Search Results for author:
Found 12 papers, 11 papers with code
Interfacing Foundation Models' Embeddings
The proposed interface is adaptive to new tasks, and new models.
LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models
To address this issue, we have created GVC data that allows for the combination of grounding and chat capabilities.
Visual In-Context Prompting
In-context prompting in large language models (LLMs) has become a prevalent approach to improve zero-shot capabilities, but this idea is less explored in the vision domain.
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
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
We present Set-of-Mark (SoM), a new visual prompting method, to unleash the visual grounding abilities of large multimodal models (LMMs), such as GPT-4V.
Semantic-SAM: Segment and Recognize Anything at Any Granularity
In this paper, we introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity.
Segment Everything Everywhere All at Once
In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs).
A Simple Framework for Open-Vocabulary Segmentation and Detection
We present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that jointly learns from different segmentation and detection datasets.
Ranked #2 on
Instance Segmentation
on ADE20K val
(using extra training data)
Generalized Decoding for Pixel, Image, and Language
We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly.
Ranked #4 on
Instance Segmentation
on ADE20K val
(using extra training data)
End-to-End Instance Edge Detection
We demonstrate highly competitive instance edge detection performance compared to state-of-the-art baselines, and also show that the proposed task and loss are complementary to instance segmentation and object detection.
Progressive Temporal Feature Alignment Network for Video Inpainting
To achieve this goal, it is necessary to find correspondences from neighbouring frames to faithfully hallucinate the unknown content.
Delving Deeper into Anti-aliasing in ConvNets
Aliasing refers to the phenomenon that high frequency signals degenerate into completely different ones after sampling.
