5 citations · 13 across the 15 of their papers we have counts for
16 papers
Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks
Ruopei Sun, Jianfeng Cai, Jinhua Zhu +5
RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences, demonstrating exceptional and measurable efficacy in instruction fol…
Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
Kangwen Zhao, Jianfeng Cai, Jinhua Zhu +5
Reinforcement Learning from Human Feedback (RLHF) relies on reward models to align large language models with human preferences. However, RLHF often suffers from reward hacking, wh…
Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression
Hanyue Tu, Siqi Wu, Li Li +2
Autoencoder-based structures have dominated recent learned image compression methods. However, the inherent information loss associated with autoencoders limits their rate-distorti…
Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling
Jianfeng Cai, Jinhua Zhu, Ruopei Sun +4
Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs) by modeling human preferences with a learnable reward m…
LaneTCA: Enhancing Video Lane Detection with Temporal Context Aggregation
Keyi Zhou, Li Li, Wengang Zhou +3
In video lane detection, there are rich temporal contexts among successive frames, which is under-explored in existing lane detectors. In this work, we propose LaneTCA to bridge th…
SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection
Yonghui Wang, Shaokai Liu, Li Li +2
Shadow detection is a fundamental and challenging task in many computer vision applications. Intuitively, most shadows come from the occlusion of light by the object itself, result…
Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis
Qi Sun, Hang Zhou, Wengang Zhou +2
Synthesizing realistic 3D indoor scenes is a challenging task that traditionally relies on manual arrangement and annotation by expert designers. Recent advances in autoregressive…
Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation
Xiaohan Lei, Min Wang, Wengang Zhou +2
As a new embodied vision task, Instance ImageGoal Navigation (IIN) aims to navigate to a specified object depicted by a goal image in an unexplored environment. The main challenge…
Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction
Zhiyang Guo, Wengang Zhou, Li Li +2
3D Gaussian Splatting (3DGS) has become an emerging tool for dynamic scene reconstruction. However, existing methods focus mainly on extending static 3DGS into a time-variant repre…
Progressive Recurrent Network for Shadow Removal
Yonghui Wang, Wengang Zhou, Hao Feng +2
Single-image shadow removal is a significant task that is still unresolved. Most existing deep learning-based approaches attempt to remove the shadow directly, which can not deal w…
SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning
Hao Feng, Wendi Wang, Jiajun Deng +3
In fisheye images, rich distinct distortion patterns are regularly distributed in the image plane. These distortion patterns are independent of the visual content and provide infor…
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
Yufei Yin, Jiajun Deng, Wengang Zhou +2
Recent progress in weakly supervised object detection is featured by a combination of multiple instance detection networks (MIDN) and ordinal online refinement. However, with only…
Exploiting Spatial-Temporal Context for Interacting Hand Reconstruction on Monocular RGB Video
Weichao Zhao, Hezhen Hu, Wengang Zhou +2
Reconstructing interacting hands from monocular RGB data is a challenging task, as it involves many interfering factors, e.g. self- and mutual occlusion and similar textures. Previ…
HandNeRF: Neural Radiance Fields for Animatable Interacting Hands
Zhiyang Guo, Wengang Zhou, Min Wang +2
We propose a novel framework to reconstruct accurate appearance and geometry with neural radiance fields (NeRF) for interacting hands, enabling the rendering of photo-realistic ima…
CLIP2GAN: Towards Bridging Text with the Latent Space of GANs
Yixuan Wang, Wengang Zhou, Jianmin Bao +3
In this work, we are dedicated to text-guided image generation and propose a novel framework, i.e., CLIP2GAN, by leveraging CLIP model and StyleGAN. The key idea of our CLIP2GAN is…
Improving Malware Detection Accuracy by Extracting Icon Information
Pedro Silva, Sepehr Akhavan-Masouleh, Li Li
Detecting PE malware files is now commonly approached using statistical and machine learning models. While these models commonly use features extracted from the structure of PE fil…