Geode: A Zero-shot Geospatial Question-Answering Agent with Explicit Reasoning and Precise Spatio-Temporal Retrievalby Devashish Vikas…
Look Within, Why LLMs Hallucinate: A Causal Perspectiveby He Li, Haoang Chi, Mingyu Liu, Wenjing…
ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extractionby Shaozhe Hao, Kai Han, Zhengyao Lv,…
Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformersby Sanket Gandhi, Atul,…
Reasoning in Large Language Models: A Geometric Perspectiveby Romain Cosentino, Sarath ShekkizharFirst submitted to arxiv…
SCMIL: Sparse Context-aware Multiple Instance Learning for Predicting Cancer Survival Probability Distribution in Whole Slide…
Continuous Sign Language Recognition Using Intra-inter Gloss Attentionby Hossein Ranjbar, Alireza TaheriFirst submitted to arxiv…
OTCE: Hybrid SSM and Attention with Cross Domain Mixture of Experts to construct Observer-Thinker-Conceiver-Expresserby Jingze…
Slot State Space Modelsby Jindong Jiang, Fei Deng, Gautam Singh, Minseung Lee, Sungjin AhnFirst submitted…
SSTFB: Leveraging self-supervised pretext learning and temporal self-attention with feature branching for real-time video polyp…