Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks85 from public data
- 871
- Out-of-Distribution Detection and Selective Generation for Conditional Language Models241
This work presents a highly accurate and lightweight OOD detection method for CLMs, and shows its effectiveness on abstractive summarization and translation, and how it can be used under the common and realistic setting of distribution shift for selective generation of high-quality outputs, while automatically abstaining from low-quality ones, enabling safer deployment of generative language models.
- Plex: Towards Reliability using Pretrained Large Model Extensions150
Plex greatly improves the state-of-the-art across reliability tasks, and simplifies the traditional protocol as it improves the out-of-the-box performance and does not require designing scores or tuning the model for each task.
- Does your dermatology classifier know what it doesn’t know? Detecting the long-tail of unseen conditions124
A novel hierarchical outlier detection (HOD) loss is proposed, which assigns multiple abstention classes corresponding to each training outlier class and jointly performs a coarse classification of inliers vs. outliers, along with fine-grained classification of the individual classes.
- Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering116
Experiments on several KGQA benchmarks show that the proposed KG-to-Text augmented LLMs approach outperforms previous KG -augmented LLMs approaches regarding answer accuracy and usefulness of knowledge statements.
- Self-Evaluation Improves Selective Generation in Large Language Models105
This work reformulates open-ended generation tasks into token-level prediction tasks, and leverage LLMs' superior calibration at the token level, and demonstrates that self-evaluation based scores not only improve accuracy, but also correlate better with the overall quality of generated content.
- DrugOOD: Out-of-Distribution Dataset Curator and Benchmark for AI-Aided Drug Discovery – a Focus on Affinity Prediction Problems with Noise Annotations81
DrugOOD offers an automated dataset curator with user-friendly customization scripts, rich domain annotations aligned with biochemistry knowledge, realistic noise level annotations, and rigorous benchmarking of SOTA OOD algorithms, as opposed to only providing fixed datasets.
- Improving Zero-shot Generalization and Robustness of Multi-Modal Models71
A simple and efficient zero-shot post-hoc method to identify images whose top-1 prediction is likely to be incorrect, by measuring consistency of the predictions w.r.t. multiple prompts and image transformations is developed.
- A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models71
Using the proposed scoring method to create a weighted average prompt ensemble, the method outperforms equal average ensemble, as well as hand-crafted prompts, on ImageNet, 4 of its variants, and 11 fine-grained classification benchmarks, all while being fully automatic, optimization-free, and not requiring access to labeled validation data.
- 66
- DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models65
A novel watermarking scheme, DiffusionShield, tailored for GDM s is introduced, which protects images from copyright infringement by GDM s through encoding the ownership information into an imperceptible watermark and injecting it into the images.
- Transferable Unlearnable Examples64
A novel unlearnable strategy based on Classwise Separability Discriminant (CSD) is proposed, which aims to better transfer the Unlearnable effects to other training settings and datasets by enhancing the linear separability.
- Explaining Neural Networks Semantically and Quantitatively61
This study proposes to distill knowledge from the CNN into an explainable additive model, which explains the CNN prediction quantitatively, and discusses the problem of the biased interpretation of CNN predictions.
- Defining and Quantifying the Emergence of Sparse Concepts in DNNs50
It is found that the inference score of a DNN can be disentangled into the effects of a few interactive concepts that can be understood as causal patterns in a sparse, symbolic causal graph, which explains the DNN.
- Towards an architectural treatment of software security42
The approach models security principal, privilege, trust, and context of architectural constituents, and can facilitate describing the security characteristics of an architecture generating enabling infrastructure, and monitoring run-time conformance.
- Learning to Remove: Towards Isotropic Pre-trained BERT Embedding41
In all tasks, the word embedding processed by the method consistently outperforms the original embedding (with average improvement of 13% on word analogy and 16% on semantic textual similarity) and two baseline methods and is proven to be more robust to changes of hyperparameter.
- 34
- FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models31
The proposed FT-Shield addresses copyright protection challenges by designing new watermark generation and detection strategies and introduces an innovative algorithm for watermark generation that integrates a Mixture of Experts (MoE) approach for watermark detection.
- TorchOpt: An Efficient Library for Differentiable Optimization24
TorchOpt provides a unified and expressive differentiable optimization programming abstraction that allows users to efficiently declare and analyze various differentiable optimization programs with explicit gradients, implicit gradients, and zero-order gradients and provides a high-performance distributed execution runtime.
- 18
- Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability17
This paper summarizes the common mechanism shared by twelve previous transferability-boosting methods in a unified view, i.e., these methods all reduce game-theoretic interactions between regional adversarial perturbations.
- Personalized Chinese Tourism Recommendation Algorithm Based on Knowledge Graph17
A new algorithm of personalized Chinese tourism recommendation based on the Knowledge Graph with significant improvement over the existing algorithms is proposed and the method of user interest modelbased on the attribute information of users and tourist attractions is proposed to improve the performance of the recommendation system.
- 15
- 14
- Mining Interpretable AOG Representations From Convolutional Networks via Active Question Answering14
A question-answering method that uses active human-computer communications to mine patterns from a pre-trained CNN, in order to incrementally explain more features in conv-layers, and achieves similar or better part-localization performance than fast-RCNN methods.
- Sharpness-Aware Data Poisoning Attack12
A novel attack method called Sharpness-Aware Data Poisoning Attack (SAPA), which leverages the concept of DNNs' loss landscape sharpness to optimize the poisoning effect on the worst re-trained model, regardless of the specific retraining procedure employed.
- Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models9
In this benchmark, a thorough evaluation of concept removals is conducted by introducing a new dataset, Six-CD, along with a novel evaluation metric, and conducting a thorough evaluation of concept removal methods.
- 9
- Why Adversarial Training of ReLU Networks Is Difficult?8
An analytic solution of the adversarial perturbation on a ReLU network is derived, and the difficulty of adversarial training is theoretically explained, which provides a unifluence explanation for previous explanations in understanding adversarialTraining.
- Events structure information accessibility less in children than adults8
It was found that children and adults were both more accurate and faster to correctly recognize objects that last occurred within events versus across event boundaries, and an interaction such that children's access to recent experience was less influenced by event boundaries than adults'.
- 8
- 7
- Research on the identification method of safety wearing of electric power workers based on deep learning7
The experimental results show that the algorithm can achieve a good recognition effect on the staff who do not wear safety according to the regulations in the video, and the feasibility and effectiveness of the algorithm in practical application are verified.
- Face Shape Classification Based on Bilinear Network with Attention Mechanism7
Experiments on public data sets show that the algorithm proposed is get state-of-the-art results and significantly improves the accuracy of face shape classification.
- 7
- 7
- 6
- 6
- 6
- Rethinking Memory Profiling and Migration for Multi-Tiered Large Memory Systems6
HM-Keeper is an application-transparent page management system that supports the effi-cient use of multi-tiered large memory, and largely outperforms seven existing solutions by 15%-78%.
- Towards Adversarial Learning6
This tutorial provides a comprehensive overview of the recent advances of adversarial learning, including both attack methods and defense methods, and presents DeepRobust, a PyTorch adversariallearning library which aims to build a comprehensive and easy-to-use platform to foster this research field.
- Defense Against Gradient Leakage Attacks via Learning to Obscure Data6
This paper proposes a new defense method to protect the privacy of clients' data by learning to obscure data and shows that this method obtains better privacy protection while preserving high accuracy compared with state-of-the-art methods.
- Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning6
This paper proposes a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes and innovatively presents an active downsampling strategy that drops unimportant neighbor nodes to facilitate faster information propagation.
- Interpretability of Neural Networks Based on Game-theoretic Interactions5
This system of game-theoretic interactions successfully bridge the gap between “the explanation of knowledge concepts encoded in a DNN” and “the explanation of the representation capacity of a DNN” as a unified explanation.
- Combining Deep Fully Convolutional Network and Graph Convolutional Neural Network for the Extraction of Buildings from Aerial Images5
The BGC-Net proposed in this paper has better results when extracting the completeness of buildings, including boundary segmentation accuracy, and shows great potential in high-precision remote sensing mapping applications.
- 5
- EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations4
This work is the first to investigate the positive application of memorization and use it for copyright protection, which turns a curse into a blessing and offers a pioneering perspective for unauthorized usage detection in generative models.
- Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs4
The proposed metrics to measure three types of complexities of transformations based on the information theory are proposed and the strong correlation between the complexity and the disentanglement of transformations is discovered.
- 4
- 4
- FlashDP: Private Training Large Language Models with Efficient DP-SGD3
FlashDP is introduced, an innovative cache-friendly per-layer DP-SGD that consolidates necessary operations into a single task, calculating gradients only once in a fused manner, and establishes FlashDP as a pivotal development for efficient and privacy-preserving training of LLMs.
- 3
- 3
- Pluralistic Image Completion with Probabilistic Mixture-of-Experts3
A unified probabilistic graph model is introduced that represents the complex interactions in image completion and is formally established the effectiveness of the method and demonstrated it with comprehensive experiments.
- 2
- Exemplar-Based Image Colorization with A Learning Framework2
This paper proposes an automatic colorization method with a learning framework that decouples the colorization process and learning process so as to generate various color styles for the same gray image.
- Transmission line distance measurement with millimeter wave radar based on improved robust Kalman filter2
A millimeter wave radar ranging algorithm based on improved robust Kalman filter, which can meet the overall demand for real-time monitoring of transmission line anti-mechanical collision line and improve the anti-coarse interference capability of the system.
- 2
- 2
- 2
- 2
- Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models1
A novel one-class open-set OOD detector that leverages text-image pre-trained models in a zero-shot fashion and incorporates various descriptions of in-domain and OOD, designed to detect anything not in- domain and offers the flexibility to detect a wide variety of OOD.
- 1
- 1
- 1
- 1
- 1
- Research on the Description Method of the Atomic Services in Extensible Network Service Model1
The thesis firstly analyzed the disadvantages of the weak service extensibility in traditional network service model, and introduced the fundamental principles of Extensible Network Service Model (ENSM), and focused on the ENSM’s kernel about the definition and conceptual model of atomic services.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Regret Minimization of Extensive Games and Its Application on Game Strategies–
This paper describes a method to solve extensive games, the basis of this method is regret minimization, and uses a concrete case to demonstrate how this technique can be used to make decisions by players in the game of Hearthstone.
- A New Context Tree Inference Algorithm for Variable Length Markov Chain Model with Applications to Biological Sequence Analyses–
This study finds that the word counts for each branch are highly intercorrelated, resulting in non-negligible effects on the distribution of the statistic of interest, demonstrating that the inferred context tree based on the original context algorithm by Bühlmann and Wyner, can be systematically biased and error prone.
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.