Geographical Information Alignment Boosts Traffic Analysis via Transpose Cross-attentionby Xiangyu Jiang, Xiwen Chen, Hao Wang,…
Is Large-Scale Pretraining the Secret to Good Domain Generalization?by Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis,…
An Information-Theoretic Analysis of Thompson Sampling for Logistic Banditsby Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J.…
Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedbackby Hiroki Furuta, Heiga Zen, Dale…
T-REG: Preference Optimization with Token-Level Reward Regularizationby Wenxuan Zhou, Shujian Zhang, Lingxiao Zhao, Tao MengFirst…
Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer…
LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentationby Huadong Tang, Youpeng Zhao,…
Event-based Tracking of Any Point with Motion-Robust Correlation Featuresby Friedhelm Hamann, Daniel Gehrig, Filbert Febryanto,…
SpaRC: Sparse Radar-Camera Fusion for 3D Object Detectionby Philipp Wolters, Johannes Gilg, Torben Teepe, Fabian…
RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilationby Xianfeng Tan, Yuhan Li, Wenxiang Shang, Yubo…