Search papers, labs, and topics across Lattice.
Affiliation:
6
0
10
0
LLM pruning can be task-aware: DIPrune's dual importance scoring jointly optimizes static feature saliency and dynamic semantic evolution, outperforming prior methods on LLaVA and Qwen-VL.
Tree search methods can significantly enhance reasoning in LLMs, revealing that traditional decoding approaches may be holding back their potential.
Amplitude Gating boosts tool-structured task performance in LLMs by over 7 percentage points without the need for retraining, highlighting a new avenue for inference optimization.
A new 3D representation and BEV alignment framework drastically enhance the generalization of robotic manipulation policies across varied environments and robot types.
Current AI agents struggle to reliably rediscover scientific knowledge, with top performers averaging only 21.5 out of a possible score, revealing critical gaps in their research capabilities.
