8 papers
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
Ziyan Liu, Zhezheng Hao, Yeqiu Chen +7
Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing approaches typically train…
TRACER: Persistent Regularization for Robust Multimodal Finetuning
Hesam Asadollahzadeh, Feng Liu, Christopher Leckie +1
Mainstream strategies for finetuning pretrained multimodal models often degrade out-of-distribution (OOD) robustness, a phenomenon known as catastrophic forgetting. In this paper,…
Target-Oriented Pretraining Data Selection via Neuron-Activated Graph
Zijun Wang, Haoqin Tu, Weidong Zhou +7
Everyday tasks come with a target, and pretraining models around this target is what turns them into experts. In this paper, we study target-oriented language model (LM) pretrainin…
Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
Yunbei Zhang, Shuaicheng Niu, Chengyi Cai +2
Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limite…
Neural Distribution Prior for LiDAR Out-of-Distribution Detection
Zizhao Li, Zhengkang Xiang, Jiayang Ao +3
LiDAR-based perception is critical for autonomous driving due to its robustness to poor lighting and visibility conditions. Yet, current models operate under the closed-set assumpt…
Semantic-aware Adversarial Fine-tuning for CLIP
Jiacheng Zhang, Jinhao Li, Hanxun Huang +3
Recent studies have shown that CLIP model's adversarial robustness in zero-shot classification tasks can be enhanced by adversarially fine-tuning its image encoder with adversarial…