15 papers
\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating
Jianghui Wang, Silong Yong, Francesco Orabona +3
Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matrices. However, LoRA remains c…
Theory of Mind Guided Strategy Adaptation for Zero-Shot Coordination
Andrew Ni, Simon Stepputtis, Stefanos Nikolaidis +3
A central challenge in multi-agent reinforcement learning is enabling agents to adapt to previously unseen teammates in a zero-shot fashion. Prior work in zero-shot coordination of…
VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
Ce Zhang, Kaixin Ma, Tianqing Fang +5
Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur signi…
Adaptively Coordinating with Novel Partners via Learned Latent Strategies
Benjamin Li, Shuyang Shi, Lucia Romero +7
Adaptation is the cornerstone of effective collaboration among heterogeneous team members. In human-agent teams, artificial agents need to adapt to their human partners in real tim…
Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation
Zifu Wan, Pingping Zhang, Yuhao Wang +4
Multi-modal semantic segmentation significantly enhances AI agents' perception and scene understanding, especially under adverse conditions like low-light or overexposed environmen…
Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
Ce Zhang, Zifu Wan, Zhehan Kan +7
While recent Large Vision-Language Models (LVLMs) have shown remarkable performance in multi-modal tasks, they are prone to generating hallucinatory text responses that do not alig…