Search papers, labs, and topics across Lattice.
School of Artificial Intelligence, Laboratory for Novel Software Technology, Nanjing University National Key, Nanjing University
5
0
10
Later Transformer layers in tabular foundation models aren't always the smartest; revisiting earlier thoughts dramatically boosts performance.
CausalArena is introduced, a unified and evolvable benchmark for causal discovery under a common protocol, and substantial ranking shifts across SCM families and protocols are revealed, showing that strong performance in one benchmark regime does not reliably transfer to others.
Iterative text-guided image fusion can significantly enhance perceptual quality and information preservation, even in the presence of complex degradations.
Hydrogen's 1s electron can drive ferromagnetism, challenging long-held beliefs about magnetic materials.
Forget finicky VQ-based recommendation models: R3-VAE's reference vector and rating-based regularization finally make them stable and effective enough for real-world deployment, boosting MRR by 1.62% in online A/B tests.
