RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation
arXiv:2508.13968v2 Announce Type: replace-cross Abstract: We investigate to what extent Multimodal Large Language Models (MLLMs) can accurately identify the orientation…
Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions
arXiv:2508.14556v1 Announce Type: cross Abstract: We introduce a new music source separation model tailored for accurate vocal isolation. Unlike Transformer-based…
Towards LLM-generated explanations for Component-based Knowledge Graph Question Answering Systems
arXiv:2508.14553v1 Announce Type: cross Abstract: Over time, software systems have reached a level of complexity that makes it difficult for…
CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description
arXiv:2508.12769v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have significantly improved the accuracy of Text-to-SQL systems.…
PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting
arXiv:2508.13773v1 Announce Type: cross Abstract: Long-term time series forecasting (LTSF) is a fundamental task with wide-ranging applications. Although Transformer-based models…
Agentic DraCor and the Art of Docstring Engineering: Evaluating MCP-empowered LLM Usage of the DraCor API
arXiv:2508.13774v1 Announce Type: cross Abstract: This paper reports on the implementation and evaluation of a Model Context Protocol (MCP) server…
Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward
arXiv:2508.12800v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit remarkable problem-solving abilities, but struggle with complex tasks due to…
Dataset Condensation with Color Compensation
arXiv:2508.01139v2 Announce Type: replace-cross Abstract: Dataset condensation always faces a constitutive trade-off: balancing performance and fidelity under extreme compression. Existing…
Image2Net: Datasets, Benchmark and Hybrid Framework to Convert Analog Circuit Diagrams into Netlists
arXiv:2508.13157v1 Announce Type: cross Abstract: Large Language Model (LLM) exhibits great potential in designing of analog integrated circuits (IC) because…