Publications (30)
The Square of Nijenhuis Tensor and Its Vanishing Results
Jun Ling
We give the strong form and the weak form of the square of Nijenhuis tensor, and some vanish results of the square.
Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO
Xuzheng Yang, Jun Ling, Tao Huang +2
We tackle the challenging yet underexplored task of Generalized Referring Expression Comprehension (GREC), which requires a model to localize the object described by a textual expr…
SemanticGarment: Semantic-Controlled Generation and Editing of 3D Gaussian Garments
Ruiyan Wang, Zhengxue Cheng, Zonghao Lin +5
3D digital garment generation and editing play a pivotal role in fashion design, virtual try-on, and gaming. Traditional methods struggle to meet the growing demand due to technica…
Some Asymptotic Behavior of the first Eigenvalue along the Ricci Flow
Jun Ling
We study some asymptotic behavior of the first nonzero eigenvalue of the Lalacian along the normalized Ricci flow and give a direct short proof for an asymptotic upper limit estima…
Estimates on the Lower Bound of the First Gap
Jun Ling
We give a new lower bound for the first gap of the Dirichlet eigenvalues of the Schr{ö}dinger operator on a bounded convex domain in R or S and greatly…
A Class of Monotonic Quantities along the Ricci Flow
Jun Ling
We construct a class of monotonic quantities along the normalized Ricci flow on closed n-dimensional manifolds.
A Function obstruction to the Existence of Complex Structures
Jun Ling
We construct a function for almost-complex Riemannian manifolds. Non-vanishing of the function for the almost-complex structure implies the almost-complex structure is not integrab…
GOTS: Greedy Orthogonal Token Selection for High-Resolution Vision-Language Models
Jun Ling, Tao Huang, Junzhuo Liu +2
Modern vision-language models (VLMs) increasingly rely on dynamic or high-resolution visual encoding, producing thousands of visual tokens that substantially increase downstream la…
A Comparison Theorem and A Sharp Bound via the Ricci Flow
Jun Ling
We prove a comparison theorem for the compact surfaces with negative Euler characteristic via the Ricci flow.
VAST: Vivify Your Talking Avatar via Zero-Shot Expressive Facial Style Transfer
Liyang Chen, Zhiyong Wu, Runnan Li +4
Current talking face generation methods mainly focus on speech-lip synchronization. However, insufficient investigation on the facial talking style leads to a lifeless and monotono…
The Non-existence of Complex Sphere ()
Jun Ling
There is error in (2.1). I am very sorry for inconvenience.
Toward Fine-grained Facial Expression Manipulation
Jun Ling, Han Xue, Li Song +3
Facial expression manipulation aims at editing facial expression with a given condition. Previous methods edit an input image under the guidance of a discrete emotion label or abso…
Lower Bounds of the First Closed and Neumann Eigenvalues of Compact Manifolds with Positive Ricci Curvature
Jun Ling
We give new estimates on the lower bounds for the first closed or Neumann eigenvalue for a compact manifold with positive Ricci curvature in terms of the diameter and the lower bou…
A Lower Bound of The First Eigenvalue of a Closed Manifold with Positive Ricci Curvature
Jun Ling
We give an estimate on the lower bound of the first non-zero eigenvalue of the Laplacian for a closed Riemannian manifold with positive Ricci curvature in terms of the in-diameter…
Region-aware Adaptive Instance Normalization for Image Harmonization
Jun Ling, Han Xue, Li Song +2
Image composition plays a common but important role in photo editing. To acquire photo-realistic composite images, one must adjust the appearance and visual style of the foreground…
When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents
Junzhuo Liu, Weiwei Li, Jun Ling +1
Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher to re-score the student's response at every turn with access t…
A Lower Bound of the First Eigenvalue of a Closed Manifold with Negative Lower Bound of the Ricci Curvature
Jun Ling
Along the line of the Yang Conjecture, we give a new estimate on the lower bound of the first non-zero eigenvalue of a closed Riemannian manifold with negative lower bound of Ricci…
Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models
Jun Ling, Yao Qi, Tao Huang +8
In this work, we address the task of table image to LaTeX code generation, with the goal of automating the reconstruction of high-quality, publication-ready tables from visual inpu…
Memories are One-to-Many Mapping Alleviators in Talking Face Generation
Anni Tang, Tianyu He, Xu Tan +2
Talking face generation aims at generating photo-realistic video portraits of a target person driven by input audio. Due to its nature of one-to-many mapping from the input audio t…
360-Degree Panorama Generation from Few Unregistered NFoV Images
Jionghao Wang, Ziyu Chen, Jun Ling +2
360 panoramas are extensively utilized as environmental light sources in computer graphics. However, capturing a 360 180 panorama poses challenges…
Transformer-S2A: Robust and Efficient Speech-to-Animation
Liyang Chen, Zhiyong Wu, Jun Ling +3
We propose a novel robust and efficient Speech-to-Animation (S2A) approach for synchronized facial animation generation in human-computer interaction. Compared with conventional ap…
Dual Forms of the Squares of Nijenhuis Tensor
Jun Ling
We express the dual forms of squares of Nijenhuis tensor in terms of the second order component derivatives of the exterior derivative on differential forms and give new vanishing…
Context-Aware Talking-Head Video Editing
Songlin Yang, Wei Wang, Jun Ling +3
Talking-head video editing aims to efficiently insert, delete, and substitute the word of a pre-recorded video through a text transcript editor. The key challenge for this task is…
PoseTalk: Text-and-Audio-based Pose Control and Motion Refinement for One-Shot Talking Head Generation
Jun Ling, Yiwen Wang, Han Xue +2
While previous audio-driven talking head generation (THG) methods generate head poses from driving audio, the generated poses or lips cannot match the audio well or are not editabl…
Learning Dense UV Completion for Human Mesh Recovery
Yanjun Wang, Qingping Sun, Wenjia Wang +4
Human mesh reconstruction from a single image is challenging in the presence of occlusion, which can be caused by self, objects, or other humans. Existing methods either fail to se…
PA-HOI: A Physics-Aware Human and Object Interaction Dataset
Ruiyan Wang, Lin Zuo, Zonghao Lin +5
The Human-Object Interaction (HOI) task explores the dynamic interactions between humans and objects in physical environments, providing essential biomechanical and cognitive-behav…
Generative Compression for Face Video: A Hybrid Scheme
Anni Tang, Yan Huang, Jun Ling +4
As the latest video coding standard, versatile video coding (VVC) has shown its ability in retaining pixel quality. To excavate more compression potential for video conference scen…
StableFace: Analyzing and Improving Motion Stability for Talking Face Generation
Jun Ling, Xu Tan, Liyang Chen +4
While previous speech-driven talking face generation methods have made significant progress in improving the visual quality and lip-sync quality of the synthesized videos, they pay…
The first Dirichlet Eigenvalue of a Compact Manifold and the Yang Conjecture
Jun Ling
We give a new estimate on the lower bound of the first Dirichlet eigenvalue of a compact Riemannian manifold with negative lower bound of Ricci curvature and provide a solution for…
A Lower Bound of the First Dirichlet Eigenvalue of a Compact Manifold with Positive Ricci Curvature
Jun Ling
We give a new estimate on the lower bound for the first Dirichlet eigenvalue for a compact manifold with positive Ricci curvature in terms of the in-diameter and the lower bound of…