Search Results for author:
Found 393 papers, 197 papers with code
Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded Manifolds
Based on our investigation, we further present a new robust learning algorithm which encourages a larger gradient component in the tangent space of data manifold, suppressing the gradient leaking phenomenon consequently.
Understanding and Stabilizing GANs' Training Dynamics Using Control Theory
There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.
Variance Reduction and Quasi-Newton for Particle-Based Variational Inference
Particle-based Variational Inference methods (ParVIs), like Stein Variational Gradient Descent, are nonparametric variational inference methods that optimize a set of particles to best approximate a target distribution.
D2AF: A Dual-Driven Annotation and Filtering Framework for Visual Grounding
This approach overcomes dataset size limitations and enriches both the quantity and diversity of referring expressions.
SageAttention2++: A More Efficient Implementation of SageAttention2
To further accelerate SageAttention2, we propose to utilize the faster instruction of FP8 Matmul accumulated in FP16.
Scaling Diffusion Transformers Efficiently via $μ$P
Finally, we validate the effectiveness of $\mu$P on text-to-image generation by scaling PixArt-$\alpha$ from 0. 04B to 0. 61B and MMDiT from 0. 18B to 18B.
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
Second, we pioneer low-bit attention to training tasks.
Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization
With the ability of 4D and video generation, Video4DGen offers a powerful tool for applications in virtual reality, animation, and beyond.
DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
Triangle meshes play a crucial role in 3D applications for efficient manipulation and rendering.
DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap
Recent works in cross-modal understanding and generation, notably through models like CLAP (Contrastive Language-Audio Pretraining) and CAVP (Contrastive Audio-Visual Pretraining), have significantly enhanced the alignment of text, video, and audio embeddings via a single contrastive loss.
Accurate INT8 Training Through Dynamic Block-Level Fallback
Transformer models have achieved remarkable success across various AI applications but face significant training costs.
UAR-NVC: A Unified AutoRegressive Framework for Memory-Efficient Neural Video Compression
Inspired by the success of traditional video compression frameworks, which process video frame by frame and can efficiently compress long videos, we adopt this modeling strategy for INRs to decrease memory consumption, while aiming to unify the frameworks from the perspective of timeline-based autoregressive modeling.
Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective, which minimizes the forward KL divergence, inherently suffers from a mode-covering tendency that limits the generation quality under limited model capacity.
Ranked #1 on
Image Generation
on ImageNet 512x512
Oscillation-Reduced MXFP4 Training for Vision Transformers
However, training with MXFP4 data format still results in significant degradation and there is a lack of systematic research on the reason.
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
A universal sparse attention that guarantees both the speedup and end-to-end performance of diverse models remains elusive.
RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
Recent advancements in video generation have enabled models to synthesize high-quality, minute-long videos.
Self-Consistent Model-based Adaptation for Visual Reinforcement Learning
We further present a practical algorithm to optimize the objective by estimating the distribution of clean observations with a pre-trained world model.
Exploratory Diffusion Model for Unsupervised Reinforcement Learning
Specifically, ExDM can accurately estimate the distribution of collected data in the replay buffer with the diffusion model and introduces the score-based intrinsic reward, encouraging the agent to explore less-visited states.
CANeRV: Content Adaptive Neural Representation for Video Compression
Furthermore, to enhance the capture of dynamics between frames within a sequence, we implement a dynamic frame-level adjustment (DFA).
Effective Black-Box Multi-Faceted Attacks Breach Vision Large Language Model Guardrails
It comprises three complementary attack facets: Visual Attack that exploits the multimodal nature of VLLMs to inject toxic system prompts through images; Alignment Breaking Attack that manipulates the model's alignment mechanism to prioritize the generation of contrasting responses; and Adversarial Signature that deceives content moderators by strategically placing misleading information at the end of the response.
A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees
We consider the problem of finding an $\epsilon$-stationary point of a nonconvex function with a Lipschitz continuous Hessian and propose a quadratic regularized Newton method incorporating a new class of regularizers constructed from the current and previous gradients.
Elucidating the Preconditioning in Consistency Distillation
Consistency distillation is a prevalent way for accelerating diffusion models adopted in consistency (trajectory) models, in which a student model is trained to traverse backward on the probability flow (PF) ordinary differential equation (ODE) trajectory determined by the teacher model.
STAIR: Improving Safety Alignment with Introspective Reasoning
Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications.
Towards the Worst-case Robustness of Large Language Models
We propose a general tight lower bound for randomized smoothing using fractional knapsack solvers or 0-1 knapsack solvers, and using them to bound the worst-case robustness of all stochastic defenses.
Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models
To eradicate this security risk, we also propose defense methods against such attacks, which can correct the bias of text embeddings and improve downstream performance in a train-free manner.
Visual Generation Without Guidance
It retains the same maximum likelihood objective as CFG and differs mainly in the parameterization of conditional models.
Robust Representation Consistency Model via Contrastive Denoising
For example, our method outperforms the certified accuracy of diffusion-based methods on ImageNet across all perturbation radii by 5. 3% on average, with up to 11. 6% at larger radii, while reducing inference costs by 85$\times$ on average.
Improving Accuracy and Calibration via Differentiated Deep Mutual Learning
Deep Neural Networks (DNNs) have achieved remarkable success in a variety of tasks, particularly in terms of prediction accuracy.
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
Sparsely activated Mixture-of-Experts (MoE) models are widely adopted to scale up model capacity without increasing the computation budget.
Fairness without Demographics through Learning Graph of Gradients
In this paper, we show that the correlation between gradients and groups can help identify and improve group fairness.
Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models
Datasets collected from the open world unavoidably suffer from various forms of randomness or noiseness, leading to the ubiquity of aleatoric (data) uncertainty.
Scaling Laws for Black box Adversarial Attacks
However, since prior studies usually adopt few models in the ensemble, there remains an open question of whether scaling the number of models can further improve black-box attacks.
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
Second, we propose a method to smooth $Q$, enhancing the accuracy of INT4 $QK^\top$.
LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models
This work explores expanding the capabilities of large language models (LLMs) pretrained on text to generate 3D meshes within a unified model.
MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
Previous works mainly focus on jailbreak in single-round dialogue, overlooking the potential jailbreak risks in multi-round dialogues, which are a vital way humans interact with and extract information from LLMs.
ManiBox: Enhancing Spatial Grasping Generalization via Scalable Simulation Data Generation
To overcome these challenges, we then focus on state-based policy generalization and present \textbf{ManiBox}, a novel bounding-box-guided manipulation method built on a simulation-based teacher-student framework.
Localization, balance and affinity: a stronger multifaceted collaborative salient object detector in remote sensing images
Despite significant advancements in salient object detection(SOD) in optical remote sensing images(ORSI), challenges persist due to the intricate edge structures of ORSIs and the complexity of their contextual relationships.
Consistency Diffusion Bridge Models
Recently, diffusion denoising bridge models (DDBMs), a new formulation of generative modeling that builds stochastic processes between fixed data endpoints based on a reference diffusion process, have achieved empirical success across tasks with coupled data distribution, such as image-to-image translation.
FrameBridge: Improving Image-to-Video Generation with Bridge Models
By formulating I2V synthesis as a frames-to-frames generation task and modelling it with a data-to-data process, we fully exploit the information in input image and facilitate the generative model to learn the image animation process.
Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
Motivated by language model alignment methods, we propose \textit{Condition Contrastive Alignment} (CCA) to facilitate guidance-free AR visual generation with high performance and analyze its theoretical connection with guided sampling methods.
RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
Bimanual manipulation is essential in robotics, yet developing foundation models is extremely challenging due to the inherent complexity of coordinating two robot arms (leading to multi-modal action distributions) and the scarcity of training data.
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
We also show that Adam behaves similarly to SignGD in terms of both optimization and generalization in this setting.
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
Although quantization has proven to be an effective method for accelerating model inference, existing quantization methods primarily focus on optimizing the linear layer.
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training
Training deep neural networks (DNNs) is costly.
Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
Masked diffusion models (MDMs) have emerged as a popular research topic for generative modeling of discrete data, thanks to their superior performance over other discrete diffusion models, and are rivaling the auto-regressive models (ARMs) for language modeling tasks.
MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization
Meshes are the de facto 3D representation in the industry but are labor-intensive to produce.
Pruning Large Language Models with Semi-Structural Adaptive Sparse Training
However, these methods often suffer from considerable performance degradation on complex language understanding tasks, raising concerns about the feasibility of pruning in LLMs.
Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning these policies to align with task-specific annotations like Q-values.
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
The recent development of Sora leads to a new era in text-to-video (T2V) generation.
HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning
The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting.
Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model
We attribute this to the issue called conditional image leakage, where the image-to-video diffusion models (I2V-DMs) tend to over-rely on the conditional image at large time steps.
MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges.
Freeplane: Unlocking Free Lunch in Triplane-Based Sparse-View Reconstruction Models
We first analyze the role of triplanes in feed-forward methods and find that the inconsistent multi-view images introduce high-frequency artifacts on triplanes, leading to low-quality 3D meshes.
Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
In this paper, we propose to investigate the task from a new perspective of the frequency domain.
Accurate and Reliable Predictions with Mutual-Transport Ensemble
Deep Neural Networks (DNNs) have achieved remarkable success in a variety of tasks, especially when it comes to prediction accuracy.
Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
In this paper, we propose a Prior-guided Bayesian Optimization (P-BO) algorithm that leverages the surrogate model as a global function prior in black-box adversarial attacks.
Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
Vidu4D also contains a novel initialization state that provides a proper start for the warping fields in DGS.
PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance
Generating compact and sharply detailed 3D meshes poses a significant challenge for current 3D generative models.
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
First, under a certain condition of data distribution, we prove that an autoregressively trained transformer learns $W$ by implementing one step of gradient descent to minimize an ordinary least squares (OLS) problem in-context.
PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
Designing generalizable agents capable of adapting to diverse embodiments has achieved significant attention in Reinforcement Learning (RL), which is critical for deploying RL agents in various real-world applications.
Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models
We introduce Vidu, a high-performance text-to-video generator that is capable of producing 1080p videos up to 16 seconds in a single generation.
MicroDreamer: Efficient 3D Generation in $\sim$20 Seconds by Score-based Iterative Reconstruction
Optimization-based approaches, such as score distillation sampling (SDS), show promise in zero-shot 3D generation but suffer from low efficiency, primarily due to the high number of function evaluations (NFEs) required for each sample and the limitation of optimization confined to latent space.
Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition
Specifically, we formulate the video-based PAR as a vision-language fusion problem and adopt a pre-trained foundation model CLIP to extract the visual features.
Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
To achieve this, we propose Transferable Visual Prompting (TVP), a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model.
SparseDM: Toward Sparse Efficient Diffusion Models
Diffusion models represent a powerful family of generative models widely used for image and video generation.
Accelerating Transformer Pre-training with 2:4 Sparsity
Utilizing this metric, we propose three techniques to preserve accuracy: to modify the sparse-refined straight-through estimator by applying the masked decay term on gradients, to determine a feasible decay factor in warm-up stage, and to enhance the model's quality by a dense fine-tuning procedure near the end of pre-training.
FlexiDreamer: Single Image-to-3D Generation with FlexiCubes
However, since directly reconstructing triangle meshes from multi-view images is challenging, most methodologies opt to an implicit representation (such as NeRF) during the sparse-view reconstruction and acquire the target mesh by a post-processing extraction.
Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
The vulnerability of deep neural networks to adversarial patches has motivated numerous defense strategies for boosting model robustness.
DreamReward: Text-to-3D Generation with Human Preference
Building upon the 3D reward model, we finally perform theoretical analysis and present the Reward3D Feedback Learning (DreamFL), a direct tuning algorithm to optimize the multi-view diffusion models with a redefined scorer.
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
Pretraining transformers are generally time-consuming.
CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model
In this work, we present the Convolutional Reconstruction Model (CRM), a high-fidelity feed-forward single image-to-3D generative model.
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
Pre-training has been investigated to improve the efficiency and performance of training neural operators in data-scarce settings.
Efficient Backpropagation with Variance-Controlled Adaptive Sampling
On all the tasks, VCAS can preserve the original training loss trajectory and validation accuracy with an up to 73. 87% FLOPs reduction of BP and 49. 58% FLOPs reduction of the whole training process.
CodeS: Towards Building Open-source Language Models for Text-to-SQL
To address the limitations, we introduce CodeS, a series of pre-trained language models with parameters ranging from 1B to 15B, specifically designed for the text-to-SQL task.
C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory
Generative Adversarial Imitation Learning (GAIL) trains a generative policy to mimic a demonstrator.
BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators
It allows users to design specific prompts to generate realistic images through some black-box APIs.
Noise Contrastive Alignment of Language Models with Explicit Rewards
We evaluate our methods in both reward and preference settings with Mistral-8*7B and 7B models.
Diffusion Models are Certifiably Robust Classifiers
Experimental results show the superior certified robustness of these Noised Diffusion Classifiers (NDCs).
Preconditioning for Physics-Informed Neural Networks
Physics-informed neural networks (PINNs) have shown promise in solving various partial differential equations (PDEs).
Towards Efficient Exact Optimization of Language Model Alignment
This leads to the same mode-seeking solution, while enables efficient optimization by circumventing the complexities of RL.
DualTeacher: Bridging Coexistence of Unlabelled Classes for Semi-supervised Incremental Object Detection
A commonly-used strategy for supervised IOD is to encourage the current model (as a student) to mimic the behavior of the old model (as a teacher), but it generally fails in SSIOD because a dominant number of object instances from old and new classes are coexisting and unlabelled, with the teacher only recognizing a fraction of them.
Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis
Specifically, we leverage the latent representation obtained from text input as our prior, and build a fully tractable Schrodinger bridge between it and the ground-truth mel-spectrogram, leading to a data-to-data process.
Spatiotemporal Transformer for Imputing Sparse Data: A Deep Learning Approach
Effective management of environmental resources and agricultural sustainability heavily depends on accurate soil moisture data.
LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models.
Ranked #1 on
LMM real-life tasks
on Leaderboard
InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
With the success of Neural Radiance Field (NeRF) in 3D-aware portrait editing, a variety of works have achieved promising results regarding both quality and 3D consistency.
Towards a General Framework for Continual Learning with Pre-training
In this work, we present a general framework for continual learning of sequentially arrived tasks with the use of pre-training, which has emerged as a promising direction for artificial intelligence systems to accommodate real-world dynamics.
DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics
In this work, we propose a novel formulation towards the optimal parameterization during sampling that minimizes the first-order discretization error of the ODE solution.
Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting
Despite the significant progress made in practical applications of aligned language models (LMs), they tend to be overconfident in output answers compared to the corresponding pre-trained LMs.
Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation
Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately.
Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
Following these empirical and theoretical insights, we propose Hierarchical Decomposition (HiDe-)Prompt, an innovative approach that explicitly optimizes the hierarchical components with an ensemble of task-specific prompts and statistics of both uninstructed and instructed representations, further with the coordination of a contrastive regularization strategy.
Score Regularized Policy Optimization through Diffusion Behavior
Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling, which excels at representing heterogeneous behavior policies.
How Robust is Google's Bard to Adversarial Image Attacks?
By attacking white-box surrogate vision encoders or MLLMs, the generated adversarial examples can mislead Bard to output wrong image descriptions with a 22% success rate based solely on the transferability.
SeisCLIP: A seismology foundation model pre-trained by multi-modal data for multi-purpose seismic feature extraction
Training specific deep learning models for particular tasks is common across various domains within seismology.
Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence
Continual learning aims to empower artificial intelligence (AI) with strong adaptability to the real world.
Heterogeneous Multi-Task Gaussian Cox Processes
This paper presents a novel extension of multi-task Gaussian Cox processes for modeling multiple heterogeneous correlated tasks jointly, e. g., classification and regression, via multi-output Gaussian processes (MOGP).
6G Network Business Support System
6G is the next-generation intelligent and integrated digital information infrastructure, characterized by ubiquitous interconnection, native intelligence, multi-dimensional perception, global coverage, green and low-carbon, native network security, etc.
Multi-task multi-station earthquake monitoring: An all-in-one seismic Phase picking, Location, and Association Network (PLAN)
Overall, our study provides for the first time a prototype self-consistent all-in-one system of simultaneous seismic phase picking, association, and location, which has the potential for next-generation autonomous earthquake monitoring.
Training Transformers with 4-bit Integers
To achieve this, we carefully analyze the specific structures of activation and gradients in transformers to propose dedicated quantizers for them.
Stabilizing GANs' Training with Brownian Motion Controller
We theoretically prove that the training process of DiracGANs-BMC is globally exponential stable and derive bounds on the rate of convergence.
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
In addition to providing a standardized means of assessing performance, PINNacle also offers an in-depth analysis to guide future research, particularly in areas such as domain decomposition methods and loss reweighting for handling multi-scale problems and complex geometry.
MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural Networks
Physics-informed Neural Networks (PINNs) have recently achieved remarkable progress in solving Partial Differential Equations (PDEs) in various fields by minimizing a weighted sum of PDE loss and boundary loss.
NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data
The neural operator has emerged as a powerful tool in learning mappings between function spaces in PDEs.
Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models
In light of these observations, we evaluate the calibration of several methods that preserve pre-trained features and show that preserving pre-trained features can improve the calibration of fine-tuned language models.
Amplification trojan network: Attack deep neural networks by amplifying their inherent weakness
Recent works found that deep neural networks (DNNs) can be fooled by adversarial examples, which are crafted by adding adversarial noise on clean inputs.
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
This paper presents \emph{ControlVideo} for text-driven video editing -- generating a video that aligns with a given text while preserving the structure of the source video.
ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
In comparison, VSD works well with various CFG weights as ancestral sampling from diffusion models and simultaneously improves the diversity and sample quality with a common CFG weight (i. e., $7. 5$).
Robust Classification via a Single Diffusion Model
As RDC does not require training on particular adversarial attacks, we demonstrate that it is more generalizable to defend against multiple unseen threats.
Ranked #2 on
Adversarial Defense
on CIFAR-10
Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs
The probability flow ordinary differential equation (ODE) of diffusion models (i. e., diffusion ODEs) is a particular case of continuous normalizing flows (CNFs), which enables deterministic inference and exact likelihood evaluation.
Ranked #1 on
Density Estimation
on CIFAR-10
Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning
The main challenge for this setting is that the intermediate guidance during the diffusion sampling procedure, which is jointly defined by the sampling distribution and the energy function, is unknown and is hard to estimate.
Learning CLIP Guided Visual-Text Fusion Transformer for Video-based Pedestrian Attribute Recognition
The averaged visual tokens and text tokens are concatenated and fed into a fusion Transformer for multi-modal interactive learning.
PREIM3D: 3D Consistent Precise Image Attribute Editing from a Single Image
As for imprecise image editing, we attribute the problem to the gap between the latent space of real images and that of generated images.
Detection Transformer with Stable Matching
We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is highlighted by the one-to-one matching design in DETR.
A Closer Look at Parameter-Efficient Tuning in Diffusion Models
Large-scale diffusion models like Stable Diffusion are powerful and find various real-world applications while customizing such models by fine-tuning is both memory and time inefficient.
Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition
The goal of this work is to develop a more reliable technique that can carry out an end-to-end evaluation of adversarial robustness for commercial systems.
Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving
3D object detection is an important task in autonomous driving to perceive the surroundings.
Rethinking Model Ensemble in Transfer-based Adversarial Attacks
It is widely recognized that deep learning models lack robustness to adversarial examples.
One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale
Inspired by the unified view, UniDiffuser learns all distributions simultaneously with a minimal modification to the original diffusion model -- perturbs data in all modalities instead of a single modality, inputs individual timesteps in different modalities, and predicts the noise of all modalities instead of a single modality.
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion.
Ranked #2 on
Zero Shot Segmentation
on Segmentation in the Wild
Task Aware Dreamer for Task Generalization in Reinforcement Learning
Extensive experiments in both image-based and state-based tasks show that TAD can significantly improve the performance of handling different tasks simultaneously, especially for those with high TDR, and display a strong generalization ability to unseen tasks.
Boundary-semantic collaborative guidance network with dual-stream feedback mechanism for salient object detection in optical remote sensing imagery
Finally, to obtain more complete saliency maps, we consider the uniqueness of the last layer of the decoder for the first time and propose the adaptive feedback refinement (AFR) module, which further refines feature representation and eliminates differences between features through a unique feedback mechanism.
Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing
Furthermore, we show that the dual problem can be solved by policy learning, with the optimal dual variable being found efficiently via bisection search (i. e., by taking advantage of the monotonicity).
To Make Yourself Invisible with Adversarial Semantic Contours
In this paper, we propose Adversarial Semantic Contour (ASC), an MAP estimate of a Bayesian formulation of sparse attack with a deceived prior of object contour.
GNOT: A General Neural Operator Transformer for Operator Learning
However, there are several challenges for learning operators in practical applications like the irregular mesh, multiple input functions, and complexity of the PDEs' solution.
A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking
In our benchmark, we evaluate the robustness of 55 typical deep learning models on ImageNet with diverse architectures (e. g., CNNs, Transformers) and learning algorithms (e. g., normal supervised training, pre-training, adversarial training) under numerous adversarial attacks and out-of-distribution (OOD) datasets.
Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels
In an effort to further advance semi-supervised generative and classification tasks, we propose a simple yet effective training strategy called dual pseudo training (DPT), built upon strong semi-supervised learners and diffusion models.
Confidence-based Reliable Learning under Dual Noises
Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization.
Revisiting Discriminative vs. Generative Classifiers: Theory and Implications
Theoretically, the paper considers the surrogate loss instead of the zero-one loss in analyses and generalizes the classical results from binary cases to multiclass ones.
A Comprehensive Survey of Continual Learning: Theory, Method and Application
To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime.
Semiparametric Regression for Spatial Data via Deep Learning
To be specific, we use a sparsely connected deep neural network with rectified linear unit (ReLU) activation function to estimate the unknown regression function that describes the relationship between response and covariates in the presence of spatial dependence.
Benchmarking Robustness of 3D Object Detection to Common Corruptions
3D object detection is an important task in autonomous driving to perceive the surroundings.
Why Are Conditional Generative Models Better Than Unconditional Ones?
Extensive empirical evidence demonstrates that conditional generative models are easier to train and perform better than unconditional ones by exploiting the labels of data.
DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding
As phrase extraction can be regarded as a $1$D text segmentation problem, we formulate PEG as a dual detection problem and propose a novel DQ-DETR model, which introduces dual queries to probe different features from image and text for object prediction and phrase mask prediction.
Ranked #11 on
Referring Expression Comprehension
on RefCOCO
Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications
Recent work shows that it provides potential benefits for machine learning models by incorporating the physical prior and collected data, which makes the intersection of machine learning and physics become a prevailing paradigm.
Improving transferability of 3D adversarial attacks with scale and shear transformations
Extensive experiments show that the SS attack proposed in this paper can be seamlessly combined with the existing state-of-the-art (SOTA) 3D point cloud attack methods to form more powerful attack methods, and the SS attack improves the transferability over 3. 6 times compare to the baseline.
Model-based Reinforcement Learning with a Hamiltonian Canonical ODE Network
Model-based reinforcement learning usually suffers from a high sample complexity in training the world model, especially for the environments with complex dynamics.
Model-based Reinforcement Learning
reinforcement-learning
+2
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
The commonly-used fast sampler for guided sampling is DDIM, a first-order diffusion ODE solver that generally needs 100 to 250 steps for high-quality samples.
Spectral Representation Learning for Conditional Moment Models
For nonparametric conditional moment models, efficient estimation often relies on preimposed conditions on various measures of ill-posedness of the hypothesis space, which are hard to validate when flexible models are used.
Isometric 3D Adversarial Examples in the Physical World
For naturalness, we constrain the adversarial example to be $\epsilon$-isometric to the original one by adopting the Gaussian curvature as a surrogate metric guaranteed by a theoretical analysis.
Accelerated Linearized Laplace Approximation for Bayesian Deep Learning
Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of pretrained deep neural networks to Bayesian neural networks.
Neural Eigenfunctions Are Structured Representation Learners
Unlike prior spectral methods such as Laplacian Eigenmap that operate in a nonparametric manner, Neural Eigenmap leverages NeuralEF to parametrically model eigenfunctions using a neural network.
ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints
Recent studies have demonstrated that visual recognition models lack robustness to distribution shift.
A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs
We present a unified hard-constraint framework for solving geometrically complex PDEs with neural networks, where the most commonly used Dirichlet, Neumann, and Robin boundary conditions (BCs) are considered.
INT: Towards Infinite-frames 3D Detection with An Efficient Framework
By employing INT on CenterPoint, we can get around 7% (Waymo) and 15% (nuScenes) performance boost with only 2~4ms latency overhead, and currently SOTA on the Waymo 3D Detection leaderboard.
Equivariant Energy-Guided SDE for Inverse Molecular Design
Inverse molecular design is critical in material science and drug discovery, where the generated molecules should satisfy certain desirable properties.
Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
To address this problem, we adopt a generative approach by decoupling the learned policy into two parts: an expressive generative behavior model and an action evaluation model.
All are Worth Words: A ViT Backbone for Diffusion Models
We evaluate U-ViT in unconditional and class-conditional image generation, as well as text-to-image generation tasks, where U-ViT is comparable if not superior to a CNN-based U-Net of a similar size.
Ranked #4 on
Text-to-Image Generation
on MS COCO
Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden's Hypergradients
In this paper, we present a novel bi-level optimization framework to resolve the challenge by decoupling the optimization of the targets and constraints.
On the Reuse Bias in Off-Policy Reinforcement Learning
In this paper, we reveal that the instability is also related to a new notion of Reuse Bias of IS -- the bias in off-policy evaluation caused by the reuse of the replay buffer for evaluation and optimization.
Regret Analysis for Hierarchical Experts Bandit Problem
We study an extension of standard bandit problem in which there are R layers of experts.
Robust Learning of Deep Time Series Anomaly Detection Models with Contaminated Training Data
In this work, to tackle this important challenge, we firstly investigate the robustness of commonly used deep TSAD methods with contaminated training data which provides a guideline for applying these methods when the provided training data are not guaranteed to be anomaly-free.
EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations
Further, we provide an alternative explanation of the EGSDE as a product of experts, where each of the three experts (corresponding to the SDE and two feature extractors) solely contributes to faithfulness or realism.
Ranked #1 on
Image-to-Image Translation
on AFHQ (Wild to Dog)
CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One
Continual learning requires incremental compatibility with a sequence of tasks.
DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
We propose Diversity-Guided Policy Optimization (DGPO), an on-policy algorithm that discovers multiple strategies for solving a given task.
Thompson Sampling for (Combinatorial) Pure Exploration
To make the algorithm efficient, they usually use the sum of upper confidence bounds within arm set $S$ to represent the upper confidence bound of $S$, which can be much larger than the tight upper confidence bound of $S$ and leads to a much higher complexity than necessary, since the empirical means of different arms in $S$ are independent.
Fast Lossless Neural Compression with Integer-Only Discrete Flows
In this work, we propose Integer-only Discrete Flows (IODF), an efficient neural compressor with integer-only arithmetic.
Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matching
To fill up this gap, we show that the negative likelihood of the ODE can be bounded by controlling the first, second, and third-order score matching errors; and we further present a novel high-order denoising score matching method to enable maximum likelihood training of score-based diffusion ODEs.
Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models
Thus, the generation performance on a subset of timesteps is crucial, which is greatly influenced by the covariance design in DPMs.
Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty of both transition and observation.
GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing
Under the GSmooth framework, we present a scalable algorithm that uses a surrogate image-to-image network to approximate the complex transformation.
Diagnosing Ensemble Few-Shot Classifiers
The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance.
DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
In this work, we propose an exact formulation of the solution of diffusion ODEs.
BadDet: Backdoor Attacks on Object Detection
We propose four kinds of backdoor attacks for object detection task: 1) Object Generation Attack: a trigger can falsely generate an object of the target class; 2) Regional Misclassification Attack: a trigger can change the prediction of a surrounding object to the target class; 3) Global Misclassification Attack: a single trigger can change the predictions of all objects in an image to the target class; and 4) Object Disappearance Attack: a trigger can make the detector fail to detect the object of the target class.
Censored Quantile Regression Neural Networks for Distribution-Free Survival Analysis
To offer theoretical insight into our algorithm, we show firstly that it can be interpreted as a form of expectation-maximisation, and secondly that it exhibits a desirable `self-correcting' property.
Fast Instrument Learning with Faster Rates
We investigate nonlinear instrumental variable (IV) regression given high-dimensional instruments.
Towards Job-Transition-Tag Graph for a Better Job Title Representation Learning
Works on learning job title representation are mainly based on \textit{Job-Transition Graph}, built from the working history of talents.
Deep Ensemble as a Gaussian Process Approximate Posterior
In this way, we relate DE to Bayesian inference to enjoy reliable Bayesian uncertainty.
NeuralEF: Deconstructing Kernels by Deep Neural Networks
Learning the principal eigenfunctions of an integral operator defined by a kernel and a data distribution is at the core of many machine learning problems.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Prior
However, the existing methods inevitably suffer from low attack success rates or poor query efficiency since it is difficult to estimate the gradient in a high-dimensional input space with limited information.
Policy Learning for Robust Markov Decision Process with a Mismatched Generative Model
Our goal is to identify a near-optimal robust policy for the perturbed testing environment, which introduces additional technical difficulties as we need to simultaneously estimate the training environment uncertainty from samples and find the worst-case perturbation for testing.
Controllable Evaluation and Generation of Physical Adversarial Patch on Face Recognition
It is therefore imperative to develop a framework that can enable a comprehensive evaluation of the vulnerability of face recognition in the physical world.
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results.
Ranked #2 on
Object Detection
on SA-Det-100k
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition
The trade-off between robustness and accuracy has been widely studied in the adversarial literature.
Memory Replay with Data Compression for Continual Learning
In this work, we propose memory replay with data compression (MRDC) to reduce the storage cost of old training samples and thus increase their amount that can be stored in the memory buffer.
DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR.
Ranked #102 on
Object Detection
on COCO minival
Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
In this work, we present a surprising result that both the optimal reverse variance and the corresponding optimal KL divergence of a DPM have analytic forms w. r. t.
BE-STI: Spatial-Temporal Integrated Network for Class-Agnostic Motion Prediction With Bidirectional Enhancement
In this paper, we propose a novel Spatial-Temporal Integrated network with Bidirectional Enhancement, BE-STI, to improve the temporal motion prediction performance by spatial semantic features, which points out an efficient way to combine semantic segmentation and motion prediction.
AutoLoss-GMS: Searching Generalized Margin-Based Softmax Loss Function for Person Re-Identification
In this paper, we propose a novel method, AutoLoss-GMS, to search the better loss function in the space of generalized margin-based softmax loss function for person re-identification automatically.
Improving Next-Application Prediction with Deep Personalized-Attention Neural Network
The second module learns job seeker representations.
AFEC: Active Forgetting of Negative Transfer in Continual Learning
Without accessing to the old training samples, knowledge transfer from the old tasks to each new task is difficult to determine, which might be either positive or negative.
Unrestricted Adversarial Attacks on ImageNet Competition
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
Adversarial Attacks on ML Defense Models Competition
Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years.
Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness
The vulnerability of deep neural networks to adversarial examples has motivated an increasing number of defense strategies for promoting model robustness.
TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations
To the best of our knowledge, Tikick is the first learning-based AI system that can take over the multi-agent Google Research Football full game, while previous work could either control a single agent or experiment on toy academic scenarios.
Ranking Cost: Building An Efficient and Scalable Circuit Routing Planner with Evolution-Based Optimization
In this work, we propose a new algorithm for circuit routing, named Ranking Cost, which innovatively combines search-based methods (i. e., A* algorithm) and learning-based methods (i. e., Evolution Strategies) to form an efficient and trainable router.
Adversarial Semantic Contour for Object Detection
To address this issue, we propose a novel method of Adversarial Semantic Contour (ASC) guided by object contour as prior.
Regularized-OFU: an efficient algorithm for general contextual bandit with optimization oracles
In contextual bandit, one major challenge is to develop theoretically solid and empirically efficient algorithms for general function classes.
Deep Ensemble as a Gaussian Process Posterior
Deep Ensemble (DE) is a flexible, feasible, and effective alternative to Bayesian neural networks (BNNs) for uncertainty estimation in deep learning.
Cluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent Priors
In this work, we propose Cluster Attack -- a Graph Injection Attack (GIA) on node classification, which injects fake nodes into the original graph to degenerate the performance of graph neural networks (GNNs) on certain victim nodes while affecting the other nodes as little as possible.
Tianshou: a Highly Modularized Deep Reinforcement Learning Library
In this paper, we present Tianshou, a highly modularized Python library for deep reinforcement learning (DRL) that uses PyTorch as its backend.
Query2Label: A Simple Transformer Way to Multi-Label Classification
The use of Transformer is rooted in the need of extracting local discriminative features adaptively for different labels, which is a strongly desired property due to the existence of multiple objects in one image.
Ranked #1 on
Multi-Label Classification
on PASCAL VOC 2012
On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms
Finally, our theoretical results are confirmed by experiments on several numerical benchmarks as well as adversarial attacks.
Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks
Transfer-based adversarial attacks can evaluate model robustness in the black-box setting.
Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning
In this paper, we provide a framework to better understand the existing methods by reformulating the problem of adversarial attacks on reinforcement learning in the function space.
Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit
However, it is in general unknown how to deriveefficient and effective EE trade-off methods for non-linearcomplex tasks, suchas contextual bandit with deep neural network as the reward function.
Improving Transferability of Adversarial Patches on Face Recognition with Generative Models
However, deep CNNs are vulnerable to adversarial patches, which are physically realizable and stealthy, raising new security concerns on the real-world applications of these models.
PVGNet: A Bottom-Up One-Stage 3D Object Detector With Integrated Multi-Level Features
Quantization-based methods are widely used in LiDAR points 3D object detection for its efficiency in extracting context information.
Accumulative Poisoning Attacks on Real-time Data
Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy.
Strategically-timed State-Observation Attacks on Deep Reinforcement Learning Agents
Deep reinforcement learning (DRL) policies are vulnerable to the adversarial attack on their observations, which may mislead real-world RL agents to catastrophic failures.
