6 papers
Attention Transfer Is Not Universally Effective for Vision Transformers
Huaiyuan Qin, Muli Yang, Gabriel James Goenawan +4
A recent work shows that Attention Transfer, which transfers only the attention patterns from a pre-trained teacher Vision Transformer (ViT) to a randomly initialized standard stud…
Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles
Jiawei Liu, Xun Gong, Fen Fang +6
Most Human-Machine Interaction (HMI) research overlooks the maneuvering needs of passengers in autonomous driving (AD). Natural language offers an intuitive interface, yet translat…
Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment
Huaiyuan Qin, Muli Yang, Gabriel James Goenawan +5
Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This could mistakenly lead to prese…
Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated
Muli Yang, Gabriel James Goenawan, Henan Wang +7
Despite being trained on balanced datasets, existing AI-generated image detectors often exhibit systematic bias at test time, frequently misclassifying fake images as real. We hypo…
Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering
Guangtao Lyu, Xinyi Cheng, Qi Liu +5
LVLMs achieve remarkable multimodal understanding and generation but remain susceptible to hallucinations. Existing mitigation methods predominantly focus on output-level adjustmen…
Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning
Huaiyuan Qin, Muli Yang, Siyuan Hu +4
Self-supervised learning (SSL) conventionally relies on the instance consistency paradigm, assuming that different views of the same image can be treated as positive pairs. However…