Yunliang Jiang
YOU?
Author Swipe
View article: Reinforcement Learning on Pre-Training Data
Reinforcement Learning on Pre-Training Data Open
The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…
View article: Numerical Investigation of Water Wave Impacting a Structure Using Fluid–Structure Interaction Simulation
Numerical Investigation of Water Wave Impacting a Structure Using Fluid–Structure Interaction Simulation Open
Unmanned surface vehicles (USVs) have great application prospects in defense, environmental surveillance and offshore energy due to their cost-effectiveness and long-duration mission ability. The structural safety issues induced by the pro…
View article: Technical Report of TeleChat2, TeleChat2.5 and T1
Technical Report of TeleChat2, TeleChat2.5 and T1 Open
We introduce the latest series of TeleChat models: \textbf{TeleChat2}, \textbf{TeleChat2.5}, and \textbf{T1}, offering a significant upgrade over their predecessor, TeleChat. Despite minimal changes to the model architecture, the new serie…
View article: Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework
Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework Open
Recent advances in large language models (LLMs) have accelerated progress toward artificial general intelligence, with inference-time scaling emerging as a key technique. Contemporary approaches leverage either sequential reasoning (iterat…
View article: Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking
Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking Open
This paper considers the problem of decentralized optimization on compact submanifolds, where a finite sum of smooth (possibly non-convex) local functions is minimized by $n$ agents forming an undirected and connected graph. However, the e…
View article: ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detection
ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detection Open
The out-of-distribution (OOD) detection on graph-structured data is crucial for deploying graph neural networks securely in open-world scenarios. However, existing methods have overlooked the prevalent scenario of multi-label classificatio…
View article: Out-of-Distribution Detection on Graphs: A Survey
Out-of-Distribution Detection on Graphs: A Survey Open
Graph machine learning has witnessed rapid growth, driving advancements across diverse domains. However, the in-distribution assumption, where training and testing data share the same distribution, often breaks in real-world scenarios, lea…
View article: A New Formulation of Lipschitz Constrained With Functional Gradient Learning for GANs
A New Formulation of Lipschitz Constrained With Functional Gradient Learning for GANs Open
This paper introduces a promising alternative method for training Generative Adversarial Networks (GANs) on large-scale datasets with clear theoretical guarantees. GANs are typically learned through a minimax game between a generator and a…
View article: MVGNet: Prediction of PI3K Inhibitors Using Multitask Learning and Multiview Frameworks
MVGNet: Prediction of PI3K Inhibitors Using Multitask Learning and Multiview Frameworks Open
PI3K (phosphatidylinositol 3-kinase) is an intracellular phosphatidylinositol kinase composed of a regulatory subunit, p85, and a catalytic subunit, p110. Based on the different structures of the p110 catalytic subunit, PI3K can be divided…
View article: Nested Annealed Training Scheme for Generative Adversarial Networks
Nested Annealed Training Scheme for Generative Adversarial Networks Open
Recently, researchers have proposed many deep generative models, including generative adversarial networks(GANs) and denoising diffusion models. Although significant breakthroughs have been made and empirical success has been achieved with…
View article: Mask‐guided image person removal with data synthesis
Mask‐guided image person removal with data synthesis Open
As a special case of common object removal, image person removal is playing an increasingly important role in social media and criminal investigation domains. Due to the integrity of person area and the complexity of human posture, person …
View article: TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation
TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation Open
One-shot image generation (OSG) with generative adversarial networks that learn from the internal patches of a given image has attracted world wide attention. In recent studies, scholars have primarily focused on extracting features of ima…
View article: Fuzzy Knowledge Distillation from High-Order TSK to Low-Order TSK
Fuzzy Knowledge Distillation from High-Order TSK to Low-Order TSK Open
High-order Takagi-Sugeno-Kang (TSK) fuzzy classifiers possess powerful classification performance yet have fewer fuzzy rules, but always be impaired by its exponential growth training time and poorer interpretability owing to High-order po…
View article: AFTGAN: prediction of multi-type PPI based on attention free transformer and graph attention network
AFTGAN: prediction of multi-type PPI based on attention free transformer and graph attention network Open
Motivation Protein–protein interaction (PPI) networks and transcriptional regulatory networks are critical in regulating cells and their signaling. A thorough understanding of PPIs can provide more insights into cellular physiology at norm…
View article: Mask-Guided Image Person Removal with Data Synthesis
Mask-Guided Image Person Removal with Data Synthesis Open
As a special case of common object removal, image person removal is playing an increasingly important role in social media and criminal investigation domains. Due to the integrity of person area and the complexity of human posture, person …
View article: A 3D printing tool-path generation strategy based on the partition of principal stress field for FFF Platform
A 3D printing tool-path generation strategy based on the partition of principal stress field for FFF Platform Open
In order to enhance the strength of 3D printed parts made of polymer materials and reduce the anisotropy caused by the fused filament fabrication process, this paper proposes an inter-layer interleaved composite path planning method based …
View article: APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment
APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment Open
Audio-guided face reenactment aims to generate a photorealistic face that has matched facial expression with the input audio. However, current methods can only reenact a special person once the model is trained or need extra operations suc…
View article: DTVNet+: A High-Resolution Scenic Dataset for Dynamic Time-lapse Video Generation
DTVNet+: A High-Resolution Scenic Dataset for Dynamic Time-lapse Video Generation Open
This paper presents a novel end-to-end dynamic time-lapse video generation framework, named DTVNet, to generate diversified time-lapse videos from a single landscape image conditioned on normalized motion vectors. The proposed DTVNet consi…