Search Results for author:
Found 83 papers, 30 papers with code
DD-TIG at Constraint@ACL2022: Multimodal Understanding and Reasoning for Role Labeling of Entities in Hateful Memes
The memes serve as an important tool in online communication, whereas some hateful memes endanger cyberspace by attacking certain people or subjects.
Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations
The emotion cause is a stimulus for human emotions.
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Our results demonstrate more precise camera control than prior work, as well as state-of-the-art results in sparse-view novel view synthesis, even in challenging settings such as driving scenes and monocular dynamic video.
Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
At the core of our approach is Difix, a single-step image diffusion model trained to enhance and remove artifacts in rendered novel views caused by underconstrained regions of the 3D representation.
DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
Classic physically-based rendering (PBR) accurately simulates the light transport, but relies on precise scene representations--explicit 3D geometry, high-quality material properties, and lighting conditions--that are often impractical to obtain in real-world scenarios.
InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models
We present InfiniCube, a scalable method for generating unbounded dynamic 3D driving scenes with high fidelity and controllability.
Interleaved-Modal Chain-of-Thought
Chain-of-Thought (CoT) prompting elicits large language models (LLMs) to produce a series of intermediate reasoning steps before arriving at the final answer.
HelloMeme: Integrating Spatial Knitting Attentions to Embed High-Level and Fidelity-Rich Conditions in Diffusion Models
We propose an effective method for inserting adapters into text-to-image foundation models, which enables the execution of complex downstream tasks while preserving the generalization ability of the base model.
BSG4Bot: Efficient Bot Detection based on Biased Heterogeneous Subgraphs
Motivated by these limitations, this paper proposes a method named BSG4Bot with an intuition that GNNs training on Biased SubGraphs can improve both performance and time/space efficiency in bot detection.
SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes
In particular, our vertex embeddings generate cyclic neighbor relationships in a halfedge mesh representation, which gives a guarantee of edge-manifoldness and the ability to represent general polygonal meshes.
Winning Solution For Meta KDD Cup' 24
The challenge is to build a RAG system from web sources and knowledge graphs.
DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training
Unfortunately, this denoising training method cannot be directly applied to text spotting tasks, as these tasks need to perform irregular shape detection tasks and more complex text recognition tasks than classification.
AIM: Let Any Multi-modal Large Language Models Embrace Efficient In-Context Learning
In-context learning (ICL) facilitates Large Language Models (LLMs) exhibiting emergent ability on downstream tasks without updating billions of parameters.
Guiding ChatGPT to Generate Salient Domain Summaries
Then, we require ChatGPT to generate $k$ candidate summaries for the inference document at a time under the guidance of the retrieved demonstration.
Unifying Demonstration Selection and Compression for In-Context Learning
In this paper, we propose an ICL framework UniICL, which Unifies demonstration selection and compression, and final response generation via a single frozen LLM.
SelfCP: Compressing Over-Limit Prompt via the Frozen Large Language Model Itself
This paper proposes a Self-Compressor (SelfCP), which employs the target LLM itself to compress over-limit prompts into dense vectors while keeping the allowed prompts unmodified.
APrompt4EM: Augmented Prompt Tuning for Generalized Entity Matching
The first is an augmented contextualized soft token-based prompt tuning method that extracts a guiding soft token benefit for the PLMs' prompt tuning, and the second is a cost-effective information augmentation strategy leveraging large language models (LLMs).
LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis
Recent text-to-3D generation approaches produce impressive 3D results but require time-consuming optimization that can take up to an hour per prompt.
DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation
Constrained decoding approaches aim to control the meaning or style of text generated by a Pre-trained Language Model (PLM) using specific target words during inference.
WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations
Enhancing the attribution in large language models (LLMs) is a crucial task.
TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation
This study presents a novel multimodal medical image zero-shot segmentation algorithm named the text-visual-prompt segment anything model (TV-SAM) without any manual annotations.
EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models
In this study, we present EventRL, a reinforcement learning approach developed to enhance event extraction for large language models (LLMs).
Towards Versatile Graph Learning Approach: from the Perspective of Large Language Models
This paper proposes a novel conceptual prototype for designing versatile graph learning methods with LLMs, with a particular focus on the "where" and "how" perspectives.
WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space
Then, we train a diffusion model in the 3D-aware latent space, thereby enabling synthesis of high-quality 3D-consistent image samples, outperforming recent state-of-the-art GAN-based methods.
Zero-Shot Digital Rock Image Segmentation with a Fine-Tuned Segment Anything Model
Despite its advanced features, SAM struggles with rock CT/SEM images due to their absence in its training set and the low-contrast nature of grayscale images.
Adaptive Shells for Efficient Neural Radiance Field Rendering
We then extract an explicit mesh of a narrow band around the surface, with width determined by the kernel size, and fine-tune the radiance field within this band.
Enhancing Rock Image Segmentation in Digital Rock Physics: A Fusion of Generative AI and State-of-the-Art Neural Networks
In digital rock physics, analysing microstructures from CT and SEM scans is crucial for estimating properties like porosity and pore connectivity.
Benchmarking Large Language Models with Augmented Instructions for Fine-grained Information Extraction
Information Extraction (IE) is an essential task in Natural Language Processing.
Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games
Furthermore, we develop a Gamified Red Team Solver (GRTS) with diversity measures to mitigate mode collapse and theoretically guarantee the convergence of approximate Nash equilibrium which results in better strategies for both teams.
ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models
Personal values are a crucial factor behind human decision-making.
Bayesian-Boosted MetaLoc: Efficient Training and Guaranteed Generalization for Indoor Localization
Existing localization approaches utilizing environment-specific channel state information (CSI) excel under specific environment but struggle to generalize across varied environments.
Flexible Isosurface Extraction for Gradient-Based Mesh Optimization
This work considers gradient-based mesh optimization, where we iteratively optimize for a 3D surface mesh by representing it as the isosurface of a scalar field, an increasingly common paradigm in applications including photogrammetry, generative modeling, and inverse physics.
Deblurring Masked Autoencoder is Better Recipe for Ultrasound Image Recognition
Overall, our work highlights the potential of MAE for ultrasound image recognition and presents a novel approach that incorporates deblurring to further improve its effectiveness.
A Diffusion Model for Event Skeleton Generation
Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs, is a critical step in the temporal complex event schema induction task.
Progressive Learning of 3D Reconstruction Network from 2D GAN Data
In this work, to overcome these limitations of generated datasets, we have two main contributions which lead us to achieve state-of-the-art results on challenging objects: 1) A robust multi-stage learning scheme that gradually relies more on the models own predictions when calculating losses, 2) A novel adversarial learning pipeline with online pseudo-ground truth generations to achieve fine details.
Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion.
Exploring the Feasibility of ChatGPT for Event Extraction
While ChatGPT has demonstrated impressive results in tasks like machine translation, text summarization, and question answering, it presents challenges when used for complex tasks like event extraction.
Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction
We present Mask-then-Fill, a flexible and effective data augmentation framework for event extraction.
Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion.
A Generative Approach for Script Event Prediction via Contrastive Fine-tuning
First, the pretrained language models adopted by current works ignore event-level knowledge, resulting in an inability to capture the correlations between events well.
Magic3D: High-Resolution Text-to-3D Content Creation
DreamFusion has recently demonstrated the utility of a pre-trained text-to-image diffusion model to optimize Neural Radiance Fields (NeRF), achieving remarkable text-to-3D synthesis results.
Ranked #2 on
Text to 3D
on T$^3$Bench
MetaLoc: Learning to Learn Wireless Localization
The framework introduces two paradigms for the optimization of meta-parameters: a centralized paradigm that simplifies the process by sharing data from all historical environments, and a distributed paradigm that maintains data privacy by training meta-parameters for each specific environment separately.
Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset
To the best of our knowledge, it is currently the largest manually-annotated Chinese dataset for open event extraction.
TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack
We present Twin Answer Sentences Attack (TASA), an adversarial attack method for question answering (QA) models that produces fluent and grammatical adversarial contexts while maintaining gold answers.
GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident.
Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention
HILA extends hierarchical vision transformer architectures by adding local connections between features of higher and lower levels to the backbone encoder.
Model Degradation Hinders Deep Graph Neural Networks
Graph Neural Networks (GNNs) have achieved great success in various graph mining tasks. However, drastic performance degradation is always observed when a GNN is stacked with many layers.
Interpretable Proof Generation via Iterative Backward Reasoning
We present IBR, an Iterative Backward Reasoning model to solve the proof generation tasks on rule-based Question Answering (QA), where models are required to reason over a series of textual rules and facts to find out the related proof path and derive the final answer.
Empathetic Response Generation with State Management
The emotion-aware dialogue management contains two parts: (1) Emotion state tracking maintains the current emotion state of the user and (2) Empathetic dialogue policy selection predicts a target emotion and a user's intent based on the results of the emotion state tracking.
Self-Supervised Light Field Depth Estimation Using Epipolar Plane Images
In this paper, we propose a self-supervised learning framework for light field depth estimation.
Fine Detailed Texture Learning for 3D Meshes with Generative Models
The reconstruction is posed as an adaptation problem and is done progressively where in the first stage, we focus on learning accurate geometry, whereas in the second stage, we focus on learning the texture with a generative adversarial network.
Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering
Representations of events described in text are important for various tasks.
Extracting Triangular 3D Models, Materials, and Lighting From Images
We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.
Ranked #2 on
Depth Prediction
on Stanford-ORB
Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis
The core of DMTet includes a deformable tetrahedral grid that encodes a discretized signed distance function and a differentiable marching tetrahedra layer that converts the implicit signed distance representation to the explicit surface mesh representation.
DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer
We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiable renderers.
3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations
Given a small set of high-quality textured objects, our method can create many novel stylized shapes, resulting in effortless 3D content creation and style-ware data augmentation.
Evaluating Deep Graph Neural Networks
Based on the experimental results, we answer the following two essential questions: (1) what actually leads to the compromised performance of deep GNNs; (2) when we need and how to build deep GNNs.
REAM$\sharp$: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation
We first clarify an assumption on reference-based metrics that, if more high-quality references are added into the reference set, the reliability of the metric will increase.
DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
To showcase the power of our approach, we generated datasets for 7 image segmentation tasks which include pixel-level labels for 34 human face parts, and 32 car parts.
Learning Deformable Tetrahedral Meshes for 3D Reconstruction
We introduce Deformable Tetrahedral Meshes (DefTet) as a particular parameterization that utilizes volumetric tetrahedral meshes for the reconstruction problem.
Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Key to our approach is to exploit GANs as a multi-view data generator to train an inverse graphics network using an off-the-shelf differentiable renderer, and the trained inverse graphics network as a teacher to disentangle the GAN's latent code into interpretable 3D properties.
Information Laundering for Model Privacy
In this work, we propose information laundering, a novel framework for enhancing model privacy.
Interactive Annotation of 3D Object Geometry using 2D Scribbles
We implement our framework as a web service and conduct a user study, where we show that user annotated data using our method effectively facilitates real-world learning tasks.
Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
We also utilize DefGrid at the output layers for the task of object mask annotation, and show that reasoning about object boundaries on our predicted polygonal grid leads to more accurate results over existing pixel-wise and curve-based approaches.
Quantum Computation for Pricing the Collateralized Debt Obligations
Collateralized debt obligation (CDO) has been one of the most commonly used structured financial products and is intensively studied in quantitative finance.
EPI-based Oriented Relation Networks for Light Field Depth Estimation
Based on the observation that an oriented line and its neighboring pixels in an EPI share a similar linear structure, we propose an end-to-end fully convolutional network (FCN) to estimate the depth value of the intersection point on the horizontal and vertical EPIs.
Omni SCADA Intrusion Detection Using Deep Learning Algorithms
We investigate deep learning based omni intrusion detection system (IDS) for supervisory control and data acquisition (SCADA) networks that are capable of detecting both temporally uncorrelated and correlated attacks.
Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
Many machine learning models operate on images, but ignore the fact that images are 2D projections formed by 3D geometry interacting with light, in a process called rendering.
Ranked #4 on
Single-View 3D Reconstruction
on ShapeNet
Representation Degeneration Problem in Training Natural Language Generation Models
We study an interesting problem in training neural network-based models for natural language generation tasks, which we call the \emph{representation degeneration problem}.
Fine-Grained Sentence Functions for Short-Text Conversation
Classification models are trained on this dataset to (i) recognize the sentence function of new data in a large corpus of short-text conversations; (ii) estimate a proper sentence function of the response given a test query.
Personalized Bundle List Recommendation
In particular, BGN improves the precision of the best competitors by 16\% on average while maintaining the highest diversity on four datasets, and yields a 3. 85x improvement of response time over the best competitors in the bundle list recommendation problem.
Mimicking the In-Camera Color Pipeline for Camera-Aware Object Compositing
We present a method for compositing virtual objects into a photograph such that the object colors appear to have been processed by the photo's camera imaging pipeline.
Fast Interactive Object Annotation with Curve-GCN
Our model runs at 29. 3ms in automatic, and 2. 6ms in interactive mode, making it 10x and 100x faster than Polygon-RNN++.
DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces
Reconstruction of geometry based on different input modes, such as images or point clouds, has been instrumental in the development of computer aided design and computer graphics.
Generating Multiple Diverse Responses for Short-Text Conversation
In this paper, we propose a novel response generation model, which considers a set of responses jointly and generates multiple diverse responses simultaneously.
Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method
We observe that in the conversation tasks, each query could have multiple responses, which forms a 1-to-n or m-to-n relationship in the view of the total corpus.
Learning to Navigate for Fine-grained Classification
In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative regions under the guidance from Teacher.
Ranked #45 on
Fine-Grained Image Classification
on FGVC Aircraft
Integrated Server for Measurement-Device-Independent Quantum Key Distribution Network
Quantum key distribution (QKD), harnessing quantum physics and optoelectronics, may promise unconditionally secure information exchange in theory.
Quantum Physics
Dropout Training, Data-dependent Regularization, and Generalization Bounds
We study the problem of generalization guarantees for dropout training.
ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation
Downstream applications then can use the user behavior vectors via vanilla attention.
Direct Mapping Hidden Excited State Interaction Patterns from ab initio Dynamics and Its Implications on Force Field Development
Based on the knowledge of these meta-stable patterns, we suggested an interpolation scheme with only a concrete and finite set of known patterns to accurately predict the ground and excited state properties of the entire dynamics trajectories.
