We have 8 of 37 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Zero-shot graph models (ZGMs), which learn transferable knowledge from source graphs and directly apply to unseen target graphs without any adaptation, have achieved promising performance and attracted considerable attention. Despite their proliferation, existing ZGMs are predominantly evaluated on clean graphs, while...
This work proposes UGE, a two-stage training strategy that progressively and stably aligns images, text, and spatial structures by combining instruction-guided contrastive learning with graph-based spatial encoding, and introduces \dataset, a spatially grounded dataset that anchors street-view images to structured spat...
Large language models (LLMs) have shown strong potential for financial analysis and trading, but direct trading remains challenging because the predictive capabilities required can vary across assets, decision fields, and market conditions. Existing LLM-based trading systems either coordinate human-defined external exp...
This work compares country-continent questions with noun, adjective, and code answers while keeping several fitted measurements distinct across Qwen, Llama, and Gemma to separate early readability, natural strength, causal steering, and later content dependence.
CurvPrompt is proposed, a topology-routed geometry prompting framework for dynamic graphs that significantly advances few-shot link prediction while delivering strong, consistent performance on node classification tasks, validating the necessity of geometry-adaptive prompting.
Video misinformation detection is often approached through global multimodal fusion or free-form multimodal reasoning. Both paradigms can under-represent localized authenticity cues that arise from coupled interactions among query phrases, contextual text, and short temporal spans of frames. Because such interactions a...
Learning transferable multimodal embeddings for urban environments is challenging because urban understanding is inherently spatial, yet existing datasets and benchmarks lack explicit alignment between street-view images and urban structure. We introduce \dataset, a spatially grounded dataset that anchors street-view i...
Molecular graph representation learning is widely used in chemical and biomedical research, and reusing widely available and well-validated pre-trained 2D encoders, while incorporating molecular domain knowledge during downstream adaptation, offers a more practical alternative.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
