Search Results for author:
Found 21 papers, 8 papers with code
Exploring Perceptual Limitation of Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have recently shown remarkable perceptual capability in answering visual questions, however, little is known about the limits of their perception.
The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models
While large language models (LLMs) are still being adopted to new domains and utilized in novel applications, we are experiencing an influx of the new generation of foundation models, namely multi-modal large language models (MLLMs).
Passive Non-Line-of-Sight Imaging with Light Transport Modulation
In this work, we propose NLOS-LTM, a novel passive NLOS imaging method that effectively handles multiple light transport conditions with a single network.
Helping Language Models Learn More: Multi-dimensional Task Prompt for Few-shot Tuning
In interaction with large language models, embedding more task-related information into prompts will make it easier to stimulate knowledge embedded in large language models.
Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs
In particular, we show that their zero-shot accuracy in answering visual questions is very sensitive to the size of the visual subject of the question, declining up to 46% with size.
PINN-based viscosity solution of HJB equation
This paper proposed a novel PINN-based viscosity solution for HJB equations.
Differentially private sliced inverse regression in the federated paradigm
Sliced inverse regression (SIR), which includes linear discriminant analysis (LDA) as a special case, is a popular and powerful dimension reduction tool.
A Study of Situational Reasoning for Traffic Understanding
Intelligent Traffic Monitoring (ITMo) technologies hold the potential for improving road safety/security and for enabling smart city infrastructure.
Using Visual Cropping to Enhance Fine-Detail Question Answering of BLIP-Family Models
As our initial analysis of BLIP-family models revealed difficulty with answering fine-detail questions, we investigate the following question: Can visual cropping be employed to improve the performance of state-of-the-art visual question answering models on fine-detail questions?
Knowledge-enhanced Agents for Interactive Text Games
We experiment with four models on the 10 tasks in the ScienceWorld text-based game environment, to illustrate the impact of knowledge injection on various model configurations and challenging task settings.
Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings
To address this, we propose geometry decomposition and adopt a two-stage, coarse-to-fine training strategy, allowing for progressively capturing high-frequency geometric details.
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases.
Utilizing Background Knowledge for Robust Reasoning over Traffic Situations
Understanding novel situations in the traffic domain requires an intricate combination of domain-specific and causal commonsense knowledge.
AReputation-Based Mechanism for Transaction Processing in Blockchain Systems
First, we modify the verification strategy so that nodes set a probability of verifying a received transaction considering the likelihood of it being spam: transactions from a node with a low reputation have a high probability of being verified.
An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs
In this paper, we study the effect of knowledge sampling strategies and sizes that can be used to generate synthetic data for adapting language models.
EventFormer: AU Event Transformer for Facial Action Unit Event Detection
Facial action units (AUs) play an indispensable role in human emotion analysis.
CCPM: A Chinese Classical Poetry Matching Dataset
We hope this dataset can further enhance the study on incorporating deep semantics into the understanding and generation system of Chinese classical poetry.
Evaluation of Transportation Systems and Novel UV-Oriented Solution for Integration, Resilience, Inclusiveness and Sustainability
ransportation systems have revolutionized the form of society.
Modeling Discourse Structure for Document-level Neural Machine Translation
Finally, we combine the discourse structure information with the word embedding before it is fed into the encoder.
Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation ($\text{POINT}^2$)
As the POI tracker is shift-invariant, $\text{POINT}^2$ is more robust to the initial pose of the 3D pre-intervention image.
