Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2609.25007v1 Announce Type: cross Abstract: The performance of state-of-the-art speaker verification (SV) systems severely degrades on short utterances due to insufficient speaker-specific info...
arXiv:2609.26185v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate impressive capabilities across many applications but remain vulnerable to jailbreak attacks, which elicit ha...
arXiv:2609.26056v1 Announce Type: new Abstract: Vision-Language Models (VLMs) offer promising capabilities for automated sports coaching but face a fundamental limitation: they implicitly compare aga...
The paper investigates whether the performance of anomaly detection systems can be predicted without labeled anomalies. For kNN-based detectors, it derives a lower bound on AUC that links detection performance to the separation and variance of inlier and outlier scores, and uses this to analyze how density variation, intrinsic dimensionality, and domain mismatch affect score variability. The authors introduce pseudo‑anomaly probes that provide a reference for estimating relative score separation, and demonstrate through experiments on DCASE benchmarks that these probes enable anomaly‑free model selection to outperform conventional development‑set selection, especially under domain shift.
arXiv:2609.24631v1 Announce Type: cross Abstract: Autonomous parking in nonconvex and narrow environments remains challenging. Although optimal-control methods can explicitly enforce vehicle dynamics...
arXiv:2609.25722v1 Announce Type: new Abstract: Signed graphs arise in trust--distrust networks, financial correlation systems, biological interaction graphs, and many other domains in which edges ca...
Vorch-Human is a unified framework for human‑centric audio‑visual generation that handles multiple tasks—animating a person from speech, jointly generating speech and video from a voice reference, and synthesizing a scene from paired appearance and voice references—using a single dual‑stream audio‑video diffusion transformer. The model incorporates clean condition‑audio and condition‑video tokens, per‑token task embeddings, temporal position types, condition masks, and a shared multimodal prompt encoder to express diverse inputs such as driving speech, timbre examples, first frames, and subject images. A two‑level data pipeline supplies the necessary supervision by extracting speech, appearance, and timbre annotations from clips and linking consistent identity and outfit references across videos, while a frozen‑prefix recurrence enables long‑form audio‑driven generation with reduced boundary discontinuity and identity drift.
Transformer language models process sequences token by token in an autoregressive manner, making growing contexts increasingly expensive. Yet many adjacent token spans are highly predictable or freque...
Foundation model embeddings of screening mammograms may encode pre-diagnostic tissue change without task-specific adaptation. We tested whether embeddings move faster along a data-derived "cancer dire...
The article discusses a small adversarial test set designed to detect retrieval failures in Retrieval-Augmented Generation (RAG) pipelines that typical evaluation sets might miss. It emphasizes the importance of proactively testing your own RAG system to uncover hidden weaknesses before users encounter them. By using this targeted test set, developers can improve the reliability and robustness of their RAG models.
Althea is a retrieval‑augmented system that supports user‑driven claim evaluation, matching standard pipelines on AVeriTeC while improving discrimination between supported and refuted claims. In a longitudinal survey experiment with 961 participants, two AI‑assisted treatments—Exploratory (guided reasoning) and Summary (synthesized verdicts)—initially boosted accuracy and confidence, but these gains faded after the system was removed, leaving no advantage over unrelated news. In contrast, a Self‑search baseline, which lacks a fading procedure, maintained a significant advantage, highlighting a fact‑checking–metalearning tradeoff where methods that improve immediate accuracy may not foster durable literacy gains.
The paper introduces Spectral Transductive Refinement (STR), a training‑free method that refines class prototypes at test time using the geometry of a joint k‑nearest‑neighbour graph and a normalized‑Laplacian spectral coordinate system. STR operates solely on frozen visual embeddings, iteratively updating pseudo‑labelled queries to improve one‑shot and few‑shot classification under domain shift. Experiments on ResNet‑18 and ResNet‑10 backbones show STR outperforms single‑prototype baselines and rivals meta‑trained cross‑domain few‑shot methods, achieving the best 1‑shot average across eight target domains.
The paper introduces a resolution‑flexible decoder for hybrid neural video representations, using uniform 2× upsampling stages that adapt to any target resolution by tracing spatial sizes backward from the final output. After each stage, feature maps are aligned to the desired size via minimal padding or cropping, and the process is guided by intermediate reconstruction supervision and a difficulty‑aware frame sampling strategy. Experiments on the UVG dataset demonstrate that this framework improves reconstruction quality compared to existing NVR baselines.
The paper introduces a fault‑diagnosis framework for electrical submersible pumps that uses Siamese contrastive representation learning to handle class imbalance and a prior‑corrected k‑nearest neighbor classifier for robust fault classification. It extracts discriminative vibration‑domain features, trains a Siamese network to cluster same‑fault samples, and applies a distance‑weighted KNN to mitigate imbalance. Validation with a Leave‑One‑ESP‑Out strategy shows consistent performance across unseen pump units, indicating potential for reliable predictive maintenance in offshore oil production.
Causilo is a new tabular foundation model that delivers state‑of‑the‑art predictive performance while achieving exceptionally fast inference. On the TabArena benchmark it scores 1785.4 Elo with a median inference time of 0.10 seconds per 1 K test samples, outperforming TabPFN‑3.5‑Fast by 31.6% in speed and reaching the performance–efficiency Pareto frontier. The architecture builds on TabICL’s column‑then‑row design, adding a row‑refinement module that exchanges information among cell representations before a final column stage, and uses cross‑attention with a fixed number of summary tokens to keep attention cost linear in the number of features.
arXiv:2609.24464v1 Announce Type: new Abstract: Using a Large Language Model (LLM) as the clusterer at production scale is hard: prompts cannot hold the entire label space, and per-document serial pr...
arXiv:2609.22486v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rely on external sources when answering questions that require proprietary information or up-to-date live w...
arXiv:2609.23574v1 Announce Type: cross Abstract: In high-dimensional tabular learning, feature screening provides a lightweight, model-agnostic way to remove irrelevant features before model fitting...
arXiv:2609.24302v1 Announce Type: cross Abstract: Virtual screening aims to prioritize active compounds from large chemical libraries within a limited experimental budget. When applying Boltz-2 to vi...
arXiv:2601.18952v3 Announce Type: replace Abstract: We propose Kernel Embedding Distributional Reinforcement Learning (KE-DRL) an offline method to estimate kernel mean embeddings of conditional mult...