2 papers
cs.CV2026
BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal Perception
Zihan Chen, Hengguang Zhou, Yuan Kang +5
Multimodal large language models (MLLMs) often struggle with fine-grained visual perception when processing complete images, as critical evidence may only appear in local regions.…
cs.CL2026
An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency
Yiming Zhang, Jinghong Zhang, Haoran Zhao +2
Memory systems for large language models have focused predominantly on efficient retrieval, whereas the decision of whether retrieved memories should be trusted has received compar…