Search Results for author:
Found 13 papers, 7 papers with code
Just Say What You Want: Only-prompting Self-rewarding Online Preference Optimization
We address the challenge of online Reinforcement Learning from Human Feedback (RLHF) with a focus on self-rewarding alignment methods.
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Training LLMs at this scale brings unprecedented challenges to training efficiency and stability.
MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels
Despite deep learning has achieved great success, it often relies on a large amount of training data with accurate labels, which are expensive and time-consuming to collect.
Generative Negative Text Replay for Continual Vision-Language Pretraining
In this work, we focus on learning a VLP model with sequential chunks of image-text pair data.
General Incremental Learning with Domain-aware Categorical Representations
Continual learning is an important problem for achieving human-level intelligence in real-world applications as an agent must continuously accumulate knowledge in response to streaming data/tasks.
Budget-aware Few-shot Learning via Graph Convolutional Network
In this work, we introduce a new budget-aware few-shot learning problem that not only aims to learn novel object categories, but also needs to select informative examples to annotate in order to achieve data efficiency.
How Well Does Self-Supervised Pre-Training Perform with Streaming ImageNet?
Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.
An EM Framework for Online Incremental Learning of Semantic Segmentation
Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting.
How Well Does Self-Supervised Pre-Training Perform with Streaming Data?
Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.
DER: Dynamically Expandable Representation for Class Incremental Learning
We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence.
Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition.
Ranked #19 on
Long-tail Learning
on Places-LT
Dynamic Context Correspondence Network for Semantic Alignment
We instantiate our strategy by designing an end-to-end learnable deep network, named as Dynamic Context Correspondence Network (DCCNet).
LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
A promising strategy is to model the feature context by a fully-connected graph neural network (GNN), which augments traditional convolutional features with an estimated non-local context representation.
