Search papers, labs, and topics across Lattice.
8
0
12
Keye-VL-2.0 achieves lossless processing of 256K video contexts, revolutionizing long-video understanding and agent collaboration.
Surprisingly, the "think before answer" paradigm fails to enhance generative recommendation models, prompting a novel approach that redefines how reasoning is integrated into these systems.
Converting noisy, human-centric guides into self-evolving agent skills can yield performance improvements of up to 25.3 percentage points across diverse tasks.
Domain-specialized LLMs can regain lost general skills without sacrificing their expertise, thanks to a new distillation method that disentangles conflicting training signals.
MLLMs can't grasp metaphors in videos, revealing a surprising gap in their high-order cognitive abilities compared to humans.
Today's agents are surprisingly bad at real-world terminal tasks, with even frontier models failing nearly 40% of the time on everyday workflows.
Reranking in recommender systems can be revolutionized by shifting from local indices to generating global identifiers, enhancing robustness and user satisfaction.
