Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2610.26357v2 Announce Type: replace Abstract: Multimodal survival prediction jointly analyzes histopathological whole-slide images (WSIs), genomic profiles, and clinical variables to stratify p...
The paper proposes an autonomous construction system that combines a large language model (ChatGPT‑5) with a reinforcement learning algorithm to control a mobile crane during retaining wall construction. An enhanced soft actor‑critic model plans crane actions, while robot kinematics ensure these actions are executable. The system also uses a custom embedding model to extract relevant construction data and generates progress updates, safety information, and reports.
arXiv:2610.27114v1 Announce Type: cross Abstract: Retrieval-augmented QA can fail even when the correct answer is in the retrieved evidence. This can happen when a competing answer satisfies some, bu...
MoSAIK (Motion Search with AI in K-space) is a new method that retrospectively estimates in-plane rigid-body motion directly from standard multi-coil TSE k-space data without requiring motion-free references, external navigators, or additional acquisitions. It uses a decoupled convolutional embedding and Transformer encoder to predict rotation and translation parameters, which are then incorporated into a motion-aware reconstruction. In both simulated and in-vivo tests, MoSAIK achieved low estimation errors and improved image quality, reducing visible artefacts while preserving anatomical detail.
The paper introduces SpaRLax, a sparse relaxation method for reinforcement learning that enhances soft Chain-of-Thought reasoning in large language models. By treating soft tokens as differentiable intermediate steps and applying an adaptive entmax sparsity technique, SpaRLax stabilizes training and improves performance across nine reasoning benchmarks. The method retains multiple plausible candidates when uncertain while truncating noise at confident steps.
arXiv:2610.28074v1 Announce Type: new Abstract: As a prototypical latent world model, Joint-Embedding Predictive Architectures (JEPAs) provide strong semantic representations. However, dense patch re...
arXiv:2610.28411v1 Announce Type: cross Abstract: Deep learning models have become essential tools in medical imaging, yet training them end-to-end for diverse tasks remains challenging due to limite...
arXiv:2610.28562v1 Announce Type: new Abstract: Many scientific phenomena are best understood as outcomes of underlying optimization problems, yet automated scientific discovery has largely focused o...
WaveCommitments is an open‑source framework that enables private and verifiable marketplaces for autonomous speech agents. It combines confidential asset valuation using Data Shapley within a trusted execution environment with multivariate polynomial commitments, allowing selective openings and tamper‑evident provenance. Experiments on three datasets and state‑of‑the‑art encoders, including Whisper, show up to 20× faster benchmarks and 39× smaller proofs, while also revealing how speaker value varies across tasks and encoders.
HierDTA is a hierarchical structure‑aware framework for drug–target affinity prediction that represents drugs as atom–motif heterogeneous graphs and proteins as residue interaction graphs. It integrates atom and residue representations via cross‑attention, supplemented by molecule fingerprints and pretrained ESM‑2 embeddings, achieving superior performance on the Davis and KIBA datasets and strong generalization in cold‑start scenarios. Ablation studies and interpretability analyses confirm the contributions of its hierarchical augmentation and interaction components, and case studies demonstrate early enrichment of candidate bioactive compounds.
arXiv:2610.27588v1 Announce Type: new Abstract: LLM agents have become capable kernel engineers on mainstream GPU stacks, but they struggle on emerging accelerators such as Ascend NPUs, whose program...
arXiv:2610.27797v1 Announce Type: new Abstract: 6G will be designed faster than it can be built: AI-driven search already proposes physical-layer algorithms at machine speed, while carrying a single...
arXiv:2610.27817v1 Announce Type: new Abstract: Every prompt sent to a hosted language model is readable by whoever runs it. We study whether the prompt can remain on the client while the host receiv...
MOSS (Model Sanity Service) is a production framework that embeds LLM-based relevance scoring into a continuous monitoring loop for recommendation, search, and offer surfaces, using targeted sampling, strategy-aware prompting, and structured alerting to diagnose semantic failures. It has been deployed for over six months at a large U.S. retailer, identifying two confirmed serving defects and quantifying a 76.4% reduction in alert rate for a backfill blending fix. Benchmark results show that LLM judges outperform non-LLM baselines on both recommendation and search tasks, demonstrating that a single LLM monitoring framework can deliver actionable quality signals across multiple product discovery surfaces.
arXiv:2610.26914v1 Announce Type: cross Abstract: Pluralistic alignment requires AI systems to learn from diverse populations whose preferences may reflect heterogeneous or even conflicting objective...
arXiv:2610.26938v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is increasingly served across geo-distributed cloud and edge infrastructures, where wide-area latency, cross-reg...
SZED submitted a system to the ArGuard 2026 Arabic hateful meme detection challenge, tackling both binary classification (A1) and fine‑grained multi‑label tagging (A2). For A1, the team fused MARBERTv2 and CLIP ViT‑L/14 embeddings using concatenation, self‑attention, and ensemble heads, achieving a macro‑F1 of 0.7597. For A2, they employed a multi‑task label‑attention architecture with per‑class query vectors and an auxiliary cascade‑calibration head, reaching a macro‑F1 of 0.3142 across ten active classes and analyzing per‑class error patterns and calibration effects.
arXiv:2610.27653v1 Announce Type: cross Abstract: Watermarking has emerged as a key tool for identifying text generated by large language models (LLMs), with current schemes embedding statistical sig...
arXiv:2610.28059v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) promise predictions that humans can inspect and correct through concepts such as "curved beak". Yet on CUB-200-2011,...
arXiv:2610.28176v1 Announce Type: cross Abstract: Large Language Models (LLMs) often struggle with temporally grounded reasoning because their static parametric memory is misaligned with the dynamic...