Search Results for author:
Found 34 papers, 20 papers with code
DeepSeek-V3 Technical Report
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key major upgrades.
Ranked #1 on
Referring Expression Comprehension
on RefCOCOg-test
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
To further improve the performance of our unified model, we adopt two key strategies: (i) decoupling the understanding and generation encoders, and (ii) aligning their representations during unified training.
Ranked #197 on
Visual Question Answering
on MM-Vet
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
In this paper, we introduce Janus, an autoregressive framework that unifies multimodal understanding and generation.
Ranked #164 on
Visual Question Answering
on MM-Vet
SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
The rectified flow framework trains one-step generative models using two operations, reflow and distillation.
Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
Additionally, we propose a multi-segment training approach for Consistency-FM to enhance expressiveness, achieving a better trade-off between sampling quality and speed.
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images.
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models.
Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows
Extensive experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.
AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies
To address this challenge, we propose AdaFlow, an imitation learning framework based on flow-based generative modeling.
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Leveraging our new pipeline, we create, to the best of our knowledge, the first one-step diffusion-based text-to-image generator with SD-level image quality, achieving an FID (Frechet Inception Distance) of $23. 3$ on MS COCO 2017-5k, surpassing the previous state-of-the-art technique, progressive distillation, by a significant margin ($37. 2$ $\rightarrow$ $23. 3$ in FID).
AutoML-GPT: Automatic Machine Learning with GPT
Ultimately, with this prompt paragraph, AutoML-GPT will automatically conduct the experiments from data processing to model architecture, hyperparameter tuning, and predicted training log.
FlowGrad: Controlling the Output of Generative ODEs With Gradients
To further accelerate the computation of the back-propagation, we propose to use a non-uniform discretization to approximate the ODE trajectory, where we measure how straight the trajectory is and gather the straight parts into one discretization step.
Fast Point Cloud Generation with Straight Flows
We perform evaluations on multiple 3D tasks and find that our PSF performs comparably to the standard diffusion model, outperforming other efficient 3D point cloud generation methods.
Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models
Experiments on different tasks across open question answering, dialogue conversation, and fact verification show that our method consistently outperforms its baselines.
Neural Volumetric Mesh Generator
We first propose a diffusion-based generative model to tackle this problem by generating voxelized shapes with close-to-reality outlines and structures.
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
The idea of rectified flow is to learn the ODE to follow the straight paths connecting the points drawn from \pi_0 and \pi_1 as much as possible.
Diffusion-based Molecule Generation with Informative Prior Bridges
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 development.
Let us Build Bridges: Understanding and Extending Diffusion Generative Models
Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorithm improvement and extensions to discrete, structured, non-Euclidean domains.
A Langevin-like Sampler for Discrete Distributions
We propose discrete Langevin proposal (DLP), a simple and scalable gradient-based proposal for sampling complex high-dimensional discrete distributions.
ALLSH: Active Learning Guided by Local Sensitivity and Hardness
Active learning, which effectively collects informative unlabeled data for annotation, reduces the demand for labeled data.
FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization
We approach text-to-image generation by combining the power of the retrained CLIP representation with an off-the-shelf image generator (GANs), optimizing in the latent space of GAN to find images that achieve maximum CLIP score with the given input text.
Ranked #46 on
Text-to-Image Generation
on MS COCO
Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach
In this work, we consider constrained optimization as a more principled approach for trading off two losses, with a special emphasis on lexicographic optimization, a degenerated limit of constrained optimization which optimizes a secondary loss inside the optimal set of the main loss.
Sampling with Trusthworthy Constraints: A Variational Gradient Framework
In this work, we propose a family of constrained sampling algorithms which generalize Langevin Dynamics (LD) and Stein Variational Gradient Descent (SVGD) to incorporate a moment constraint specified by a general nonlinear function.
Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent
Finding diverse and representative Pareto solutions from the Pareto front is a key challenge in multi-objective optimization (MOO).
Conflict-Averse Gradient Descent for Multi-task Learning
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.
Sampling with Trusthworthy Constraints: A Variational Gradient Framework
In this work, we propose a family of constrained sampling algorithms which generalize Langevin Dynamics (LD) and Stein Variational Gradient Descent (SVGD) to incorporate a moment constraint specified by a general nonlinear function.
Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent
Finding diverse and representative Pareto solutions from the Pareto front is a key challenge in multi-objective optimization (MOO).
Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach
In this work, we consider constrained optimization as a more principled approach for trading off two losses, with a special emphasis on lexicographic optimization, a degenerated limit of constrained optimization which optimizes a secondary loss inside the optimal set of the main loss.
Centroid Transformers: Learning to Abstract with Attention
Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs.
Ranked #672 on
Image Classification
on ImageNet
Fast Training of Contrastive Learning with Intermediate Contrastive Loss
We apply our method to recently-proposed MOCO, SimCLR, SwAV and notice that we can reduce the computational cost with little loss on the performance of ImageNet linear classification and other downstream tasks.
Certified Monotonic Neural Networks
In this work, we propose to certify the monotonicity of the general piece-wise linear neural networks by solving a mixed integer linear programming problem. This provides a new general approach for learning monotonic neural networks with arbitrary model structures.
Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
We propose multipoint quantization, a quantization method that approximates a full-precision weight vector using a linear combination of multiple vectors of low-bit numbers; this is in contrast to typical quantization methods that approximate each weight using a single low precision number.
Transfer Value or Policy? A Value-centric Framework Towards Transferrable Continuous Reinforcement Learning
In this paper, we investigate the problem of transfer learning across environments with different dynamics while accomplishing the same task in the continuous control domain.
