#transformer models
50 papers match
S-CEReBrO: Breaking the Memory Barrier in Continuous EEG Monitoring
Glenn Anta Bucagu, Thorir Mar Ingolfsson, Yawei Li +1
The paper introduces S-CEReBrO, a streaming Transformer architecture that uses a windowed alternating attention mechanism to keep memory usage constant during continuous EEG monito…
CCFormer: Efficient Cross-Field Interaction and Hierarchical Sequence Compression for Industrial Recommendation at Tencent
Yunlong Wang, Huizhe Zhang, Haonan Hu +5
The paper introduces CCFormer, an efficient Transformer architecture that combines cross-field attention with hierarchical sequence compression to improve industrial recommendation…
Arm2Air: Cross-Embodiment Skeleton Transfer for 3D Relay Formation
Dohun Lee, Kyeonghyun Yoo, Seokmin Kim +3
The paper introduces Arm2Air, a method that transfers obstacle-avoidance motion skeletons learned from robot arms to UAVs for efficient 3D relay placement in cluttered urban enviro…
MUL-T: Decoding Spatial Cellular Architecture in Multiplexed Tissue Images
Farzaneh Seyedshahi, Kai Rakovic, Adalberto Claudio Quiros +2
The paper introduces MUL-T, a lightweight transformer that models spatial cellular architecture in multiplexed tissue images by predicting masked cell tokens, achieving strong perf…
LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning
Mohand Mezmaz, Grégoire Danoy
The paper introduces LM-GRASP, a method that trains a Transformer-based construction policy online for each combinatorial optimization instance using imitation learning from a loca…
Causal Discovery with Inverted Self-attention for Multivariate Time Series
Yusen Liu, Yong Wang, Yifan Yin +3
The paper introduces a transformer-based framework that uses an inverted self‑attention mechanism to uncover causal relationships in multivariate time series, emphasizing indirect…