18 citations · 34 across the 14 of their papers we have counts for
16 papers
LoopREG: Representation Supervision Enables Test-Time Recurrent Depth in Diffusion Transformers
Zipeng Wang, Anping Xiong, Jing Zhang +17
Reusing Transformer blocks offers a way to increase diffusion-model computation at test time, but naive recurrence can degrade generation beyond its training depth. We introduce Lo…
Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning
Ping Chen, Xiang Liu, Xingpeng Zhang +7
Diffusion models operate in a reflexive System 1 mode, constrained by a fixed, content-agnostic sampling schedule. This rigidity arises from the curse of state dimensionality, wher…
Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D
Ping Chen, Zezhou Chen, Xingpeng Zhang +8
Current 2D-to-3D conversion methods achieve geometric accuracy but are artistically deficient, failing to replicate the immersive and emotionally resonant experience of professiona…
PSTF-AttControl: Per-Subject-Tuning-Free Personalized Image Generation with Controllable Face Attributes
Xiang liu, Zhaoxiang Liu, Huan Hu +5
Recent advancements in personalized image generation have significantly improved facial identity preservation, particularly in fields such as entertainment and social media. Howeve…
Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity
Ping Chen, Xiang Liu, Zhaoxiang Liu +7
With the rapid advancement of large language models (LLMs), natural language processing (NLP) has achieved remarkable progress. Nonetheless, significant challenges remain in handli…
Hierarchical Deep Fusion Framework for Multi-dimensional Facial Forgery Detection -- The 2024 Global Deepfake Image Detection Challenge
Kohou Wang, Huan Hu, Xiang Liu +4
The proliferation of sophisticated deepfake technology poses significant challenges to digital security and authenticity. Detecting these forgeries, especially across a wide spectr…
iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement
Kohou Wang, ZhaoXiang Liu, Lin Bai +5
It is crucial that robots' performance can be improved after deployment, as they are inherently likely to encounter novel scenarios never seen before. This paper presents an innova…
SLearnLLM: A Self-Learning Framework for Efficient Domain-Specific Adaptation of Large Language Models
Xiang Liu, Zhaoxiang Liu, Peng Wang +4
When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tun…
Optimizing for the Shortest Path in Denoising Diffusion Model
Ping Chen, Xingpeng Zhang, Zhaoxiang Liu +6
In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality.…
A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis
Xiang Liu, Zhaoxiang Liu, Huan Hu +4
While conversational generative AI has shown considerable potential in enhancing decision-making for agricultural professionals, its exploration has predominantly been anchored in…
StageDesigner: Artistic Stage Generation for Scenography via Theater Scripts
Zhaoxing Gan, Mengtian Li, Ruhua Chen +5
In this work, we introduce StageDesigner, the first comprehensive framework for artistic stage generation using large language models combined with layout-controlled diffusion mode…
Data-Centric AI Paradigm Based on Application-Driven Fine-Grained Dataset Design
Huan Hu, Yajie Cui, Zhaoxiang Liu +1
Deep learning has a wide range of applications in industrial scenario, but reducing false alarm (FA) remains a major difficulty. Optimizing network architecture or network paramete…
A Neural Virtual Anchor Synthesizer based on Seq2Seq and GAN Models
Zipeng Wang, Zhaoxiang Liu, Zezhou Chen +2
This paper presents a novel framework to generate realistic face video of an anchor, who is reading certain news. This task is also known as Virtual Anchor. Given some paragraphs o…
Video synthesis of human upper body with realistic face
Zhaoxiang Liu, Huan Hu, Zipeng Wang +3
This paper presents a generative adversarial learning-based human upper body video synthesis approach to generate an upper body video of target person that is consistent with the b…
A Realistic Face-to-Face Conversation System based on Deep Neural Networks
Zezhou Chen, Zhaoxiang Liu, Huan Hu +4
To improve the experiences of face-to-face conversation with avatar, this paper presents a novel conversation system. It is composed of two sequence-to-sequence models respectively…
Feature Aggregation Network for Video Face Recognition
Zhaoxiang Liu, Huan Hu, Jinqiang Bai +2
This paper aims to learn a compact representation of a video for video face recognition task. We make the following contributions: first, we propose a meta attention-based aggregat…