Search Results for author:
Found 88 papers, 24 papers with code
Accept More, Reject Less: Reducing up to 19% Unnecessary Desk-Rejections over 11 Years of ICLR Data
The explosive growth of AI research has driven paper submissions at flagship AI conferences to unprecedented levels, necessitating many venues in 2025 (e. g., CVPR, ICCV, KDD, AAAI, IJCAI, WSDM) to enforce strict per-author submission limits and to desk-reject any excess papers by simple ID order.
Ming-Omni: A Unified Multimodal Model for Perception and Generation
We propose Ming-Omni, a unified multimodal model capable of processing images, text, audio, and video, while demonstrating strong proficiency in both speech and image generation.
Proactive Guidance of Multi-Turn Conversation in Industrial Search
The evolution of Large Language Models (LLMs) has significantly advanced multi-turn conversation systems, emphasizing the need for proactive guidance to enhance users' interactions.
Sci-Fi: Symmetric Constraint for Frame Inbetweening
Frame inbetweening aims to synthesize intermediate video sequences conditioned on the given start and end frames.
ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representations
Visual-Interleaved Chain-of-Thought (VI-CoT) enables MLLMs to continually update their understanding and decisions based on step-wise intermediate visual states (IVS), much like a human would, which demonstrates impressive success in various tasks, thereby leading to emerged advancements in related benchmarks.
Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese
Recent advances in large language models (LLMs) have significantly improved text-to-speech (TTS) systems, enhancing control over speech style, naturalness, and emotional expression, which brings TTS Systems closer to human-level performance.
GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
Despite remarkable advancements in video depth estimation, existing methods exhibit inherent limitations in achieving geometric fidelity through the affine-invariant predictions, limiting their applicability in reconstruction and other metrically grounded downstream tasks.
Exploring the Limits of KV Cache Compression in Visual Autoregressive Transformers
In this work, we take the first step in formally defining the KV-cache compression problem for Visual Autoregressive transformers.
SMILE: a Scale-aware Multiple Instance Learning Method for Multicenter STAS Lung Cancer Histopathology Diagnosis
To address the bias, sparse and heterogeneous nature of STAS, we propose an scale-aware multiple instance learning(SMILE) method for STAS diagnosis of lung cancer.
BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing
Element-level visual manipulation is essential in digital content creation, but current diffusion-based methods lack the precision and flexibility of traditional tools.
Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding
The key-value (KV) cache in the tensor version of transformers presents a significant bottleneck during inference.
Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows
Flow matching has emerged as a powerful framework for generative modeling, offering computational advantages over diffusion models by leveraging deterministic Ordinary Differential Equations (ODEs) instead of stochastic dynamics.
Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content
While significant progress has been made in developing objective models to assess these dimensions, the performance of such models heavily relies on the scale and quality of human annotations.
On Computational Limits of FlowAR Models: Expressivity and Efficiency
In this study, we address this gap by analyzing the circuit complexity of the FlowAR architecture.
Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies
As AI research surges in both impact and volume, conferences have imposed submission limits to maintain paper quality and alleviate organizational pressure.
Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers
In this work, we extend the Loop Transformer architecture's neural algorithmic reasoning capability to simulate hypergraph algorithms, addressing the gap between neural networks and combinatorial optimization over hypergraphs.
RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation
This limitation often arises from the inability of the text encoder to produce accurate embeddings, which hinders the video generation model.
On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective
Graph Neural Networks (GNNs) have become the standard approach for learning and reasoning over relational data, leveraging the message-passing mechanism that iteratively propagates node embeddings through graph structures.
Circuit Complexity Bounds for Visual Autoregressive Model
Understanding the expressive ability of a specific model is essential for grasping its capacity limitations.
On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis
Recently, Visual Autoregressive ($\mathsf{VAR}$) Models introduced a groundbreaking advancement in the field of image generation, offering a scalable approach through a coarse-to-fine ``next-scale prediction'' paradigm.
DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
Based on our careful design, the video generated by DiTCtrl achieves smooth transitions and consistent object motion given multiple sequential prompts without additional training.
Theoretical Constraints on the Expressive Power of $\mathsf{RoPE}$-based Tensor Attention Transformers
Tensor Attention extends traditional attention mechanisms by capturing high-order correlations across multiple modalities, addressing the limitations of classical matrix-based attention.
Fast Gradient Computation for RoPE Attention in Almost Linear Time
The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information.
Grams: Gradient Descent with Adaptive Momentum Scaling
The results demonstrate Grams' superior performance, including faster convergence and better generalization, compared to widely-used optimizers such as Adam, Lion, and their cautious variants.
The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity
In this paper, we analyze the computational limitations of Mamba and State-space Models (SSMs) by using the circuit complexity framework.
On the Expressive Power of Modern Hopfield Networks
Modern Hopfield networks (MHNs) have emerged as powerful tools in deep learning, capable of replacing components such as pooling layers, LSTMs, and attention mechanisms.
NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images
Recent advancements in generative models have significantly improved novel view synthesis (NVS) from multi-view data.
Circuit Complexity Bounds for RoPE-based Transformer Architecture
In this work, we establish a circuit complexity bound for Transformers with $\mathsf{RoPE}$ attention.
Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent
Our results demonstrate that as long as the input data has a constant condition number, e. g., $n = O(d)$, the linear looped Transformers can achieve a small error by multi-step gradient descent during in-context learning.
Advancing the Understanding of Fixed Point Iterations in Deep Neural Networks: A Detailed Analytical Study
Recent empirical studies have identified fixed point iteration phenomena in deep neural networks, where the hidden state tends to stabilize after several layers, showing minimal change in subsequent layers.
Fine-grained Attention I/O Complexity: Comprehensive Analysis for Backward Passes
For small cache sizes, we provide an algorithm that improves over existing methods and achieves the tight bounds.
Array2BR: An End-to-End Noise-immune Binaural Audio Synthesis from Microphone-array Signals
Telepresence technology aims to provide an immersive virtual presence for remote conference applications, and it is extremely important to synthesize high-quality binaural audio signals for this aim.
RockTrack: A 3D Robust Multi-Camera-Ken Multi-Object Tracking Framework
3D Multi-Object Tracking (MOT) obtains significant performance improvements with the rapid advancements in 3D object detection, particularly in cost-effective multi-camera setups.
StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos
This paper presents a novel framework for converting 2D videos to immersive stereoscopic 3D, addressing the growing demand for 3D content in immersive experience.
ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control.
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Our training approach enables the model to generate depth sequences with variable lengths at one time, up to 110 frames, and harvest both precise depth details and rich content diversity from realistic and synthetic datasets.
MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement
Existing works in single-image human reconstruction suffer from weak generalizability due to insufficient training data or 3D inconsistencies for a lack of comprehensive multi-view knowledge.
A Tighter Complexity Analysis of SparseGPT
In this work, we improved the analysis of the running time of SparseGPT [Frantar, Alistarh ICML 2023] from $O(d^{3})$ to $O(d^{\omega} + d^{2+a+o(1)} + d^{1+\omega(1, 1, a)-a})$ for any $a \in [0, 1]$, where $\omega$ is the exponent of matrix multiplication.
Fast John Ellipsoid Computation with Differential Privacy Optimization
Determining the John ellipsoid - the largest volume ellipsoid contained within a convex polytope - is a fundamental problem with applications in machine learning, optimization, and data analytics.
Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360°
To the best of our knowledge, our model is the first parametric 3D full-head that achieves 360{\deg} free-view synthesis, image-based fitting, appearance editing, and animation within a single model.
SpaDiT: Diffusion Transformer for Spatial Gene Expression Prediction using scRNA-seq
The rapid development of spatial transcriptomics (ST) technologies is revolutionizing our understanding of the spatial organization of biological tissues.
COT: A Generative Approach for Hate Speech Counter-Narratives via Contrastive Optimal Transport
This module achieves this by generating an anisotropic distribution of token representations.
CV-VAE: A Compatible Video VAE for Latent Generative Video Models
Moreover, since current diffusion-based approaches are often implemented using pre-trained text-to-image (T2I) models, directly training a video VAE without considering the compatibility with existing T2I models will result in a latent space gap between them, which will take huge computational resources for training to bridge the gap even with the T2I models as initialization.
Fast-Poly: A Fast Polyhedral Framework For 3D Multi-Object Tracking
3D Multi-Object Tracking (MOT) captures stable and comprehensive motion states of surrounding obstacles, essential for robotic perception.
Ranked #2 on
3D Multi-Object Tracking
on nuScenes
UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling
Therefore, we propose UV Gaussians, which models the 3D human body by jointly learning mesh deformations and 2D UV-space Gaussian textures.
stMCDI: Masked Conditional Diffusion Model with Graph Neural Network for Spatial Transcriptomics Data Imputation
Spatially resolved transcriptomics represents a significant advancement in single-cell analysis by offering both gene expression data and their corresponding physical locations.
Constraint Latent Space Matters: An Anti-anomalous Waveform Transformation Solution from Photoplethysmography to Arterial Blood Pressure
Arterial blood pressure (ABP) holds substantial promise for proactive cardiovascular health management.
Advances in 3D Generation: A Survey
In this survey, we aim to introduce the fundamental methodologies of 3D generation methods and establish a structured roadmap, encompassing 3D representation, generation methods, datasets, and corresponding applications.
ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesis
In this work, we propose a method to address the challenge of rendering a 3D human from a single image in a free-view manner.
HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion
Optimization-based methods that lift text-to-image diffusion models to 3D generation often fail to preserve the texture details of the reference image, resulting in inconsistent appearances in different views.
HiFi-123: Towards High-fidelity One Image to 3D Content Generation
Our contributions are twofold: First, we propose a Reference-Guided Novel View Enhancement (RGNV) technique that significantly improves the fidelity of diffusion-based zero-shot novel view synthesis methods.
Probing Large Language Models from A Human Behavioral Perspective
Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP.
Anti-Aliased Neural Implicit Surfaces with Encoding Level of Detail
Drawing inspiration from voxel-based representations with the level of detail (LoD), we introduce a multi-scale tri-plane-based scene representation that is capable of capturing the LoD of the signed distance function (SDF) and the space radiance.
Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals
Inspired by this, this paper innovatively proposes a multimodal Hypergraph-of-Thought (HoT) reasoning paradigm, which enables the foundation models to possess the expert-level ability of high-order multi-hop reasoning and multimodal comparative judgement.
Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields
Extensive experiments demonstrate that our Text2NeRF outperforms existing methods in producing photo-realistic, multi-view consistent, and diverse 3D scenes from a variety of natural language prompts.
Local Implicit Ray Function for Generalizable Radiance Field Representation
To solve this problem, we propose LIRF to aggregate the information from conical frustums to construct a ray.
NeAI: A Pre-convoluted Representation for Plug-and-Play Neural Ambient Illumination
Recent advances in implicit neural representation have demonstrated the ability to recover detailed geometry and material from multi-view images.
3D Video Loops from Asynchronous Input
Looping videos are short video clips that can be looped endlessly without visible seams or artifacts.
TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection
Multimodal hate detection, which aims to identify harmful content online such as memes, is crucial for building a wholesome internet environment.
CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network
Finally, we propose a sign-based gradient surgery to promote the training of CO-Net, thereby emphasizing the usage of task-shared parameters and guaranteeing that each task can be thoroughly optimized.
3D GAN Inversion with Facial Symmetry Prior
It is natural to associate 3D GANs with GAN inversion methods to project a real image into the generator's latent space, allowing free-view consistent synthesis and editing, referred as 3D GAN inversion.
A Benchmark of Video-Based Clothes-Changing Person Re-Identification
In this paper, we focus on the relatively new yet practical problem of clothes-changing video-based person re-identification (CCVReID), which is less studied.
Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars
We propose a novel 3D GAN framework for unsupervised learning of generative, high-quality and 3D-consistent facial avatars from unstructured 2D images.
CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion
As such, we propose a novel camera-LiDAR fusion 3D MOT framework based on the Combined Appearance-Motion Optimization (CAMO-MOT), which uses both camera and LiDAR data and significantly reduces tracking failures caused by occlusion and false detection.
FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing
Unlike existing dynamic NeRFs that require dense images as input and can only be modeled for a single identity, our method enables face reconstruction across different persons with few-shot inputs.
Formal guarantees for heuristic optimization algorithms used in machine learning
We show that their last iterate has optimal convergence for unconstrained convex stochastic optimization problems.
Neural Parameterization for Dynamic Human Head Editing
Implicit radiance functions emerged as a powerful scene representation for reconstructing and rendering photo-realistic views of a 3D scene.
UV Volumes for Real-time Rendering of Editable Free-view Human Performance
Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications.
Hallucinated Neural Radiance Fields in the Wild
This paper studies the problem of hallucinated NeRF: i. e., recovering a realistic NeRF at a different time of day from a group of tourism images.
FENeRF: Face Editing in Neural Radiance Fields
2D GANs can generate high fidelity portraits but with low view consistency.
Deblur-NeRF: Neural Radiance Fields from Blurry Images
We demonstrate that our method can be used on both camera motion blur and defocus blur: the two most common types of blur in real scenes.
Let's See Clearly: Contaminant Artifact Removal for Moving Cameras
This new dataset and our novel framework lead to our method that is able to address different contaminants and outperforms competitive restoration approaches both qualitatively and quantitatively.
Measurement of the absolute branching fractions for purely leptonic $D_s^+$ decays
Constraining our measurement to the Standard Model expectation of lepton universality ($R=9. 75$), we find the more precise results $\cal B(D_s^+\to \tau^+\nu_\tau) = (5. 22\pm0. 10\pm 0. 14)\times10^{-2}$ and $A_{\it CP}(\tau^\pm\nu_\tau) = (-0. 1\pm1. 9\pm1. 0)\%$.
High Energy Physics - Experiment
On the Last Iterate Convergence of Momentum Methods
In this paper, we focus on the convergence rate of the last iterate of SGDM.
Measurements of the center-of-mass energies of $e^{+}e^{-}$ collisions at BESIII
During the 2016-17 and 2018-19 running periods, the BESIII experiment collected 7. 5~fb$^{-1}$ of $e^+e^-$ collision data at center-of-mass energies ranging from 4. 13 to 4. 44 GeV.
High Energy Physics - Experiment
Deep Sketch-guided Cartoon Video Inbetweening
The key idea of the proposed approach is to estimate the dense cross-domain correspondence between the sketch and cartoon video frames, and employ a blending module with occlusion estimation to synthesize the middle frame guided by the sketch.
A High Probability Analysis of Adaptive SGD with Momentum
We use it to prove for the first time the convergence of the gradients to zero in high probability in the smooth nonconvex setting for Delayed AdaGrad with momentum.
A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
Moreover, we show the surprising property that these two strategies are \emph{adaptive} to the noise level in the stochastic gradients of PL functions.
Document Rectification and Illumination Correction using a Patch-based CNN
We propose a novel learning method to rectify document images with various distortion types from a single input image.
Blind Geometric Distortion Correction on Images Through Deep Learning
We propose the first general framework to automatically correct different types of geometric distortion in a single input image.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Using Clinical Narratives and Structured Data to Identify Distant Recurrences in Breast Cancer
Our model can accurately and efficiently identify distant recurrences in breast cancer by combining features extracted from unstructured clinical narratives and structured clinical data.
Natural Language Processing for EHR-Based Computational Phenotyping
This article reviews recent advances in applying natural language processing (NLP) to Electronic Health Records (EHRs) for computational phenotyping.
On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes
In this paper, we start closing this gap: we theoretically analyze in the convex and non-convex settings a generalized version of the AdaGrad stepsizes.
Quantum Laplacian Eigenmap
While classical Laplacian eigenmap algorithm requires polynomial time to solve the eigenvector problem, our algorithm is able to exponentially speed up nonlinear dimensionality reduction.
Machine Learned Resume-Job Matching Solution
In our solution, rather than using manual rules, machine learned methods to automatically detect the semantic similarity of positions are proposed.
An Empirical Study on Sentiment Classification of Chinese Review using Word Embedding
In this article, how word embeddings can be used as features in Chinese sentiment classification is presented.
