7.7k citations
- Pennsylvania State UniversityUS63 papers
- University of PisaIT58 papers
- Texas A&M UniversityUS34 papers
- University of BolognaIT33 papers
- Duke UniversityUS31 papers
- Nanjing UniversityCN29 papers
- National Research CouncilLK25 papers
- University of WashingtonUS25 papers
- Centre National de la Recherche ScientifiqueFR23 papers
- Princeton UniversityUS23 papers
- Tel Aviv UniversityIL23 papers
- Pontificia Universidad Católica de ChileCL22 papers
19 papers · 1 filter
Fusion techniques of time frequency-based images to predict the outcome of rTMS depression therapy
Wael Korani, Md Fahimul Kabir Chowdhury, Mohammed Aledhari +2
Depression is a mental condition that can lead to suicide and self-harm. Predicting the outcome of depression treatment is one of the most difficult tasks for clinicians. Among var…
On the (Intuitionistic) Logic of Next-Token Prediction
Paul Tarau
We model in intuitionistic implicational logic the key enabler of today's GenerativeAI: the next-token prediction in autoregressive causal neural networks. In our framework, next-t…
Mind the Gap: A Dual Knowledge Graph Framework for Unified Multi-task User Intent Inference
Tzu-Cheng Peng, Chien Chin Chen, Chih-Hao Ku +1
This paper proposes DKG-MTI, a dual knowledge graph framework for unified multi-task user intent inference from online travel reviews. Existing approaches often rely on hierarchica…
SymNet: A Multi-Task Network for Joint Radio Map Reconstruction and Transmitter Localization
Lyuzhou Ye, Thanh Dat Le, Yan Huang
Accurately predicting directional radio maps is essential for wireless applications, yet prior approaches primarily focus on omnidirectional signals and typically treat transmitter…
The black hole occupation fraction as a fossil record of seeding, dynamics, and galaxy assembly
Emma Jane Weller, Priyamvada Natarajan, Colin J. Burke
The black hole occupation fraction (BHOF) is a powerful but intrinsically layered diagnostic of massive black hole (BH) seeding and subsequent galaxy assembly. We measure the total…
Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency
Md Abdullah Al Forhad, Weishi Shi
While Deep Active Learning (DAL) effectively reduces human annotation costs, its efficacy is constrained by human annotation errors. This is because the data sampled for active lea…