Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2609.15320v1 Announce Type: new Abstract: Volume-based multimodal retrieval jointly scores a text query with a candidate's video, audio, and subtitle embeddings. While this approach captures hi...
arXiv:2609.14449v1 Announce Type: new Abstract: Recent work has shown that a teacher model can transfer a bias to a student through a dataset from which every explicit reference to that bias has been...
arXiv:2501.08815v2 Announce Type: replace Abstract: UV map estimation is used in computer vision for detailed analysis of human posture or activity. Previous methods assign pixels to body model verti...
The study presents a virtual imaging trial framework that uses reinforcement learning to optimize computed tomography (CT) protocols, balancing liver lesion detectability against radiation dose. By training a Proximal Policy Optimization agent on 63 computational human models across 468 parameter combinations, the authors demonstrate that evaluating only eight protocols per patient—about 2% of exhaustive testing—recovers 98.2% of the optimal objective. Conditioning the agent on patient‑specific CT localizer embeddings further improves zero‑simulation recovery by 10.7 percentage points compared to a localizer‑blind policy.
arXiv:2609.14572v1 Announce Type: cross Abstract: Teaching abstract theoretical computer science (TCS) concepts such as algorithm analysis and complexity theory is challenging because students must h...
The study examines how duplicate content is used to detect coordination in social media information operations. It distinguishes between generic, low‑information duplicates and non‑generic, more specific duplicates, labeling 187,000 tweets with an LLM‑assisted protocol and supervised classifiers. Results show that generic duplicates are rare with lexical matching but comprise nearly 39% of campaigns identified by embedding methods, and filtering out generic duplicates yields smaller, denser coordination graphs, indicating a more focused structure.
arXiv:2503.17894v4 Announce Type: replace-cross Abstract: We propose a generative learner for estimating conditional average treatment effects and characterizing the full distribution of these effect...
The paper presents a carbon‑aware routing framework for function‑calling in large language models that distributes queries across a three‑tier edge‑cloud architecture. A lightweight k‑NN predictor estimates accuracy, delay, and power for each edge tier, and real‑time grid carbon intensity is used to route queries to the lowest‑emission tier that can execute them. Experiments on state‑of‑the‑art benchmarks show the framework matches cloud‑level accuracy while cutting operational carbon emissions by an average of four times.
arXiv:2609.14717v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept seve...
arXiv:2609.13664v1 Announce Type: new Abstract: Knowledge graphs are increasingly distributed across autonomous organizations that share an entity space but own disjoint subsets of relations, forming...
arXiv:2609.13768v1 Announce Type: new Abstract: Multi-hop question answering often fails when retrieval treats evidence as isolated matches to the original question, since the facts needed to answer...
arXiv:2609.08797v2 Announce Type: replace-cross Abstract: The Potts model extends the Ising model to multinomial data. We introduce a Rater Ising-Potts model that uses agreement indicators between pa...
The paper critiques the Semantic Web’s failure to deliver machine‑interpretable knowledge, arguing that its standards omitted key elements—conditions for claims, operational grounding, and coverage scope—making truth, applicability, and boundary recognition impossible. It proposes a new framework, Semantic Knowledge Technologies, with a seven‑layer architecture and five measurable tests of understanding (check, connect, derive, act, delimit). The authors introduce concepts such as Large Knowledge Models, SLKMs, and a falsifiable definition of Semantic Artificial General Intelligence, presenting a research agenda to address these gaps.
arXiv:2609.13268v1 Announce Type: new Abstract: Annual reports, diligence packs, and infographic dashboards bury numbers in page images: axes, cell grids, and footnotes that OCR pipelines flatten and...
arXiv:2609.13190v1 Announce Type: new Abstract: Continuous cuffless blood pressure (BP) monitoring using photoplethysmography (PPG) offers a promising solution for personalized healthcare. However, e...
arXiv:2609.14100v1 Announce Type: cross Abstract: Fashion Image Captioning (FIC) plays a vital role in enhancing user experience and product search in e-commerce platforms. Unlike natural scene image...
arXiv:2609.14245v1 Announce Type: cross Abstract: Context compression reduces generator input in retrieval-augmented generation, but answer quality alone does not characterize citation attribution. W...
The paper introduces LLM-Microscope, a toolkit for measuring how Large Language Models encode contextual information at the token level. It shows that seemingly minor tokens—such as determiners, stopwords, and punctuation—carry surprisingly high contextual weight, and removing them degrades performance on benchmarks like MMLU and BABILong-4k. The study also finds a strong link between contextualization and linearity, indicating that the transformation between layers can be approximated by a single linear mapping when tokens are well contextualized.
arXiv:2606.23843v2 Announce Type: replace Abstract: Vision-language models (VLMs) achieve strong cross-modal alignment but remain brittle to negation, often relying on shallow word associations rathe...
arXiv:2606.08918v2 Announce Type: replace Abstract: Worldwide image geo-localization aims to determine where on Earth a single image was captured. However, visually similar scenes may lie thousands o...