Search papers, labs, and topics across Lattice.
Affiliation:
7
0
8
Small proxy models can reveal near-optimal SFT-RL budget allocations for large LLMs, streamlining the post-training process significantly.
Agents falter in partially observable settings, revealing that merely gathering visual evidence isn't enough without robust perceptual state management.
LLMs can show drastically different skill levels depending on the language used, revealing a hidden barrier to true multilingual capabilities.
Agents can discover tool behaviors but fail to adapt effectively, often resorting to inefficient exhaustive searches in dynamic environments.
Metacognitive regulation emerges as a key differentiator for deeper collaboration in human-AI interactions, reshaping our understanding of dialogue dynamics.
Forgetting specific data without sacrificing model performance just got a theoretical boost鈥擧AMU guarantees improvements in unlearning quality based on data hardness.
Fine-tuning LLMs to emulate specific cultural values improves average accuracy, but simultaneously widens the disparity in performance between demographic subgroups.
