9 citations · 27 across the 20 of their papers we have counts for
22 papers
Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling
Cong Hua, Qianqian Xu, Zitai Wang +4
Sampling-based test-time scaling enhances LLM reasoning by aggregating multiple reasoning paths for the same query. Existing methods use answer frequencies or path confidence to co…
GoodDiffusion: Proactive Copyright Protection for Diffusion Bridge Models via Learnable Sample-specific Signatures
Shixi Qin, Zhiyong Yang, Shilong Bao +3
This paper tackles the challenging problem of developing a proactive copyright protection mechanism that cuts off unauthorized use of diffusion bridge models. Existing studies larg…
Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning
Yanyu Zhu, Hoilam Pao, Niu Hu +6
Large Language Models suffer from slow autoregressive inference. While self-speculative decoding accelerates this process, its efficiency is hampered by static configurations like…
The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works
Guanghui Wang, Kaiwen Lv Kacuila, Zhiyong Yang +5
Knowledge distillation (KD) transfers knowledge from a large teacher model to a smaller student. In language modeling, the student is trained either on tokens sampled from the teac…
Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs
Zhikang Xu, Qianqian Xu, Zitai Wang +4
Out-of-distribution (OOD) detection seeks to identify samples from unknown classes, a critical capability for deploying machine learning models in open-world scenarios. Recent rese…
Making Training-Free Diffusion Segmentors Scale with the Generative Power
Benyuan Meng, Qianqian Xu, Zitai Wang +3
As powerful generative models, text-to-image diffusion models have recently been explored for discriminative tasks. A line of research focuses on adapting a pre-trained diffusion m…
Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation
Difu Feng, Qianqian Xu, Zitai Wang +3
Nowadays, recommendation systems have become crucial to online platforms, shaping user exposure by accurate preference modeling. However, such an exposure strategy can also reinfor…
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via --Divergence
Guanghui Wang, Zhiyong Yang, Zitai Wang +3
Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model by minimizing the divergence between their output distributions, typically usi…
Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
Sicong Li, Qianqian Xu, Zhiyong Yang +4
Real-world datasets often follow a long-tailed distribution, making generalization to tail classes difficult. Recent methods resorted to long-tail variants of Sharpness-Aware Minim…
OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning
Cong Hua, Qianqian Xu, Zhiyong Yang +3
Prompt tuning adapts Vision-Language Models like CLIP to open-world tasks with minimal training costs. In this direction, one typical paradigm evaluates model performance separatel…
GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
Jiwei Tang, Zhicheng Zhang, Shunlong Wu +8
Large Language Models (LLMs) have achieved remarkable performance across a wide range of Natural Language Processing (NLP) tasks. However, in long-context scenarios, they face two…
EDGE: Unknown-aware Multi-label Learning by Energy Distribution Gap Expansion
Yuchen Sun, Qianqian Xu, Zitai Wang +2
Multi-label Out-Of-Distribution (OOD) detection aims to discriminate the OOD samples from the multi-label In-Distribution (ID) ones. Compared with its multiclass counterpart, it is…
Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
Benyuan Meng, Qianqian Xu, Zitai Wang +3
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as feat…
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
Benyuan Meng, Qianqian Xu, Zitai Wang +2
Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense fea…
HGOE: Hybrid External and Internal Graph Outlier Exposure for Graph Out-of-Distribution Detection
Junwei He, Qianqian Xu, Yangbangyan Jiang +3
With the progressive advancements in deep graph learning, out-of-distribution (OOD) detection for graph data has emerged as a critical challenge. While the efficacy of auxiliary da…
Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification
Zitai Wang, Qianqian Xu, Zhiyong Yang +4
Multi-label ranking, which returns multiple top-ranked labels for each instance, has a wide range of applications for visual tasks. Due to its complicated setting, prior arts have…
DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations
Zhiyong Yang, Qianqian Xu, Sicong Li +3
This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the v…
ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection
Junwei He, Qianqian Xu, Yangbangyan Jiang +2
Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Al…
A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization
Zitai Wang, Qianqian Xu, Zhiyong Yang +4
Due to the inherent imbalance in real-world datasets, naïve Empirical Risk Minimization (ERM) tends to bias the learning process towards the majority classes, hindering generalizat…
When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top- Multi-Label Learning
Yuchen Sun, Qianqian Xu, Zitai Wang +1
With the great success of deep neural networks, adversarial learning has received widespread attention in various studies, ranging from multi-class learning to multi-label learning…
OpenAUC: Towards AUC-Oriented Open-Set Recognition
Zitai Wang, Qianqian Xu, Zhiyong Yang +3
Traditional machine learning follows a close-set assumption that the training and test set share the same label space. While in many practical scenarios, it is inevitable that some…
Optimizing Partial Area Under the Top-k Curve: Theory and Practice
Zitai Wang, Qianqian Xu, Zhiyong Yang +3
Top-k error has become a popular metric for large-scale classification benchmarks due to the inevitable semantic ambiguity among classes. Existing literature on top-k optimization…