ScoutNeRV: Rapid Encoding of Grid-Based Video INRs via ScoutNet
Research
Research News
New papers, breakthroughs and academic AI research
AstraLOD3: Zero-shot multimodal agentic reconstruction of LOD3 building models
Research
Complementary Roles of Activation and Parametric Memory in Few-Shot Learning
Research
Can LLMs Catch a Rigged Backtest? A Clean-Control Calibration Benchmark
Research
VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision
Research
UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
Research
Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning
Research
All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation
Research
MENO: Memory-Efficient Neural Operator
Research
NS-ATTENTION: Newton-Schulz Transformations of Attention Outputs in Vision Transformers
Research
What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates
Research
FedIncome: Federated Learning for Income Estimation in Digital Lending Under Data Sovereignty Constraints
Research