arXiv:2604.02448v1 Announce Type: cross Abstract: Diabetic Retinopathy (DR) is a serious microvascular complication of diabetes, and one of the leading causes of vision loss worldwide. Although automated detection and grading, with Deep Learning (DL), can reduce the burden on ophthalmologists, it is constrained by the limited availability of high-quality datasets. Existing repositories often remain geographically […]
Comparing the Impact of Pedagogy-Informed Custom and General-Purpose GAI Chatbots on Students’ Science Problem-Solving Processes and Performance Using Heterogeneous Interaction Network Analysis
arXiv:2604.03022v1 Announce Type: cross Abstract: Problem solving plays an essential role in science education, and generative AI (GAI) chatbots have emerged as a promising tool for supporting students’ science problem solving. However, general-purpose chatbots (e.g., ChatGPT), which often provide direct, ready-made answers, may lead to students’ cognitive offloading. Prior research has rarely focused on custom […]
Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing
arXiv:2603.24326v2 Announce Type: replace-cross Abstract: Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to a quadratic increase in the number of vision tokens and significantly raises computational costs. We attribute this inefficiency to substantial […]
Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers
arXiv:2603.28013v2 Announce Type: replace-cross Abstract: We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success rate (ASR); we localize the pipeline stage at which each model’s defense activates. We instrument every run with a cryptographic canary token (SECRET-[A-F0-9]8) tracked through four kill-chain stages — Exposed, […]
High-resolution probabilistic estimation of three-dimensional regional ocean dynamics from sparse surface observations
arXiv:2604.02850v1 Announce Type: cross Abstract: The ocean interior regulates Earth’s climate but remains sparsely observed due to limited in situ measurements, while satellite observations are restricted to the surface. We present a depth-aware generative framework for reconstructing high-resolution three-dimensional ocean states from extremely sparse surface data. Our approach employs a conditional denoising diffusion probabilistic model […]
The Spectral Edge Thesis: A Mathematical Framework for Intra-Signal Phase Transitions in Neural Network Training
arXiv:2603.28964v2 Announce Type: replace-cross Abstract: We develop the spectral edge thesis: phase transitions in neural network training — grokking, capability gains, loss plateaus — are controlled by the spectral gap of the rolling-window Gram matrix of parameter updates. In the extreme aspect ratio regime (parameters $P sim 10^8$, window $W sim 10$), the classical BBP […]
A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos
arXiv:2604.02860v1 Announce Type: cross Abstract: Temporal sentence grounding in videos (TSGV) aims to localize a temporal segment that semantically corresponds to a sentence query from an untrimmed video. Most current methods adopt pre-trained query-agnostic visual encoders for offline feature extraction, and the video backbones are frozen and not optimized for TSGV. This leads to a […]
NavCrafter: Exploring 3D Scenes from a Single Image
arXiv:2604.02828v1 Announce Type: cross Abstract: Creating flexible 3D scenes from a single image is vital when direct 3D data acquisition is costly or impractical. We introduce NavCrafter, a novel framework that explores 3D scenes from a single image by synthesizing novel-view video sequences with camera controllability and temporal-spatial consistency. NavCrafter leverages video diffusion models to […]
LLM+Graph@VLDB’2025 Workshop Summary
arXiv:2604.02861v1 Announce Type: cross Abstract: The integration of large language models (LLMs) with graph-structured data has become a pivotal and fast evolving research frontier, drawing strong interest from both academia and industry. The 2nd LLM+Graph Workshop, co-located with the 51st International Conference on Very Large Data Bases (VLDB 2025) in London, focused on advancing algorithms […]
Transfer learning for nonparametric Bayesian networks
arXiv:2604.01021v2 Announce Type: replace-cross Abstract: This paper introduces two transfer learning methodologies for estimating nonparametric Bayesian networks under scarce data. We propose two algorithms, a constraint-based structure learning method, called PC-stable-transfer learning (PCS-TL), and a score-based method, called hill climbing transfer learning (HC-TL). We also define particular metrics to tackle the negative transfer problem in […]
One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging
arXiv:2604.02881v1 Announce Type: cross Abstract: Weight-space model merging combines independently fine-tuned models without accessing original training data, offering a practical alternative to joint training. While merging succeeds in multitask settings, its behavior in multilingual contexts remains poorly understood. We systematically study weight-space merging for multilingual machine translation by fully fine-tuning language model on large-scale bilingual […]
ProdCodeBench: A Production-Derived Benchmark for Evaluating AI Coding Agents
arXiv:2604.01527v2 Announce Type: replace-cross Abstract: Benchmarks that reflect production workloads are better for evaluating AI coding agents in industrial settings, yet existing benchmarks differ from real usage in programming language distribution, prompt style and codebase structure. This paper presents a methodology for curating production-derived benchmarks, illustrated through ProdCodeBench, a benchmark sourced from real developer-agent sessions. […]