3 citations · 3 across the 7 of their papers we have counts for
7 papers
The Velocity Deficit: Initial Energy Injection for Flow Matching
Linze Li, Zong-Wei Hong, Shen Zhang +4
While Flow Matching theoretically guarantees constant-velocity trajectories, we identify a critical breakdown in high-dimensional practice: the Velocity Deficit. We show that the M…
GeoFusion-CAD: Structure-Aware Diffusion with Geometric State Space for Parametric 3D Design
Xiaolei Zhou, Chuangjie Fang, Jie Wu +3
Parametric Computer-Aided Design (CAD) is fundamental to modern 3D modeling, yet existing methods struggle to generate long command sequences, especially under complex geometric an…
Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection
Jinglun Li, Kaixun Jiang, Zhaoyu Chen +4
Pre-trained vision-language models have exhibited remarkable abilities in detecting out-of-distribution (OOD) samples. However, some challenging OOD samples, which lie close to in-…
Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
Wenpeng Xing, Bohan Yang, Mohan Li +5
Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations. We introduce Latent Fusion Jailbreak (LFJ)…
Boosting Generalization with Adaptive Style Techniques for Fingerprint Liveness Detection
Kexin Zhu, Bo Lin, Yang Qiu +3
We introduce a high-performance fingerprint liveness feature extraction technique that secured first place in LivDet 2023 Fingerprint Representation Challenge. Additionally, we dev…
SimpleDG: Simple Domain Generalization Baseline without Bells and Whistles
Zhi Lv, Bo Lin, Siyuan Liang +4
We present a simple domain generalization baseline, which wins second place in both the common context generalization track and the hybrid context generalization track respectively…
Efficient One Pass Self-distillation with Zipf's Label Smoothing
Jiajun Liang, Linze Li, Zhaodong Bing +4
Self-distillation exploits non-uniform soft supervision from itself during training and improves performance without any runtime cost. However, the overhead during training is ofte…