Blind document image inpainting (DII) aims to restore degraded document scans without prior knowledge of noise locations, yet existing methods either produce over-smoothed text or introduce pseudo-characters. We propose a novel high-fidelity, text-guided restoration framework based on a ControlNet-guided Latent Diffusion Model (CGLDM). First, we extract and refine noisy OCR outputs using a two-stage Vision Language Model (VLM) and Large Language Model (LLM) pipeline, leveraging both global document context and local text cues to deliver near ground-truth textual fidelity. Next, these refined text features, together with an initial visually restored image, condition a latent diffusion process that progressively denoises and reconstructs clean image latents. To suppress patch-wise background inconsistencies inherent in high-resolution processing, we introduce an explicit feature-alignment loss of diffusion model training that enforces agreement between the predicted features and the VAE-encoded features of the ground-truth image. Extensive experiments on the FUNSD-ZH dataset demonstrate that our approach outperforms state-of-the-art methods in OCR legibility and maintains competitive image-level fidelity.

Determining and verifying product provenance remains a critical challenge in global supply chains, particularly as geopolitical conflicts and shifting borders create new incentives for misrepresentation of commodities, such as hiding the origin of illegally harvested timber or stolen agricultural products. Stable Isotope Ratio Analysis (SIRA), combined with Gaussian process regression-based isoscapes, has emerged as a powerful tool for geographic origin verification. While these models are now actively deployed in operational settings supporting regulators, certification bodies, and companies, they remain constrained by data scarcity and suboptimal dataset selection. In this work, we introduce a novel deployed data valuation framework designed to enhance the selection and utilization of training data for machine learning models applied in SIRA. By quantifying the marginal utility of individual samples using Shapley values, our method guides strategic, cost-effective, and robust sampling campaigns within active monitoring programs. By prioritizing high-informative samples, our approach improves model robustness and predictive accuracy across diverse datasets and geographies. Our framework has been implemented and validated in a live provenance verification system currently used by enforcement agencies, demonstrating tangible, real-world impact. Through extensive experiments and deployment in a live provenance verification system, we show that this system significantly enhances provenance verification, mitigates fraudulent trade practices, and strengthens regulatory enforcement of global supply chains.

Recent advancements in large language models (LLMs) have demonstrated their potential to significantly impact finance trading, particularly through sentiment analysis. The cryptocurrency market, known for its volatility and unpredictability, often renders price-based trading approaches inadequate. This necessitates the adoption of more sophisticated techniques such as market sentiment analysis, which can benefit from the insights provided by LLMs. This study introduces an innovative method that integrates sentiment analysis derived from five distinct LLMs with deep reinforcement learning to devise a cryptocurrency trading strategy. Recognizing that LLM outputs cannot be guaranteed to be infallibly accurate, which contributing to the LLM hallucinations, this paper details the implementation of a stringent outlier detection and removal process. By adopting a “Trust-The-Majority” strategy, the research aims to ensure that trading decisions are informed by reliable sentiment data. In addition, sentiment scores are traditionally timestamped to the publication of news or social media posts. To more accurately reflect the actual impact of such information on market sentiment, this study applies the Ebbinghaus Forgetting Curve to model the waning influence of information over time. This allows for a more nuanced understanding of how news affects market dynamics. The enhanced sentiment scores, in conjunction with traditional market data such as OHLCV (Open, High, Low, Close, Volume), are utilized by a deep reinforcement learning model to make trading decisions. Experimental results demonstrate that the proposed multi-LLM sentiment-driven framework improves trading performance in the fast-paced cryptocurrency market. The methodology outlined in this paper offers a solid foundation for incorporating real-time market sentiment analysis into financial applications.

With increasing urban traffic complexity, Traffic Signal Control (TSC) is essential for optimizing traffic flow and improving road safety. Large Language Models (LLMs) emerge as promising approaches for TSC. However, they are prone to hallucinations in emergencies, leading to unreliable decisions that may cause substantial delays for emergency vehicles. Moreover, diverse intersection types present substantial challenges for traffic state encoding and cross-intersection training, limiting generalization across heterogeneous intersections. Therefore, this paper proposes Retrieval Augmented Generation (RAG)-enhanced distributed LLM agents with Emergency response for Generalizable TSC (REG-TSC). Firstly, this paper presents an emergencyaware reasoning framework, which dynamically adjusts reasoning depth based on the emergency scenario and is equipped with a novel Reviewer-based Emergency RAG (RERAG) to distill specific knowledge and guidance from historical cases, enhancing the reliability and rationality of agents' emergency decisions. Secondly, this paper designs a type-agnostic traffic representation and proposes a Reward-guided Reinforced Refinement ($\mathbf{R}^{3}$) for heterogeneous intersections.$\mathbf{R}^{3}$adaptively samples training experience from diverse intersections with environment feedbackbased priority and fine-tunes LLM agents with a designed reward-weighted likelihood loss, guiding REG-TSC toward highreward policies across heterogeneous intersections. On three realworld road networks with 17 to 177 heterogeneous intersections, extensive experiments show that REG-TSC reduces travel time by 42.00%, queue length by 62.31%, and emergency vehicle waiting time by 83.16%, outperforming other state-of-the-art methods.

Spreadsheets are routinely used in business and scientific contexts, and one of the most vexing challenges is performing data cleaning prior to analysis and evaluation. The ad-hoc and arbitrary nature of data cleaning problems, such as typos, inconsistent formatting, missing values, and a lack of standardization, often creates the need for highly specialized pipelines. We ask whether an LLM can find its way around a spreadsheet and how to support end-users in taking their free-form data processing requests to fruition. Just like RAG retrieves context to answer users' queries, we demonstrate how we can retrieve elements from a code library to compose data preprocessing pipelines. Through comprehensive experiments, we demonstrate the quality of our system and how it is able to continuously augment its vocabulary by saving new codes and pipelines back to the code library for future retrieval.

Building on their demonstrated ability to perform a variety of tasks, we investigate the application of large language models (LLMs) to enhance in-depth analytical reasoning within the context of intelligence analysis. Intelligence analysts typically work with massive dossiers to draw connections between seemingly unrelated entities, and uncover adversaries’ plans and motives. We explore if and how LLMs can be helpful to analysts for this task and develop an architecture to augment the capabilities of an LLM with a memory module called dynamic evidence trees (DETs) to develop and track multiple investigation threads. Through extensive experiments on multiple datasets, we highlight how LLMs, as-is, are still inadequate to support intelligence analysts and offer recommendations to improve LLMs for such intricate reasoning applications.

This paper leverages open source “big data” intelligence to develop predictive models that can provide timely, relevant and accurate indications, warning, and tracking of migration flows / movements of large groups (> 100 persons) through South and Central America to the southwest border of the United States. We describe experiments with a live forecasting setup, development and refinement of predictive models, and how machine learning models can yield insight into the factors underlying mass migration.

Developers build programs based on software libraries. When a library evolves, programmers need to migrate their client code from the library's old release(s) to new release(s). Due to the API backwards incompatibility issues, such code migration may require developers to replace API usage and apply extra edits (e.g., statement insertions or deletions) to ensure the syntactic or semantic correctness of migrated code. Existing tools extract API replacement rules without handling the additional edits necessary to fulfill a migration task. This paper presents our novel approach, Meditor, which extracts and applies the necessary edits together with API replacement changes. Meditor has two phases: inference and application of migration edits. For edit inference, Meditor mines open source repositories for migration-related (MR) commits, and conducts program dependency analysis on changed Java files to locate and cluster MR code changes. From these changes, Meditor further generalizes API migration edits by abstracting away unimportant details (e.g., concrete variable identifiers). For edit application, Meditor matches a given program with inferred edits to decide which edit is applicable, customizes each applicable edit, and produces a migrated version for developers to review. We applied Meditor to four popular libraries: Lucene, CraftBukkit, Android SDK, and Commons IO. By searching among 602,249 open source projects on GitHub, Meditor identified 1,368 unique migration edits. Among these edits, 885 edits were extracted from single updated statements, while the other 483 more complex edits were from multiple co-changed statements. We sampled 937 inferred edits for manual inspection and found all of them to be correct. Our evaluation shows that Meditor correctly applied code migrations in 218 out of 225 cases. This research will help developers automatically adapt client code to different library versions.