Zephyrus: An Agentic Framework for Weather Science
Sumanth Varambally (University of California San Diego), Rose Yu (University of California San Diego)
CodeLarge Language ModelAgentic AITabularTime SeriesPhysics Related
🎯 What it does: Proposes the ZEPHYRUS framework, integrating LLMs with weather data, forecasts, simulations, climate statistics, and other tools to enable interactive reasoning in weather science.
🎯 What it does: Designed and implemented a dual-branch zero-sacrifice persistent robustness adversarial defense framework called ZePAD, aimed at enhancing the robustness of publicly pre-trained encoders against downstream irrelevant adversarial samples while maintaining or even improving the performance on normal samples.
Zero-shot HOI Detection with MLLM-based Detector-agnostic Interaction Recognition
Shiyu Xuan (Nanjing University of Science and Technology), Jinhui Tang (Nanjing University of Science and Technology)
CodeRecognitionObject DetectionTransformerLarge Language ModelPrompt EngineeringImageTextMultimodality
🎯 What it does: Propose a decoupled framework that separates object detection from interaction recognition in zero-shot human-object interaction detection, leveraging multimodal large language models (MLLMs) to convert interaction recognition into a deterministic visual question-answering task, achieving training-free interaction recognition, and enhancing performance and efficiency through spatial-aware pooling and single deterministic matching.
ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
Weiwei Sun (Carnegie Mellon University), Yiming Yang (Carnegie Mellon University)
CodeRetrievalTransformerLarge Language ModelText
🎯 What it does: Developed a generative retrieval framework called ZEROGR that can be used in zero-shot scenarios and applied to diverse document retrieval tasks.
Zeros can be Informative: Masked Binary U-Net for Image Segmentation on Tensor Cores
Chunshu Wu (Pacific Northwest National Laboratory), Ang Li (Pacific Northwest National Laboratory)
CodeSegmentationComputational EfficiencyConvolutional Neural NetworkImageBiomedical Data
🎯 What it does: Propose Masked Binary U-Net and achieve efficient inference on Tensor Core, addressing computational and energy efficiency bottlenecks for real-time segmentation on edge devices.
CodeDomain AdaptationOptimizationConvolutional Neural NetworkTransformerLarge Language ModelImageTextBenchmark
🎯 What it does: Propose ZeroSiam, an asymmetric Siamese architecture that minimizes entropy during testing to prevent models from collapsing into degenerate solutions caused by one-hot encoding;