiv:2509.12635v4 Announce Type: replace-cross Abstract: We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention sco...
arXiv:2609.09757v1 Announce Type: cross Abstract: Real-time MRI (rtMRI) captures the dynamics of the entire vocal tract during speech, but labeled data are scarce and the modality - single-slice, gra...
arXiv:2510.13852v3 Announce Type: replace-cross Abstract: Is an LLM telling you different facts than it's telling me? This paper introduces ConsistencyAI, an independent benchmark for measuring the f...
The paper introduces a transfer learning framework for structured matrix estimation when both the ambient dimension and the intrinsic representation grow over time. It models the target parameter as an embedded source component plus low‑rank innovations and sparse edits, and proposes an anchored alternating projection estimator that preserves the transferred subspace while estimating only the new components. Deterministic error bounds are derived that separate target noise, representation growth, and source estimation error, showing improved rates when rank and sparsity increments are small, and the framework is applied to Markov transition matrix estimation and structured covariance estimation with theoretical guarantees and empirical validation.
FedGenSC introduces a federated generative semantic communication system that uses a global generator with local discriminators, a semantic prototype bank, and SNR‑conditioned generation to address instability, semantic drift, and channel‑agnostic issues in GAN‑based federated learning. Experiments on the Europarl dataset over Rayleigh fading channels show that FedGenSC outperforms the FedDeepSC baseline under non‑IID data, achieving up to a 58.2% relative improvement in BLEU‑1 at 18 dB. Ablation studies confirm that each component independently contributes to the overall performance gains.
arXiv:2609.07050v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective reasoning. However, this remains particularl...
The paper introduces a framework that learns the kernel used in kernel methods through alignment, leveraging the Collaborative Learning and Inference (CLaI) approach. It demonstrates that CLaI can be interpreted as a kernel alignment process and that its inference stage is equivalent to kernel Bayes classification with Parzen-window density estimation. By replacing cosine similarity with a learned Mahalanobis distance, the authors extend CLaI to multiclass classification, achieving higher accuracy, faster convergence, and lower calibration error on datasets such as CIFAR-10, PathMNIST, and SleepEDF, while also showing connections to Gaussian processes and competitive calibration in sepsis prediction.
The paper studies candidate generation for alternative vacation rental recommendations, comparing collaborative filtering, shallow embeddings, and graph neural network (GNN) methods on a platform with over 2 million active properties. A hybrid model that combines item-based collaborative filtering with GNN-based retrieval achieves a 14.8% higher Recall@300 than the best baseline, leveraging each method’s strengths: collaborative filtering for well-interacted properties and GNNs for diverse, cold-start alternatives. The authors also show that stronger candidate pools improve downstream ranking quality, though the exact impact is intertwined with ranker training.
arXiv:2503.11006v3 Announce Type: replace-cross Abstract: Vision and Language Navigation (VLN) requires an embodied agent to traverse complex environments by following natural language instructions,...
arXiv:2605.27156v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, particularly for long-tail do...
arXiv:2609.06712v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) achieve strong video generation quality, but their dense spatiotemporal self-attention scales quadratically with sequ...
The paper introduces REASONS, a benchmark of 12,723 sentence-level citation instances across 12 arXiv subject categories, to evaluate scientific citation attribution under different evidence conditions. It proposes a dual-metric framework—Abstention Rate (AR) and Hallucination Rate (HR)—to balance reliability and responsiveness. Experiments with proprietary and open-source LLMs across various prompting and retrieval settings show that advanced Retrieval-Augmented Generation (RAG) reduces hallucinations but increases abstention, while adversarial metadata can push hallucination rates above 85%. Human evaluation confirms a high ratio of factual hallucinations to acceptable paraphrases, underscoring the need for systems that can appropriately abstain under uncertainty.
arXiv:2603.01690v3 Announce Type: replace-cross Abstract: While dense biomedical embeddings achieve strong performance, their opaque dimensions limit transparency in biomedical NLP. Recent question-b...
arXiv:2609.07075v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is commonly evaluated by whether the final answer is correct. That test is insufficient: an answer can match its r...
The study demonstrates that contrastive pre‑training of ECG representations using cardiac magnetic resonance (CMR) imaging data can enhance ECG‑based detection of Chagas disease. By aligning an ECG encoder with a CMR embedding space from 63,193 paired UK Biobank examinations, the authors achieved higher AUROC and sensitivity metrics on CODE‑15%, SaMi‑Trop, and PhysioNet/CinC 2025 Challenge datasets compared to an unaligned baseline. The approach shows that imaging‑supervised ECG representations generalize across different populations and resource‑constrained settings.
arXiv:2609.08442v1 Announce Type: cross Abstract: Aerial Vision-and-Language Navigation requires drones to follow natural-language instructions and navigate through complex urban environments. Accura...
arXiv:2509.24877v3 Announce Type: replace Abstract: The social science of large language models (LLMs) examines how these systems evoke mind attributions, interact with one another, and transform hum...
arXiv:2609.05518v1 Announce Type: cross Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, m...
arXiv:2601.15891v4 Announce Type: replace Abstract: Vision-language pretraining has driven progress in medical image representation learning, but it depends on paired image-text data and can inherit...