arXiv:2512.15468v2 Announce Type: replace-cross Abstract: The success of large language models for code relies on vast amounts of code data, including public open-source repositories, such as GitHub, and private, confidential code from companies. This raises concerns about intellectual property compliance and the potential unauthorized use of license-restricted code. While membership inference (MI) techniques have been […]
Fair-Eye Net: A Fair, Trustworthy, Multimodal Integrated Glaucoma Full Chain AI System
arXiv:2601.18464v1 Announce Type: cross Abstract: Glaucoma is a top cause of irreversible blindness globally, making early detection and longitudinal follow-up pivotal to preventing permanent vision loss. Current screening and progression assessment, however, rely on single tests or loosely linked examinations, introducing subjectivity and fragmented care. Limited access to high-quality imaging tools and specialist expertise further […]
Design Techniques for LLM-Powered Interactive Storytelling: A Case Study of the Dramamancer System
arXiv:2601.18785v1 Announce Type: cross Abstract: The rise of Large Language Models (LLMs) has enabled a new paradigm for bridging authorial intent and player agency in interactive narrative. We consider this paradigm through the example of Dramamancer, a system that uses an LLM to transform author-created story schemas into player-driven playthroughs. This extended abstract outlines some […]
Explainability, risk modeling, and segmentation based customer churn analytics for personalized retention in e-commerce
arXiv:2510.11604v2 Announce Type: replace Abstract: In online retail, customer acquisition typically incurs higher costs than customer retention, motivating firms to invest in churn analytics. However, many contemporary churn models operate as opaque black boxes, limiting insight into the determinants of attrition, the timing of retention opportunities, and the identification of high-risk customer segments. Accordingly, the […]
Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond
arXiv:2405.03251v2 Announce Type: replace-cross Abstract: The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer architecture. However, the underlying learning dynamics that contribute to the effectiveness of softmax remain largely unexplored. As a step towards better understanding, this paper […]
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
arXiv:2505.20298v3 Announce Type: replace-cross Abstract: Manga, or Japanese comics, is a richly multimodal narrative form that blends images and text in complex ways. Teaching large multimodal models (LMMs) to understand such narratives at a human-like level could help manga creators reflect on and refine their stories. To this end, we introduce two benchmarks for multimodal […]
CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal
arXiv:2512.19554v2 Announce Type: replace-cross Abstract: Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stall; when one happens to be correct, the update usually ignores why the others are close-but-wrong, and credit can be misassigned to spurious chains. We present […]
Tackling Federated Unlearning as a Parameter Estimation Problem
arXiv:2508.19065v3 Announce Type: replace-cross Abstract: Privacy regulations require the erasure of data from deep learning models. This is a significant challenge that is amplified in Federated Learning, where data remains on clients, making full retraining or coordinated updates often infeasible. This work introduces an efficient Federated Unlearning framework based on information theory, modeling leakage as […]
Structure-Aware Contrastive Learning with Fine-Grained Binding Representations for Drug Discovery
arXiv:2509.14788v2 Announce Type: replace-cross Abstract: Accurate identification of drug-target interactions (DTI) remains a central challenge in computational pharmacology, where sequence-based methods offer scalability. This work introduces a sequence-based drug-target interaction framework that integrates structural priors into protein representations while maintaining high-throughput screening capability. Evaluated across multiple benchmarks, the model achieves state-of-the-art performance on Human and […]
Data-Augmented Deep Learning for Downhole Depth Sensing and Validation
arXiv:2511.00129v3 Announce Type: replace-cross Abstract: Accurate downhole depth measurement is essential for oil and gas well operations, directly influencing reservoir contact, production efficiency, and operational safety. Collar correlation using a casing collar locator (CCL) is fundamental for precise depth calibration. While neural network has achieved significant progress in collar recognition, preprocessing methods for such applications […]
Crossing the Functional Desert: Cascade-Driven Assembly and Feasibility Transitions in Early Life
arXiv:2601.06272v3 Announce Type: replace-cross Abstract: The origin of life poses a problem of combinatorial feasibility: How can temporally supported functional organization arise in exponentially branching assembly spaces when unguided exploration behaves as a memoryless random walk? We show that nonlinear threshold-cascade dynamics in connected interaction networks provide a minimal, substrate-agnostic mechanism that can soften this […]
When Domain Pretraining Interferes with Instruction Alignment: An Empirical Study of Adapter Merging in Medical LLMs
arXiv:2601.18350v1 Announce Type: cross Abstract: Large language models (LLMs) show strong general capability but often struggle with medical terminology precision and safety-critical instruction following. We present a case study for adapter interference in safety-critical domains using a 14B-parameter base model through a two-stage LoRA pipeline: (1) domain-adaptive pre-training (PT) to inject broad medical knowledge via […]