Search papers, labs, and topics across Lattice.
4
0
8
5
Milestone inference can significantly enhance credit assignment in long-horizon reinforcement learning, leading to superior agent performance without extra model complexity.
Multilingual instruction following in VLA models reveals a surprising performance drop, highlighting a critical gap that could hinder global applicability of these systems.
Task-specific LLMs can be efficiently fine-tuned by explicitly routing inputs to LoRA experts based on semantic similarity, rather than relying on implicit or uniform weighting schemes.
Forget shallow alignment – STK-Adapter deeply fuses evolving knowledge graph structure and event chains into LLMs, unlocking superior temporal reasoning.
