Search papers, labs, and topics across Lattice.
7
0
11
Synergistic edge effects can dramatically enhance the fidelity of graph explanations, revealing deeper insights into GNN decision-making.
Current SID-based generative recommendation models can sometimes reach future items but falter with completely unseen tokens, revealing critical gaps in cold-start handling.
Hidden Decoding achieves unprecedented performance improvements in large language models by scaling computation along the sequence length without modifying the Transformer architecture.
CHAUN achieves a remarkable 25.6% improvement in QINI scores, redefining the benchmarks for uplift modeling in the presence of unobserved confounding.
Memento achieves state-of-the-art long-term subject consistency by reconstructing identities from memory, preventing dilution and loss across video shots.
Achieve superior audio-visual generation with a 6.3B parameter model by disentangling alignment and generation, outperforming larger models.
Forget catastrophic forgetting: a neuroscience-inspired scaling method actually *improves* performance on prior domains while adapting LLMs to new tasks.
