arXiv:2603.17439v1 Announce Type: cross Abstract: Transformers enable in-context learning (ICL) for rapid, gradient-free adaptation in time series forecasting, yet most ICL-style approaches rely on tabularized, hand-crafted features, while end-to-end sequence models lack inference-time adaptation. We bridge this gap with a unified framework, Baguan-TS, which integrates the raw-sequence representation learning with ICL, instantiated by a 3D […]
Detecting the Machine: A Comprehensive Benchmark of AI-Generated Text Detectors Across Architectures, Domains, and Adversarial Conditions
arXiv:2603.17522v1 Announce Type: cross Abstract: The rapid proliferation of large language models (LLMs) has created an urgent need for robust and generalizable detectors of machine-generated text. Existing benchmarks typically evaluate a single detector on a single dataset under ideal conditions, leaving open questions about cross-domain transfer, cross-LLM generalization, and adversarial robustness. We present a comprehensive […]
CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization
arXiv:2603.16966v1 Announce Type: cross Abstract: Traditional speaker diarization systems have primarily focused on constrained scenarios such as meetings and interviews, where the number of speakers is limited and acoustic conditions are relatively clean. To explore open-world speaker diarization, we extend this task to the visual media domain, encompassing complex audiovisual programs such as films and […]
Are a Thousand Words Better Than a Single Picture? Beyond Images — A Framework for Multi-Modal Knowledge Graph Dataset Enrichment
arXiv:2603.16974v1 Announce Type: cross Abstract: Multi-Modal Knowledge Graphs (MMKGs) benefit from visual information, yet large-scale image collection is hard to curate and often excludes ambiguous but relevant visuals (e.g., logos, symbols, abstract scenes). We present Beyond Images, an automatic data-centric enrichment pipeline with optional human auditing. This pipeline operates in three stages: (1) large-scale retrieval […]
Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models
arXiv:2603.17044v1 Announce Type: cross Abstract: Unified multimodal models share a language model backbone for both understanding and generating images. Can DPO align both capabilities simultaneously? We present the first systematic study of this question, applying DPO to Janus-Pro at 1B and 7B parameters under seven training strategies and two post-hoc methods. The central finding is […]
CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning
arXiv:2603.17075v1 Announce Type: cross Abstract: Motivated by auto-proof generation and Valiant’s VP vs. VNP conjecture, we study the problem of discovering efficient arithmetic circuits to compute polynomials, using addition and multiplication gates. We formulate this problem as a single-player game, where an RL agent attempts to build the circuit within a fixed number of operations. […]
Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework
arXiv:2603.17123v1 Announce Type: cross Abstract: Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive comparative security assessment exists across major LLM architectures, leaving organizations unable to quantify risk or select appropriately secure LLMs for sensitive applications. […]
PAuth – Precise Task-Scoped Authorization For Agents
arXiv:2603.17170v1 Announce Type: cross Abstract: The emerging agentic web envisions AI agents that reliably fulfill users’ natural-language (NL)-based tasks by interacting with existing web services. However, existing authorization models are misaligned with this vision. In particular, today’s operator-scoped authorization, exemplified by OAuth, grants broad permissions tied to operators (e.g., the transfer operator) rather than to […]
Tabular LLMs for Interpretable Few-Shot Alzheimer’s Disease Prediction with Multimodal Biomedical Data
arXiv:2603.17191v1 Announce Type: cross Abstract: Accurate diagnosis of Alzheimer’s disease (AD) requires handling tabular biomarker data, yet such data are often small and incomplete, where deep learning models frequently fail to outperform classical methods. Pretrained large language models (LLMs) offer few-shot generalization, structured reasoning, and interpretable outputs, providing a powerful paradigm shift for clinical prediction. […]
Adaptive Contracts for Cost-Effective AI Delegation
arXiv:2603.17212v1 Announce Type: cross Abstract: When organizations delegate text generation tasks to AI providers via pay-for-performance contracts, expected payments rise when evaluation is noisy. As evaluation methods become more elaborate, the economic benefits of decreased noise are often overshadowed by increased evaluation costs. In this work, we introduce adaptive contracts for AI delegation, which allow […]
TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human Validation
arXiv:2603.17220v1 Announce Type: cross Abstract: The rapid proliferation of Large Language Models (LLMs) has created a profound digital divide, effectively excluding indigenous languages of the Global South from the AI revolution. The Tharu language, an Indo-Aryan vernacular spoken by approximately 1.7 million people across the Terai belt of Nepal and India, exemplifies this crisis. Despite […]
Binary Latent Protein Fitness Landscapes for Quantum Annealing Optimization
arXiv:2603.17247v1 Announce Type: cross Abstract: We propose Q-BIOLAT, a framework for modeling and optimizing protein fitness landscapes in binary latent spaces. Starting from protein sequences, we leverage pretrained protein language models to obtain continuous embeddings, which are then transformed into compact binary latent representations. In this space, protein fitness is approximated using a quadratic unconstrained […]