2 papers
cs.CV2026
COMiT: Learning Structured Visual Tokens through Sequential Communication
Aram Davtyan, Yusuf Sahin, Yasaman Haghighi +4
Discrete image tokenizers provide a sequential interface for vision and multimodal models, but are typically optimized for reconstruction or compression and therefore tend to encod…
cs.LG2025
Multi-Source Urban Traffic Flow Forecasting with Drone and Loop Detector Data
Weijiang Xiong, Robert Fonod, Alexandre Alahi +1
Traffic forecasting is a fundamental task in transportation research, however the scope of current research has mainly focused on a single data modality of loop detectors. Recently…