Search Results for author:
Found 41 papers, 19 papers with code
Can Editing LLMs Inject Harm?
Then, we find that editing attacks can inject both types of misinformation into LLMs, and the effectiveness is particularly high for commonsense misinformation injection.
MMSci: A Multimodal Multi-Discipline Dataset for PhD-Level Scientific Comprehension
The rapid advancement of Large Language Models (LLMs) and Large Multimodal Models (LMMs) has heightened the demand for AI-based scientific assistants capable of understanding scientific articles and figures.
MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs
Current multimodal misinformation detection (MMD) methods often assume a single source and type of forgery for each sample, which is insufficient for real-world scenarios where multiple forgery sources coexist.
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
We introduce MuirBench, a comprehensive benchmark that focuses on robust multi-image understanding capabilities of multimodal LLMs.
Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner
Specifically, semantic guidance is derived by establishing a semantic editing direction based on reasoned intentions, while quality guidance is achieved through classifier guidance using an image fidelity discriminator.
FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs
The massive generation of multimodal fake news involving both text and images exhibits substantial distribution discrepancies, prompting the need for generalized detectors.
Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
We also show that by fine-tuning on a small collection of diverse task-oriented dialogues, we can equip modestly sized models, specifically a 13B parameter LLaMA2-Chat model, with function-calling capabilities and DST performance comparable to ChatGPT while maintaining their chat capabilities.
MANUS: Markerless Grasp Capture using Articulated 3D Gaussians
Since our representation uses Gaussian primitives, it enables us to efficiently and accurately estimate contacts between the hand and the object.
Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models
The experiments demonstrate the superior performance of Surf-D in shape generation across multiple modalities as conditions.
InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser
We employ DDIM inversion to extract this noise from the reference image and leverage a diffusion model to generate new stylized images from the "style" noise.
GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding
This paper introduces GeoLM, a geospatially grounded language model that enhances the understanding of geo-entities in natural language.
AlpaCare:Instruction-tuned Large Language Models for Medical Application
Instruction-finetuning (IFT) has become crucial in aligning Large Language Models (LLMs) with diverse human needs and has shown great potential in medical applications.
Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals
Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practical scenarios.
IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization
Semi-supervised learning (SSL) aims to leverage massive unlabeled data when labels are expensive to obtain.
Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection
In this work, we establish a benchmark to evaluate the robustness of instruction-following LLMs against prompt injection attacks.
The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Maps
mapKurator empowers automated extraction, post-processing, and linkage of text labels from large numbers of large-dimension historical map scans.
Learning Anchor Transformations for 3D Garment Animation
Once the anchor transformations are found, per-vertex nonlinear displacements of the garment template can be regressed in a canonical space, which reduces the complexity of deformation space learning.
CHATEDIT: Towards Multi-turn Interactive Facial Image Editing via Dialogue
This paper explores interactive facial image editing via dialogue and introduces the ChatEdit benchmark dataset for evaluating image editing and conversation abilities in this context.
Time Series as Images: Vision Transformer for Irregularly Sampled Time Series
This paper introduces a novel perspective by converting irregularly sampled time series into line graph images, then utilizing powerful pre-trained vision transformers for time series classification in the same way as image classification.
Guiding Large Language Models via Directional Stimulus Prompting
Our experiments demonstrate that the framework consistently improves LLMs' (e. g., ChatGPT, Codex, InstructGPT) performance on these supervised tasks using minimal labeled data.
Order-Prompted Tag Sequence Generation for Video Tagging
This paper proposes a novel generative model, Order-Prompted Tag Sequence Generation (OP-TSG), according to the above characteristics.
SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation
Characterizing geo-entities is integral to various application domains, such as geo-intelligence and map comprehension, while a key challenge is to capture the spatial-varying context of an entity.
Explanations from Large Language Models Make Small Reasoners Better
Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations.
Controllable Dialogue Simulation with In-Context Learning
Experimental results on the MultiWOZ dataset demonstrate that training a model on the simulated dialogues leads to even better performance than using the same amount of human-generated dialogues under the challenging low-resource settings, with as few as 85 dialogues as a seed.
Limitations of Language Models in Arithmetic and Symbolic Induction
LMs with tutor is able to deliver 100% accuracy in situations of OOD and repeating symbols, shedding new insights on the boundary of large LMs in induction.
HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection
Sample assignment plays a prominent part in modern object detection approaches.
Eliminating Gradient Conflict in Reference-based Line-Art Colorization
To understand the instability in training, we detect the gradient flow of attention and observe gradient conflict among attention branches.
Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection
We show that the state-of-the-art text detection models (e. g., PSENet) can benefit from the synthetic historical maps and achieve significant improvement for historical map text detection.
An Automatic Approach for Generating Rich, Linked Geo-Metadata from Historical Map Images
This paper presents an end-to-end approach to address the real-world problem of finding and indexing historical map images.
Optical Character Recognition
Optical Character Recognition (OCR)
SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction
CDI builds the global attention and interaction among different levels in decoupled space which also solves the problem of heavy computation.
GraphFM: Graph Factorization Machines for Feature Interaction Modeling
To solve the problems, we propose a novel approach, Graph Factorization Machine (GraphFM), by naturally representing features in the graph structure.
DyGCN: Dynamic Graph Embedding with Graph Convolutional Network
We naturally generalizes the embedding propagation scheme of GCN to dynamic setting in an efficient manner, which is to propagate the change along the graph to update node embeddings.
A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning
How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world.
PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth Image
In this paper, a real-time method called PoP-Net is proposed to predict multi-person 3D poses from a depth image.
Cold-start Sequential Recommendation via Meta Learner
As there is generally no side information in the setting of sequential recommendation task, previous cold-start methods could not be applied when only user-item interactions are available.
DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection
Furthermore, these two components are both plug-and-play and can be embedded in any backbone.
Heterogeneous Graph Collaborative Filtering
In this work, we propose to model user-item interactions as a heterogeneous graph which consists of not only user-item edges indicating their interaction but also user-user edges indicating their similarity.
DGTN: Dual-channel Graph Transition Network for Session-based Recommendation
These item transitions include potential collaborative information and reflect similar behavior patterns, which we assume may help with the recommendation for the target session.
Ranked #6 on
Session-Based Recommendations
on Diginetica
Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction
The key of this task is to model feature interactions among different feature fields.
Ranked #10 on
Click-Through Rate Prediction
on Avazu
Semi-supervised Compatibility Learning Across Categories for Clothing Matching
To achieve the alignment, we minimize the distances between distributions with unsupervised adversarial learning, and also the distances between some annotated compatible items which play the role of anchor points to help align.
Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks
In this paper, we aim to investigate a practical problem of fashion recommendation by answering the question "which item should we select to match with the given fashion items and form a compatible outfit".
Ranked #1 on
Recommendation Systems
on Polyvore
(Accuracy metric)
