Yusheng Xie
YOU?
Author Swipe
View article: ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models
ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models Open
Large Language Models (LLMs) have revolutionized natural language processing tasks. However, their practical application is constrained by substantial memory and computational demands. Post-training quantization (PTQ) is considered an effe…
View article: ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models
ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models Open
Large Language Models (LLMs) have revolutionized natural language processing tasks. However, their practical application is constrained by substantial memory and computational demands. Post-training quantization (PTQ) is considered an effe…
View article: MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets Open
Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs. Previous approaches augment textual dialogues with retrieved images…
View article: Histone deacetylase 9 exacerbates podocyte injury in hyperhomocysteinemia through epigenetic repression of Klotho
Histone deacetylase 9 exacerbates podocyte injury in hyperhomocysteinemia through epigenetic repression of Klotho Open
Although hyperhomocysteinemia (hHcys) has been recognized as an important independent risk factor in the progression of end-stage renal disease and the development of cardiovascular complications related to end-stage renal disease, the mec…
View article: CCDC92 deficiency ameliorates podocyte lipotoxicity in diabetic kidney disease
CCDC92 deficiency ameliorates podocyte lipotoxicity in diabetic kidney disease Open
View article: Targeting RNA oxidation by ISG20-mediated degradation is a potential therapeutic strategy for acute kidney injury
Targeting RNA oxidation by ISG20-mediated degradation is a potential therapeutic strategy for acute kidney injury Open
Oxidative stress plays a central role in the pathophysiology of acute kidney injury (AKI). Although RNA is one of the most vulnerable cell components to oxidative damage, it is unclear whether RNA oxidation is involved in the pathogenesis …
View article: AQT: Adversarial Query Transformers for Domain Adaptive Object Detection
AQT: Adversarial Query Transformers for Domain Adaptive Object Detection Open
Adversarial feature alignment is widely used in domain adaptive object detection. Despite the effectiveness on CNN-based detectors, its applicability to transformer-based detectors is less studied. In this paper, we present AQT (adversaria…
View article: JAML promotes acute kidney injury mainly through a macrophage-dependent mechanism
JAML promotes acute kidney injury mainly through a macrophage-dependent mechanism Open
Although macrophages are undoubtedly attractive therapeutic targets for acute kidney injury (AKI) because of their critical roles in renal inflammation and repair, the underlying mechanisms of macrophage phenotype switching and efferocytos…
View article: Targeting tissue-resident memory CD8+ T cells in the kidney is a potential therapeutic strategy to ameliorate podocyte injury and glomerulosclerosis
Targeting tissue-resident memory CD8+ T cells in the kidney is a potential therapeutic strategy to ameliorate podocyte injury and glomerulosclerosis Open
View article: FGFR2–BRD4 Axis Regulates Transcriptional Networks of Histone 3 Modification and Synergy Between Its Inhibitors and PD-1/PD-L1 in a TNBC Mouse Model
FGFR2–BRD4 Axis Regulates Transcriptional Networks of Histone 3 Modification and Synergy Between Its Inhibitors and PD-1/PD-L1 in a TNBC Mouse Model Open
Epigenetic reprogramming is an independent mode of gene expression that often involves changes in the transcription and chromatin structure due to tumor initiation and development. In this study, we developed a specifically modified peptid…
View article: Contemporary synthesis of bioactive cyclobutane natural products
Contemporary synthesis of bioactive cyclobutane natural products Open
Many cyclobutane natural products have intriguing biological properties that arise from their fascinating chemical structures. Cyclobutane natural products feature a cyclobutane scaffold as the core or as a part of the spirocyclic or fused…
View article: TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation Open
Estimating the 2D human poses in each view is typically the first step in calibrated multi-view 3D pose estimation. But the performance of 2D pose detectors suffers from challenging situations such as occlusions and oblique viewing angles.…
View article: DocFormer: End-to-End Transformer for Document Understanding
DocFormer: End-to-End Transformer for Document Understanding Open
We present DocFormer -- a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU). VDU is a challenging problem which aims to understand documents in their varied formats (forms, receipts etc.) and la…
View article: Single-step fluorescent probes to detect decrotonylation activity of HDACs through intramolecular reactions
Single-step fluorescent probes to detect decrotonylation activity of HDACs through intramolecular reactions Open
View article: MVHM: A Large-Scale Multi-View Hand Mesh Benchmark for Accurate 3D Hand Pose Estimation
MVHM: A Large-Scale Multi-View Hand Mesh Benchmark for Accurate 3D Hand Pose Estimation Open
Estimating 3D hand poses from a single RGB image is challenging because depth ambiguity leads the problem ill-posed. Training hand pose estimators with 3D hand mesh annotations and multi-view images often results in significant performance…
View article: DGGAN: Depth-image Guided Generative Adversarial Networks for Disentangling RGB and Depth Images in 3D Hand Pose Estimation
DGGAN: Depth-image Guided Generative Adversarial Networks for Disentangling RGB and Depth Images in 3D Hand Pose Estimation Open
Estimating3D hand poses from RGB images is essentialto a wide range of potential applications, but is challengingowing to substantial ambiguity in the inference of depth in-formation from RGB images. State-of-the-art estimators ad-dress th…
View article: Temporal-Aware Self-Supervised Learning for 3D Hand Pose and Mesh Estimation in Videos
Temporal-Aware Self-Supervised Learning for 3D Hand Pose and Mesh Estimation in Videos Open
Estimating 3D hand pose directly from RGB imagesis challenging but has gained steady progress recently bytraining deep models with annotated 3D poses. Howeverannotating 3D poses is difficult and as such only a few 3Dhand pose datasets are …
View article: Towards Good Practices in Self-supervised Representation Learning
Towards Good Practices in Self-supervised Representation Learning Open
Self-supervised representation learning has seen remarkable progress in the last few years. More recently, contrastive instance learning has shown impressive results compared to its supervised learning counterparts. However, even with the …
View article: MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis
MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis Open
Estimating the 3D hand pose from a monocular RGB image is important but challenging. A solution is training on large-scale RGB hand images with accurate 3D hand keypoint annotations. However, it is too expensive in practice. Instead, we ha…
View article: A pyrene-based ratiometric fluorescent probe with a large Stokes shift for selective detection of hydrogen peroxide in living cells
A pyrene-based ratiometric fluorescent probe with a large Stokes shift for selective detection of hydrogen peroxide in living cells Open
View article: Generating Realistic Training Images Based on Tonality-Alignment Generative Adversarial Networks for Hand Pose Estimation
Generating Realistic Training Images Based on Tonality-Alignment Generative Adversarial Networks for Hand Pose Estimation Open
Hand pose estimation from a monocular RGB image is an important but challenging task. The main factor affecting its performance is the lack of a sufficiently large training dataset with accurate hand-keypoint annotations. In this work, we …
View article: Distinguish Polarity in Bag-of-Words Visualization
Distinguish Polarity in Bag-of-Words Visualization Open
Neural network-based BOW models reveal that word-embedding vectors encode strong semantic regularities. However, such models are insensitive to word polarity. We show that, coupled with simple information such as word spellings, word-embed…
View article: Experimental studies of diffusion welding of YBCO to copper using solder layers
Experimental studies of diffusion welding of YBCO to copper using solder layers Open
The welding technology is of great importance in YBCO application. To make better joints, the diffusion welding of YBCO tape to copper has been carried out in a vacuum environment. In consideration of high welding temperature (above 200°C)…
View article: Variational hybridization and transformation for large inaccurate noisy-or networks
Variational hybridization and transformation for large inaccurate noisy-or networks Open
Variational inference provides approximations to the computationally intractable posterior distribution in Bayesian networks. A prominent medical application of noisy-or Bayesian network is to infer potential diseases given observed sympto…
View article: Reducing infrequent-token perplexity via variational corpora
Reducing infrequent-token perplexity via variational corpora Open
Yusheng Xie, Pranjal Daga, Yu Cheng, Kunpeng Zhang, Ankit Agrawal, Alok Choudhary. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Proce…