arXiv:2509.15098v4 Announce Type: replace-cross Abstract: Humanitarian Mine Action (HMA) addresses the challenge of detecting and removing landmines from conflict regions. Much of the life-saving operational knowledge produced by HMA agencies is buried in unstructured reports, limiting the transferability of information between agencies. To address this issue, we propose TextMineX: the first dataset, evaluation framework and […]
Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models
arXiv:2411.07559v2 Announce Type: replace-cross Abstract: Jailbreaking methods, which induce Multi-modal Large Language Models (MLLMs) to output harmful responses, raise significant safety concerns. Among these methods, gradient-based approaches, which use gradients to generate malicious prompts, have been widely studied due to their high success rates in white-box settings, where full access to the model is available. […]
SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback
arXiv:2505.19514v4 Announce Type: replace-cross Abstract: Prompt quality plays a critical role in the performance of large language models (LLMs), motivating a growing body of work on prompt optimization. Most existing methods optimize prompts over a fixed dataset, assuming static input distributions and offering limited support for iterative improvement. We introduce SIPDO (Self-Improving Prompts through Data-Augmented […]
SoilNet: A Multimodal Multitask Model for Hierarchical Classification of Soil Horizons
arXiv:2508.03785v2 Announce Type: replace-cross Abstract: Recent advances in artificial intelligence (AI), in particular foundation models, have improved the state of the art in many application domains including geosciences. Some specific problems, however, could not benefit from this progress yet. Soil horizon classification, for instance, remains challenging because of its multimodal and multitask characteristics and a […]
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
arXiv:2509.26383v4 Announce Type: replace-cross Abstract: Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucinations and expose reasoning traces. However, many KG-RAG systems compose multiple LLM modules (e.g planning, reasoning, and responding), inflating inference cost and binding behavior to a specific target KG. To address this, we […]
ResMatching: Noise-Resilient Computational Super-Resolution via Guided Conditional Flow Matching
arXiv:2510.26601v3 Announce Type: replace-cross Abstract: Computational Super-Resolution (CSR) in fluorescence microscopy has, despite being an ill-posed problem, a long history. At its very core, CSR is about finding a prior that can be used to extrapolate frequencies in a micrograph that have never been imaged by the image-generating microscope. It stands to reason that, with […]
ViSIL: Unified Evaluation of Information Loss in Multimodal Video Captioning
arXiv:2601.09851v2 Announce Type: replace-cross Abstract: Multimodal video captioning condenses dense footage into a structured format of keyframes and natural language. By creating a cohesive multimodal summary, this approach anchors generative AI in rich semantic evidence and serves as a lightweight proxy for high-efficiency retrieval. However, traditional metrics like BLEU or ROUGE fail to quantify information […]
The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation
arXiv:2601.17737v2 Announce Type: replace-cross Abstract: Recent advances in video generation have produced models capable of synthesizing stunning visual content from simple text prompts. However, these models struggle to generate long-form, coherent narratives from high-level concepts like dialogue, revealing a “semantic gap” between a creative idea and its cinematic execution. To bridge this gap, we introduce […]
Revisiting Incremental Stochastic Majorization-Minimization Algorithms with Applications to Mixture of Experts
arXiv:2601.19811v1 Announce Type: cross Abstract: Processing high-volume, streaming data is increasingly common in modern statistics and machine learning, where batch-mode algorithms are often impractical because they require repeated passes over the full dataset. This has motivated incremental stochastic estimation methods, including the incremental stochastic Expectation-Maximization (EM) algorithm formulated via stochastic approximation. In this work, we […]
PowerGraph-LLM: Novel Power Grid Graph Embedding and Optimization with Large Language Models
arXiv:2501.07639v3 Announce Type: replace Abstract: Efficiently solving Optimal Power Flow (OPF) problems in power systems is crucial for operational planning and grid management. There is a growing need for scalable algorithms capable of handling the increasing variability, constraints, and uncertainties in modern power networks while providing accurate and fast solutions. To address this, machine learning […]
Holistic Explainable AI (H-XAI): Extending Transparency Beyond Developers in AI-Driven Decision Making
arXiv:2508.05792v2 Announce Type: replace Abstract: As AI systems increasingly mediate decisions in domains such as credit scoring and financial forecasting, their lack of transparency and bias raises critical concerns for fairness and public trust. Existing explainable AI (XAI) approaches largely serve developers, focusing on model justification rather than the needs of affected users or regulators. […]
Who Gets Cited Most? Benchmarking Long-Context Reasoning on Scientific Articles
arXiv:2509.21028v2 Announce Type: replace Abstract: We introduce SciTrek, a novel question-answering benchmark designed to evaluate long-context reasoning capabilities of large language models (LLMs) using scientific articles. Current long-context benchmarks often focus on simple information retrieval tasks, or employ artificial contexts. SciTrek addresses these limitations by creating benchmark questions that require information aggregation and synthesis across […]