arXiv:2603.23533v2 Announce Type: replace-cross Abstract: RAG pipelines typically rely on fixed-size chunking, which ignores document structure, fragments semantic units across boundaries, and requires multiple LLM calls per chunk for metadata extraction. We present MDKeyChunker, a three-stage pipeline for Markdown documents…
arXiv:2603.26469v1 Announce Type: cross Abstract: Developing and evaluating distributed inference algorithms remains difficult due to the lack of standardized tools for modeling heterogeneous devices and networks. Existing studies often rely on ad-hoc testbeds or proprietary infrastructure, making results hard to…
arXiv:2407.19660v5 Announce Type: replace-cross Abstract: Self-supervised learning has emerged as a powerful paradigm for pretraining foundation models using large-scale data. Existing pretraining approaches predominantly rely on masked reconstruction or next-token prediction strategies, demonstrating strong performance across various downstream tasks, including…
arXiv:2511.00810v3 Announce Type: replace-cross Abstract: Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal Large Language Model (MLLM) approaches typically formulate GUI grounding as a text-based…
arXiv:2511.22265v2 Announce Type: replace Abstract: Federated learning (FL) enables collaborative training across clients while preserving privacy. While most existing FL methods assume homogeneous model architectures, client heterogeneity in both data and resources makes this assumption impractical, thus motivating model-heterogeneous FL.…
arXiv:2603.14688v2 Announce Type: replace Abstract: As multi-agent AI systems are increasingly deployed in real-world settings – from automated customer support to DevOps remediation – failures become harder to diagnose due to cascading effects, hidden dependencies, and long execution traces. We…
arXiv:2603.25872v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel sampling framework that…
arXiv:2603.25894v1 Announce Type: new Abstract: This paper presents a data-driven framework for modeling plastic deformation in crystalline metals through acoustic emission (AE) analysis. Building on experimental data from compressive loading of nickel micropillars, the study introduces a wavelet-based method using…
arXiv:2603.25857v1 Announce Type: new Abstract: The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However, their effectiveness in in-context learning remains ambiguous, particularly given the potential for training…
arXiv:2603.25861v1 Announce Type: new Abstract: Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal conflict between true and stated goals. We identify a fundamental blind spot: probes fail on coherent misalignment –…
