9 papers
Background Gradients Shape Memorization in Flow Matching
Xuanhua Yin, Boyu Wei, Shuyi Zhang +3
Repetition is closely associated with memorization in generative models, but how other training images affect the retention and copying of targets remains unclear. We study this qu…
When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models
Yu Feng, Chunting Zang, Chen Shen +4
Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs. We audit two widely used safety-guard…
Beyond Random Masking: A Dual-Stream Approach for Rotation-Invariant Point Cloud Masked Autoencoders
Xuanhua Yin, Dingxin Zhang, Yu Feng +3
Existing rotation-invariant point cloud masked autoencoders (MAE) rely on random masking strategies that overlook geometric structure and semantic coherence. Random masking treats…
Reflex First, Reflect Later: Latency-Aware Embodied LLM Agents for Dynamic Response
Yangqing Zheng, Shunqi Mao, Dingxin Zhang +1
Large language models (LLMs) have substantially improved the planning capabilities of embodied agents, enabling their deployment in dynamic and safety-critical environments. Howeve…
HFBRI-MAE: Handcrafted Feature Based Rotation-Invariant Masked Autoencoder for 3D Point Cloud Analysis
Xuanhua Yin, Dingxin Zhang, Jianhui Yu +1
Self-supervised learning (SSL) has demonstrated remarkable success in 3D point cloud analysis, particularly through masked autoencoders (MAEs). However, existing MAE-based methods…
Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness
Yu Feng, Dingxin Zhang, Runkai Zhao +3
Backdoor attacks pose a severe threat to deep neural networks (DNNs) by implanting hidden backdoors that can be activated with predefined triggers to manipulate model behaviors mal…
CA-W3D: Leveraging Context-Aware Knowledge for Weakly Supervised Monocular 3D Detection
Chupeng Liu, Runkai Zhao, Weidong Cai
Weakly supervised monocular 3D detection, while less annotation-intensive, often struggles to capture the global context required for reliable 3D reasoning. Conventional label-effi…
MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention
Tianyi Wang, Jianan Fan, Dingxin Zhang +4
Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease. Multi-modal self-supervised learnin…
DINeuro: Distilling Knowledge from 2D Natural Images via Deformable Tubular Transferring Strategy for 3D Neuron Reconstruction
Yik San Cheng, Runkai Zhao, Heng Wang +5
Reconstructing neuron morphology from 3D light microscope imaging data is critical to aid neuroscientists in analyzing brain networks and neuroanatomy. With the boost from deep lea…