Search papers, labs, and topics across Lattice.
6
0
9
0
Pruning redundant reasoning in teacher traces can boost recommendation model performance while streamlining output length.
Re-ranking can make or break user engagement, and GR2 boosts performance by over 18% by harnessing the power of LLMs in ways previously unexplored.
Highlighting pivotal evidence can boost LLM performance without altering the original context, leading to substantial improvements in reasoning tasks.
Reconstructing 3D scenes from images obscured by smoke and extreme darkness is now significantly more achievable, thanks to insights gleaned from the NTIRE 2026 challenge.
By surgically removing "hallucination patterns" from a model's hidden state, HulluEdit offers a reference-free, single-pass method to dramatically reduce object hallucinations in LVLMs without sacrificing visual grounding.
NGDB-Zoo unlocks up to 6.8x faster training for Neural Graph Databases by decoupling logical operators and integrating semantic priors from pre-trained text encoders, all while maintaining high GPU utilization.
