1k citations · 1.1k across the 19 of their papers we have counts for
21 papers
Before the Token Commits: Trajectory-Level Benchmarking of Visual Hallucinations in Diffusion VLMs
Yadong Wang, Siping Yue, Yu Tian +2
Multimodal diffusion language models generate responses by iteratively unmasking tokens, making each answer the endpoint of a multi-step trajectory rather than an immediate commitm…
Open-Weather Robust 3D Detection via Dual-Critic Diffusion Alignment
Shuyao Li, Chuanxing Geng, Heyang Sun +2
Robust 3D object detection under adverse weather remains a critical hurdle for autonomous driving. Despite progress with LiDAR-4D radar fusion, most methods are constrained by a cl…
Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning
Yadong Wang, Haodong Chen, Yu Tian +3
Latent reasoning reduces the token-generation cost of chain-of-thought reasoning by replacing explicit intermediate tokens with continuous latent transitions. However, existing lat…
Reflect then Learn: Active Prompting for Information Extraction Guided by Introspective Confusion
Dong Zhao, Yadong Wang, Xiang Chen +6
Large Language Models (LLMs) show remarkable potential for few-shot information extraction (IE), yet their performance is highly sensitive to the choice of in-context examples. Con…
LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data
Chuanxing Geng, Qifei Li, Xinrui Wang +3
Using unlabeled wild data containing both in-distribution (ID) and out-of-distribution (OOD) data to improve the safety and reliability of models has recently received increasing a…
ULFine: Unbiased Lightweight Fine-tuning for Foundation-Model-Assisted Long-Tailed Semi-Supervised Learning
Enhao Zhang, Chaohua Li, Chuanxing Geng +1
Based on the success of large-scale visual foundation models like CLIP in various downstream tasks, this paper initially attempts to explore their impact on Long-Tailed Semi-Superv…
Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Survey
Chaohua Li, Enhao Zhang, Chuanxing Geng +1
Out-of-distribution detection (OOD) is a pivotal task for real-world applications that trains models to identify samples that are distributionally different from the in-distributio…
Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning
Xinrui Wang, Chuanxing Geng, Wenhai Wan +2
Recent studies have verified that semi-supervised learning (SSL) is vulnerable to data poisoning backdoor attacks. Even a tiny fraction of contaminated training data is sufficient…
Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
Xinrui Wang, Chuanxing Geng, Wenhai Wan +2
Online continual learning requires the models to learn from constant, endless streams of data. While significant efforts have been made in this field, most were focused on mitigati…
All-around Neural Collapse for Imbalanced Classification
Enhao Zhang, Chaohua Li, Chuanxing Geng +1
Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to reach \textit{optimal}…
Dynamic Against Dynamic: An Open-set Self-learning Framework
Haifeng Yang, Chuanxing Geng, Pong C. Yuen +1
In open-set recognition, existing methods generally learn statically fixed decision boundaries using known classes to reject unknown classes. Though they have achieved promising re…
All Beings Are Equal in Open Set Recognition
Chaohua Li, Enhao Zhang, Chuanxing Geng +1
In open-set recognition (OSR), a promising strategy is exploiting pseudo-unknown data outside given known classes as an additional +-th class to explicitly model potentia…
Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends
Xinrui Wang, Wenhai Wan, Chuanxin Geng +2
Learning binary classifiers from positive and unlabeled data (PUL) is vital in many real-world applications, especially when verifying negative examples is difficult. Despite the i…
Class-Aware Universum Inspired Re-Balance Learning for Long-Tailed Recognition
Enhao Zhang, Chuanxing Geng, Songcan Chen
Data augmentation for minority classes is an effective strategy for long-tailed recognition, thus developing a large number of methods. Although these methods all ensure the balanc…
Explicit View-labels Matter: A Multifacet Complementarity Study of Multi-view Clustering
Chuanxing Geng, Aiyang Han, Songcan Chen
Consistency and complementarity are two key ingredients for boosting multi-view clustering (MVC). Recently with the introduction of popular contrastive learning, the consistency le…
Universum-inspired Supervised Contrastive Learning
Aiyang Han, Chuanxing Geng, Songcan Chen
As an effective data augmentation method, Mixup synthesizes an extra amount of samples through linear interpolations. Despite its theoretical dependency on data properties, Mixup r…
Leave Zero Out: Towards a No-Cross-Validation Approach for Model Selection
Weikai Li, Chuanxing Geng, Songcan Chen
As the main workhorse for model selection, Cross Validation (CV) has achieved an empirical success due to its simplicity and intuitiveness. However, despite its ubiquitous role, CV…
A Multi-view Perspective of Self-supervised Learning
Chuanxing Geng, Zhenghao Tan, Songcan Chen
As a newly emerging unsupervised learning paradigm, self-supervised learning (SSL) recently gained widespread attention, which usually introduces a pretext task without manual anno…
Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning
Chuanxing Geng, Lue Tao, Songcan Chen
In the process of exploring the world, the curiosity constantly drives humans to cognize new things. Supposing you are a zoologist, for a presented animal image, you can recognize…
Recent Advances in Open Set Recognition: A Survey
Chuanxing Geng, Sheng-jun Huang, Songcan Chen
In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a rec…
Collective decision for open set recognition
Chuanxing Geng, Songcan Chen
In open set recognition (OSR), almost all existing methods are designed specially for recognizing individual instances, even these instances are collectively coming in batch. Recog…