Search Results for author:
Found 68 papers, 20 papers with code
HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration
Single-image human reconstruction is vital for digital human modeling applications but remains an extremely challenging task.
WonderTurbo: Generating Interactive 3D World in 0.72 Seconds
Interactive 3D generation is gaining momentum and capturing extensive attention for its potential to create immersive virtual experiences.
HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
To address this, we propose HumanDreamer, a decoupled human video generation framework that first generates diverse poses from text prompts and then leverages these poses to generate human-motion videos.
ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation
Specifically, on Waymo, ReconDreamer++ achieves performance comparable to Street Gaussians for the original trajectory while significantly outperforming ReconDreamer on novel trajectories.
Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection
Although sparse-point methods lower computational load and maintain high accuracy in complex lane geometries, current methods fail to fully leverage the geometric structure of lanes in both lane geometry representations and model design.
Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-Agent
Debt collection negotiations (DCN) are vital for managing non-performing loans (NPLs) and reducing creditor losses.
Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models
Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become essential for tasks such as question answering and content generation.
Do Large Language Models Truly Understand Geometric Structures?
Geometric ability is a significant challenge for large language models (LLMs) due to the need for advanced spatial comprehension and abstract thinking.
RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
To address those problems, we propose a novel black-box "knowledge watermark" approach, named RAG-WM, to detect IP infringement of RAGs.
OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation
Within OccScene, the perception module can be effectively improved with customized and diverse generated scenes, while the perception priors in return enhance the generation performance for mutual benefits.
Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction
Camera-based 3D Semantic Occupancy Prediction (SOP) is crucial for understanding complex 3D scenes from limited 2D image observations.
3D Semantic Occupancy Prediction
LIDAR Semantic Segmentation
+2
Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation
The rise of deep learning models in the digital era has raised substantial concerns regarding the generation of Not-Safe-for-Work (NSFW) content.
ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
This is complemented by a progressive data update strategy designed to ensure high-quality rendering for more complex maneuvers.
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising.
EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation
Video generation has emerged as a promising tool for world simulation, leveraging visual data to replicate real-world environments.
Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
Aligning language models (LMs) with human preferences has become a key area of research, enabling these models to meet diverse user needs better.
DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on conditions closely aligned with training data distributions, which are largely confined to forward-driving scenarios.
Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models
Extensive experiments on a range of LLMs, PEFTs, and downstream tasks substantiate the effectiveness of our proposed method, showcasing IST's capacity to enhance existing layer-based PEFT methods.
Revising the Problem of Partial Labels from the Perspective of CNNs' Robustness
These remarkable achievements are greatly attributed to the support of extensive datasets with precise labels.
OPa-Ma: Text Guided Mamba for 360-degree Image Out-painting
In this paper, we tackle the recently popular topic of generating 360-degree images given the conventional narrow field of view (NFoV) images that could be taken from a single camera or cellphone.
Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond
General world models represent a crucial pathway toward achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual environments to decision-making systems.
Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering
In customer service technical support, swiftly and accurately retrieving relevant past issues is critical for efficiently resolving customer inquiries.
DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation
DriveDreamer-2 is the first world model to generate customized driving videos, it can generate uncommon driving videos (e. g., vehicles abruptly cut in) in a user-friendly manner.
DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
DPAdapter modifies and enhances the sharpness-aware minimization (SAM) technique, utilizing a two-batch strategy to provide a more accurate perturbation estimate and an efficient gradient descent, thereby improving parameter robustness against noise.
WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens
World models play a crucial role in understanding and predicting the dynamics of the world, which is essential for video generation.
Malla: Demystifying Real-world Large Language Model Integrated Malicious Services
The underground exploitation of large language models (LLMs) for malicious services (i. e., Malla) is witnessing an uptick, amplifying the cyber threat landscape and posing questions about the trustworthiness of LLM technologies.
Nighttime Person Re-Identification via Collaborative Enhancement Network with Multi-domain Learning
Prevalent nighttime person re-identification (ReID) methods typically combine image relighting and ReID networks in a sequential manner.
On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving
This has been a significant bottleneck, particularly in the development of common sense reasoning and nuanced scene understanding necessary for safe and reliable autonomous driving.
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
In our research, we propose a novel attack, Janus, which exploits the fine-tuning interface to recover forgotten PIIs from the pre-training data in LLMs.
Large Language Model Soft Ideologization via AI-Self-Consciousness
Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks.
Reliable Majority Vote Computation with Complementary Sequences for UAV Waypoint Flight Control
In this study, we propose a non-coherent over-the-air computation scheme to calculate the majority vote (MV) reliably in fading channels.
DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving
The established world model holds immense potential for the generation of high-quality driving videos, and driving policies for safe maneuvering.
CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification
Using the aggregated similarity scores as the initial pseudo labels at the training stage, we propose an optimization framework to train the parameters of the classification network and refine pseudo labels for unobserved labels.
Towards Imbalanced Large Scale Multi-label Classification with Partially Annotated Labels
In this work, we address the issue of label imbalance and investigate how to train classifiers using partial labels in large labeling spaces.
Prompt Injection attack against LLM-integrated Applications
We deploy HouYi on 36 actual LLM-integrated applications and discern 31 applications susceptible to prompt injection.
MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion
As a prominent instance of vandalism edits, Wiki search poisoning for illicit promotion is a cybercrime in which the adversary aims at editing Wiki articles to promote illicit businesses through Wiki search results of relevant queries.
D-Score: A White-Box Diagnosis Score for CNNs Based on Mutation Operators
However, concerns have been raised with respect to the trustworthiness of these models: The standard testing method evaluates the performance of a model on a test set, while low-quality and insufficient test sets can lead to unreliable evaluation results, which can have unforeseeable consequences.
Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion
However, due to the inherent representation gap between stereo geometry and BEV features, it is non-trivial to bridge them for dense prediction task of SSC.
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
Using a pre-trained SSL image encoder and subsequently training a downstream classifier, impressive performance can be achieved on various tasks with very little labeled data.
OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception
Towards a comprehensive benchmarking of surrounding perception algorithms, we propose OpenOccupancy, which is the first surrounding semantic occupancy perception benchmark.
CSDR-BERT: a pre-trained scientific dataset match model for Chinese Scientific Dataset Retrieval
As the number of open and shared scientific datasets on the Internet increases under the open science movement, efficiently retrieving these datasets is a crucial task in information retrieval (IR) research.
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
Finally, we perform both theoretical and experimental analysis, showing that the GRASP enhancement does not reduce the effectiveness of the stealthy attacks against the backdoor detection methods based on weight analysis, as well as other backdoor mitigation methods without using detection.
FE-TCM: Filter-Enhanced Transformer Click Model for Web Search
In this paper, We use Transformer as the backbone network of feature extraction, add filter layer innovatively, and propose a new Filter-Enhanced Transformer Click Model (FE-TCM) for web search.
Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark
To mitigate the problem, we propose the Autonomous-driving StreAming Perception (ASAP) benchmark, which is the first benchmark to evaluate the online performance of vision-centric perception in autonomous driving.
Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
Our idea is to retrain a given DNN model on randomly labeled clean data, to induce a CF on the model, leading to a sudden forget on both primary and backdoor tasks; then we recover the primary task by retraining the randomized model on correctly labeled clean data.
Depth Monocular Estimation with Attention-based Encoder-Decoder Network from Single Image
Depth information is the foundation of perception, essential for autonomous driving, robotics, and other source-constrained applications.
An Effective Approach for Multi-label Classification with Missing Labels
Through comprehensive experiments on three large-scale multi-label image datasets, i. e. MS-COCO, NUS-WIDE, and Pascal VOC12, we show that our method can handle the imbalance between positive labels and negative labels, while still outperforming existing missing-label learning approaches in most cases, and in some cases even approaches with fully labeled datasets.
G2NetPL: Generic Game-Theoretic Network for Partial-Label Image Classification
To effectively address partial-label classification, this paper proposes an end-to-end Generic Game-theoretic Network (G2NetPL) for partial-label learning, which can be applied to most partial-label settings, including a very challenging, but annotation-efficient case where only a subset of the training images are labeled, each with only one positive label, while the rest of the training images remain unlabeled.
Understanding Impacts of Task Similarity on Backdoor Attack and Detection
With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect.
Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models
In this study, we propose an imitation adversarial attack on black-box neural passage ranking models.
Scenario-Adaptive and Self-Supervised Model for Multi-Scenario Personalized Recommendation
we summarize three practical challenges which are not well solved for multi-scenario modeling: (1) Lacking of fine-grained and decoupled information transfer controls among multiple scenarios.
PLMCL: Partial-Label Momentum Curriculum Learning for Multi-Label Image Classification
A special case is to annotate only one positive label in each training image.
Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning
In contrast, multi-frame depth estimation methods improve the depth accuracy thanks to the success of Multi-View Stereo (MVS), which directly makes use of geometric constraints.
MVSTER: Epipolar Transformer for Efficient Multi-View Stereo
Therefore, we present MVSTER, which leverages the proposed epipolar Transformer to learn both 2D semantics and 3D spatial associations efficiently.
PLGAN: Generative Adversarial Networks for Power-Line Segmentation in Aerial Images
Accurate segmentation of power lines in various aerial images is very important for UAV flight safety.
New Benchmark for Household Garbage Image Recognition
Household garbage images are usually faced with complex backgrounds, variable illuminations, diverse angles, and changeable shapes, which bring a great difficulty in garbage image classification.
Domain-Invariant Proposals based on a Balanced Domain Classifier for Object Detection
We embed a domain classification network in the region proposal network~(RPN) using adversarial learning.
Context-aware Heterogeneous Graph Attention Network for User Behavior Prediction in Local Consumer Service Platform
Hence, in this paper, we propose a context-aware heterogeneous graph attention network (CHGAT) to dynamically generate the representation of the user and to estimate the probability for future behavior.
SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems
In this paper, we present our systematization of knowledge for ASR security and provide a comprehensive taxonomy for existing work based on a modularized workflow.
The effect of aspherical stellar wind of giant stars on the symbiotic channel of type Ia supernovae
The progenitor systems accounting for explosions of type Ia supernovae (SNe Ia) is still under debate.
Solar and Stellar Astrophysics
HyMap: eliciting hypotheses in early-stage software startups using cognitive mapping
Regarding the first, it provides a better understanding of the guidance founders use to develop their startups and, for the latter, a technique to identify hypotheses in early-stage software startups.
Computers and Society
SN 2017hpa: A Nearby Carbon-Rich Type Ia Supernova with a Large Velocity Gradient
We present extensive, well-sampled optical and ultraviolet photometry and optical spectra of the Type Ia supernova (SN Ia) 2017hpa.
High Energy Astrophysical Phenomena Solar and Stellar Astrophysics
Towards Dark Jargon Interpretation in Underground Forums
Dark jargons are benign-looking words that have hidden, sinister meanings and are used by participants of underground forums for illicit behavior.
TTPLA: An Aerial-Image Dataset for Detection and Segmentation of Transmission Towers and Power Lines
Accurate detection and segmentation of transmission towers~(TTs) and power lines~(PLs) from aerial images plays a key role in protecting power-grid security and low-altitude UAV safety.
Empirical Standards for Software Engineering Research
Empirical Standards are natural-language models of a scientific community's expectations for a specific kind of study (e. g. a questionnaire survey).
Software Engineering General Literature
Drug–target affinity prediction using graph neural network and contact maps
Computer-aided drug design uses high-performance computers to simulate the tasks in drug design, which is a promising research area.
Ranked #3 on
Drug Discovery
on LIT-PCBA(ESR1_ant)
Query-Free Attacks on Industry-Grade Face Recognition Systems under Resource Constraints
To launch black-box attacks against a Deep Neural Network (DNN) based Face Recognition (FR) system, one needs to build \textit{substitute} models to simulate the target model, so the adversarial examples discovered from substitute models could also mislead the target model.
