Search Results for author:
Found 27 papers, 11 papers with code
Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
Diffusion models have demonstrated remarkable performance in generating unimodal data across various tasks, including image, video, and text generation.
Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Models
We conduct extensive and comprehensive experiments on both perception- and reasoning-required datasets with open-source VLMs ranging from 3B to 72B and proprietary models such as Gemini 2. 0.
FF-PNet: A Pyramid Network Based on Feature and Field for Brain Image Registration
To address this, we construct a new pyramid registration network based on feature and deformation field (FF-PNet).
Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms
We rigorously analyze the proposed schemes and establish the second-order accuracy of the $\theta$-trapezoidal method in KL divergence.
Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images
Through better capturing the inherent stochasticity and heterogeneity in ST data, $\textbf{Stem}$ achieves state-of-the-art performance on spatial gene expression prediction and generates biologically meaningful gene profiles for new H&E stained images at test time.
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
Ranked #2 on
Mathematical Reasoning
on AIME24
Rethinking Query-based Transformer for Continual Image Segmentation
To address these, we conduct an in-depth investigation of the built-in objectness and find that highly aggregated image features provide a shortcut for queries to generate masks through simple feature alignment.
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.
When Can Proxies Improve the Sample Complexity of Preference Learning?
In these cases, it is often unclear whether the addition of proxy data can improve policy learning.
Generative modeling assisted simulation of measurement-altered quantum criticality
In quantum many-body systems, measurements can induce qualitative new features, but their simulation is hindered by the exponential complexity involved in sampling the measurement results.
Learning to Stop: Deep Learning for Mean Field Optimal Stopping
Optimal stopping is a fundamental problem in optimization with applications in risk management, finance, robotics, and machine learning.
Plug-and-Play Controllable Generation for Discrete Masked Models
This methodological development enables broad applications across downstream tasks such as class-specific image generation and protein design.
Plain-Det: A Plain Multi-Dataset Object Detector
Recent advancements in large-scale foundational models have sparked widespread interest in training highly proficient large vision models.
Token-Mol 1.0: Tokenized drug design with large language model
This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in drug discovery into probabilistic prediction problems, thereby enabling learning through a unified paradigm.
Human-level molecular optimization driven by mol-gene evolution
De novo molecule generation allows the search for more drug-like hits across a vast chemical space.
Structured Learning of Compositional Sequential Interventions
We show the identification properties of our compositional model, inspired by advances in causal matrix factorization methods.
Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups
However, our trivialization technique creates to a new momentum variable that stays in a simple $\textbf{fixed vector space}$.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.
A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization
Under this regime, the stochastic gradient descent-ascent corresponds to a Wasserstein gradient flow over the space of probability measures defined over the space of neural network parameters.
Quantum State Generation with Structure-Preserving Diffusion Model
This article considers the generative modeling of the (mixed) states of quantum systems, and an approach based on denoising diffusion model is proposed.
Meaningful Causal Aggregation and Paradoxical Confounding
On the positive side, we show that cause-effect relations can be aggregated when the macro interventions are such that the distribution of micro states is the same as in the observational distribution; we term this natural macro interventions.
Deep Learning for Mean Field Optimal Transport
The first one is based on directly learning an optimal control.
Causal Inference with Treatment Measurement Error: A Nonparametric Instrumental Variable Approach
We propose a kernel-based nonparametric estimator for the causal effect when the cause is corrupted by error.
Causal Effect Inference for Structured Treatments
We address the estimation of conditional average treatment effects (CATEs) for structured treatments (e. g., graphs, images, texts).
Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction
In particular, we provide a unifying view of two-stage and moment restriction approaches for solving this problem in a nonlinear setting.
Model Rectification via Unknown Unknowns Extraction from Deployment Samples
Model deficiency that results from incomplete training data is a form of structural blindness that leads to costly errors, oftentimes with high confidence.
EQuANt (Enhanced Question Answer Network)
By training and evaluating EQuANt on SQuAD 2, we show that it is indeed possible to extend QANet to the unanswerable domain.
