Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks160 from public data
- Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback552
A LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules to significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses.
- Mitigating Neural Network Overconfidence with Logit Normalization438
This work shows that the overconfidence issue can be mitigated through Logit Normalization (LogitNorm) -- a simple fix to the cross-entropy loss -- by enforcing a constant vector norm on the logits in training.
- Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models193
This research introduces a simple heuristic: not all tokens in auto-regressive LLM text equally represent the underlying meaning, as"linguistic redundancy"often allows a few keywords to convey the essence of long sentences, and proposes Shifting Attention to more Relevant (SAR) components at both token- and sentence-levels for better UQ.
- Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification172
An asymmetric co-teaching framework, which resists noisy labels by cooperating two models to select data with possibly clean labels for each other, which can consistently benefit most clustering based methods, and boost the state-of-the-art adaptation accuracy.
- CollabLLM: From Passive Responders to Active Collaborators145
CollabLLM is introduced, a novel and general training framework that enhances multiturn human-LLM collaboration and estimates the long-term contribution of responses using Multiturn-aware Rewards by reinforcement fine-tuning these rewards.
- LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints140
This work uses an attention-based temporally dense lane-aware estimation module to continuously estimate the likelihood of the alignment between motion dynamics and scene information extracted from an HD map, and leverages a second-stage motion refinement module to further explore temporal consistency across the complete time horizon.
- VisDrone-DET2018: The Vision Meets Drone Object Detection in Image Challenge Results133
A large-scale drone-based dataset, including 8, 599 images with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc, is released, to narrow the gap between current object detection performance and the real-world requirements.
- Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving129
This paper introduces a bounding box proposal matching module of high performance and a keypoints selection strategy to compress the CPM size and solve the multi-vehicle data fusion problem, and proposes an effective localization error correction module with maximum consensus to increase the robustness of the data fusion.
- Compound faults diagnosis and analysis for a wind turbine gearbox via a novel vibration model and empirical wavelet transform126
Aiming at the diagnosis of the above compound faults in an industrial wind turbine gearbox, empirical wavelet transform is utilized to adaptively find weak fault frequency in planetary stage as well as evident fault characteristics in other ordinary stages.
- Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning115
Self-supervised learning has shown great potentials in improving the video representation ability of deep neural networks by getting supervision from the data itself, but some of the current methods tend to cheat from the background, so this work proposes to remove the background impact by adding the background.
- 93
- VisDrone-SOT2018: The Vision Meets Drone Single-Object Tracking Challenge Results87
The evaluation protocol of the VisDrone-SOT2018 challenge is presented and the results of a comparison of 22 trackers on the benchmark dataset are presented, which are publicly available on the challenge website.
- VisDrone-VDT2018: The Vision Meets Drone Video Detection and Tracking Challenge Results81
A large-scale video object detection and tracking dataset, which consists of 79 video clips with about 1.5 million annotated bounding boxes in 33, 366 frames, and the evaluation protocol of the VisDrone-VDT2018 challenge and the results of the algorithms on the benchmark dataset are presented.
- ShadowFormer: Global Context Helps Image Shadow Removal67
A Retinex-based shadow model is proposed, from which a novel transformer-based network is derived, dubbed ShandowFormer, to exploit non-shadow regions to help shadow region restoration and achieves state-of-the-art performance by using up to 150X fewer model parameters.
- Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention66
It is found that the proposed external attention mechanism can significantly improve the performance of existing AI systems, allowing practitioners to easily customize foundation AI models to many diverse downstream applications.
- Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians63
A novel deep network termed Pedestrian-Interference Suppression Network (PISNet) is presented, which leverages a Query-Guided Attention Block (QGAB) to enhance the feature of the target in the gallery, under the guidance of the query.
- DNN‐based approach for fault detection in a direct drive wind turbine63
The proposed deep neural network (DNN) approach is successfully applied to the fault detection of the fall off of permanent magnets in a direct drive wind turbine generator.
- 52
- AMENet: Attentive Maps Encoder Network for trajectory prediction51
This work proposes an end-to-end generative model named Attentive Maps Encoder Network (AMENet) for accurate and realistic multi-path trajectory prediction that leverages the target road user's motion information and the interaction information with the neighboring road users at each time step to predict multiple plausible future trajectories conditioned on the observed past trajectories.
- 49
- 48
- Two Wrongs Don’t Make a Right: Combating Confirmation Bias in Learning with Label Noise45
This work proposes Robust Label Refurbishment (Robust LR)—a new hybrid method that integrates pseudo-labeling and confidence estimation techniques to refurbish noisy labels and achieves state-of-the-art performance across datasets and noise types.
- Autonomous Vehicles Drive into Shared Spaces: eHMI Design Concept Focusing on Vulnerable Road Users44
The results suggest that novel eHMIs might be useful for AV-VRU communication when the original drivers are not present, and a potential eHMI design concept was proposed for different VRUs to meet their various expectations.
- Exploring Dynamic Context for Multi-path Trajectory Prediction39
In this paper, a novel framework, named Dynamic Context Encoder Network (DCENet), the spatial context between agents is explored by using self-attention architectures, and a set of future trajectories for each agent is predicted conditioned on the learned spatial-temporal context by sampling from the latent space.
- Filter Grafting for Deep Neural Networks36
An entropy-based criterion to measure the information of filters and an adaptive weighting strategy for balancing the grafted information among networks are developed and performed to improve the representation capability of Deep Neural Networks.
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 2026-10-13. 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.