82 citations · 289 across the 23 of their papers we have counts for
23 papers
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
Yangguang Li, Zi-Xin Zou, Zexiang Liu +8
Recent advancements in diffusion techniques have propelled image and video generation to unprecedented levels of quality, significantly accelerating the deployment and application…
SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
Yuanzhi Zhu, Xingchao Liu, Qiang Liu
Diffusion models excel in high-quality generation but suffer from slow inference due to iterative sampling. While recent methods have successfully transformed diffusion models into…
Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
Ling Yang, Zixiang Zhang, Zhilong Zhang +6
Flow matching (FM) is a general framework for defining probability paths via Ordinary Differential Equations (ODEs) to transform between noise and data samples. Recent approaches a…
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Zhimin Li, Jianwei Zhang, Qin Lin +42
We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transfo…
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Hanshu Yan, Xingchao Liu, Jiachun Pan +3
We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time win…
Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows
Shujian Zhang, Lemeng Wu, Chengyue Gong +1
Recent works have demonstrated success in controlling sentence attributes (, sentiment) and structure (, syntactic structure) based on the diffusion language model. A k…
AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies
Xixi Hu, Bo Liu, Xingchao Liu +1
Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in…
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Xingchao Liu, Xiwen Zhang, Jianzhu Ma +2
Diffusion models have revolutionized text-to-image generation with its exceptional quality and creativity. However, its multi-step sampling process is known to be slow, often requi…
AutoML-GPT: Automatic Machine Learning with GPT
Shujian Zhang, Chengyue Gong, Lemeng Wu +2
AI tasks encompass a wide range of domains and fields. While numerous AI models have been designed for specific tasks and applications, they often require considerable human effort…
Fast Point Cloud Generation with Straight Flows
Lemeng Wu, Dilin Wang, Chengyue Gong +6
Diffusion models have emerged as a powerful tool for point cloud generation. A key component that drives the impressive performance for generating high-quality samples from noise i…
Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models
Shujian Zhang, Chengyue Gong, Xingchao Liu
Retriever-reader models achieve competitive performance across many different NLP tasks such as open question answering and dialogue conversations. In this work, we notice these mo…
Neural Volumetric Mesh Generator
Yan Zheng, Lemeng Wu, Xingchao Liu +3
Deep generative models have shown success in generating 3D shapes with different representations. In this work, we propose Neural Volumetric Mesh Generator(NVMG) which can generate…
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Xingchao Liu, Chengyue Gong, Qiang Liu
We present rectified flow, a surprisingly simple approach to learning (neural) ordinary differential equation (ODE) models to transport between two empirically observed distributio…
Diffusion-based Molecule Generation with Informative Prior Bridges
Lemeng Wu, Chengyue Gong, Xingchao Liu +2
AI-based molecule generation provides a promising approach to a large area of biomedical sciences and engineering, such as antibody design, hydrolase engineering, or vaccine develo…
Let us Build Bridges: Understanding and Extending Diffusion Generative Models
Xingchao Liu, Lemeng Wu, Mao Ye +1
Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorit…
A Langevin-like Sampler for Discrete Distributions
Ruqi Zhang, Xingchao Liu, Qiang Liu
We propose discrete Langevin proposal (DLP), a simple and scalable gradient-based proposal for sampling complex high-dimensional discrete distributions. In contrast to Gibbs sampli…
ALLSH: Active Learning Guided by Local Sensitivity and Hardness
Shujian Zhang, Chengyue Gong, Xingchao Liu +3
Active learning, which effectively collects informative unlabeled data for annotation, reduces the demand for labeled data. In this work, we propose to retrieve unlabeled samples w…
FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization
Xingchao Liu, Chengyue Gong, Lemeng Wu +3
Generating images from natural language instructions is an intriguing yet highly challenging task. We approach text-to-image generation by combining the power of the retrained CLIP…
Conflict-Averse Gradient Descent for Multi-task Learning
Bo Liu, Xingchao Liu, Xiaojie Jin +2
The goal of multi-task learning is to enable more efficient learning than single task learning by sharing model structures for a diverse set of tasks. A standard multi-task learnin…
Centroid Transformers: Learning to Abstract with Attention
Lemeng Wu, Xingchao Liu, Qiang Liu
Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs. In essence, what self-attention does is to infer the pairwise rel…
Certified Monotonic Neural Networks
Xingchao Liu, Xing Han, Na Zhang +1
Learning monotonic models with respect to a subset of the inputs is a desirable feature to effectively address the fairness, interpretability, and generalization issues in practice…
Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
Xingchao Liu, Mao Ye, Dengyong Zhou +1
We consider the post-training quantization problem, which discretizes the weights of pre-trained deep neural networks without re-training the model. We propose multipoint quantizat…