Search Results for author:
Found 18 papers, 11 papers with code
Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models
In this framework, people can propose new basic composition methods and combine them to get the new mixed composition methods.
Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT
Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions.
Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers
Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details.
CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model
To this end, we introduce MoELoRA to MLLMs which is effective to retain the previous instruction alignment.
Symmetrical Bidirectional Knowledge Alignment for Zero-Shot Sketch-Based Image Retrieval
In this paper, we propose a novel Symmetrical Bidirectional Knowledge Alignment for zero-shot sketch-based image retrieval (SBKA).
3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V
In this work, we present a new visual prompting method called 3DAxiesPrompts (3DAP) to unleash the capabilities of GPT-4V in performing 3D spatial tasks.
Less is More: On the Feature Redundancy of Pretrained Models When Transferring to Few-shot Tasks
Transferring a pretrained model to a downstream task can be as easy as conducting linear probing with target data, that is, training a linear classifier upon frozen features extracted from the pretrained model.
Enhanced Federated Optimization: Adaptive Unbiased Client Sampling with Reduced Variance
Central to this process is the technique of unbiased client sampling, which ensures a representative selection of clients.
Language-Enhanced Session-Based Recommendation with Decoupled Contrastive Learning
Furthermore, we introduce a novel Decoupled Contrastive Learning method to enhance the effectiveness of the language representation.
DETA: Denoised Task Adaptation for Few-Shot Learning
Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples.
A Closer Look at Few-shot Classification Again
Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples.
Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid
In this paper, we find that this problem usually occurs when the positions of support samples are in the vicinity of task centroid -- the mean of all class centroids in the task.
Channel Importance Matters in Few-Shot Image Classification
When facing novel few-shot tasks in the test-time datasets, this transformation can greatly improve the generalization ability of learned image representations, while being agnostic to the choice of training algorithms and datasets.
Exploring Category-correlated Feature for Few-shot Image Classification
To alleviate this problem, we present a simple yet effective feature rectification method by exploring the category correlation between novel and base classes as the prior knowledge.
Adaptive Multi-layer Contrastive Graph Neural Networks
AMC-GNN generates two graph views by data augmentation and compares different layers' output embeddings of Graph Neural Network encoders to obtain feature representations, which could be used for downstream tasks.
Boosting Few-Shot Classification with View-Learnable Contrastive Learning
The goal of few-shot classification is to classify new categories with few labeled examples within each class.
Rectifying the Shortcut Learning of Background for Few-Shot Learning
The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL).
Auto-view contrastive learning for few-shot image recognition
Few-shot learning aims to recognize new classes with few annotated instances within each category.
