Search Results for author:
Found 32 papers, 15 papers with code
Reverse Thinking Makes LLMs Stronger Reasoners
Reverse thinking plays a crucial role in human reasoning.
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Extensive experiments demonstrate that Model Swarms could flexibly adapt LLM experts to a single task, multi-task domains, reward models, as well as diverse human interests, improving over 12 model composition baselines by up to 21. 0% across tasks and contexts.
CROME: Cross-Modal Adapters for Efficient Multimodal LLM
Multimodal Large Language Models (MLLMs) demonstrate remarkable image-language capabilities, but their widespread use faces challenges in cost-effective training and adaptation.
Ranked #46 on
Visual Question Answering
on MM-Vet
Data-augmented phrase-level alignment for mitigating object hallucination
To fine-tune MLLMs with DPA, we first generate a set of `hallucinated' and `correct' response pairs through generative data augmentation by selectively altering the ground-truth information of the correct responses at a phrase level.
Continual Learning of Large Language Models: A Comprehensive Survey
In this survey, we provide a comprehensive overview of the current research progress on LLMs within the context of CL.
TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents
Given their nature as black-boxes using complex reasoning processes on their inputs, it is inevitable that the demand for scalable and faithful explanations for LLMs' generated content will continue to grow.
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation.
PAITS: Pretraining and Augmentation for Irregularly-Sampled Time Series
In this paper, we present PAITS (Pretraining and Augmentation for Irregularly-sampled Time Series), a framework for identifying suitable pretraining strategies for sparse and irregularly sampled time series datasets.
LANISTR: Multimodal Learning from Structured and Unstructured Data
To bridge this gap, we propose LANISTR, an attention-based framework to learn from LANguage, Image, and STRuctured data.
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction
In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain while increasing accuracy and coverage.
Beyond Invariance: Test-Time Label-Shift Adaptation for Distributions with "Spurious" Correlations
However, we assume that the generative model for features $p(x|y, z)$ is invariant across domains.
Test-Time Adaptation for Visual Document Understanding
For visual document understanding (VDU), self-supervised pretraining has been shown to successfully generate transferable representations, yet, effective adaptation of such representations to distribution shifts at test-time remains to be an unexplored area.
Contrastive Test-Time Adaptation
We propose a novel way to leverage self-supervised contrastive learning to facilitate target feature learning, along with an online pseudo labeling scheme with refinement that significantly denoises pseudo labels.
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting.
Zero-Shot Reward Specification via Grounded Natural Language
Reward signals in reinforcement learning can be expensive signals in many tasks and often require access to direct state.
Differentiable Gradient Sampling for Learning Implicit 3D Scene Reconstructions from a Single Image
Existing approaches for single object reconstruction impose supervision signals based on the loss of the signed distance value from all locations in a scene, posing difficulties when extending to real-world scenarios.
On-target Adaptation
Domain adaptation seeks to mitigate the shift between training on the \emph{source} domain and testing on the \emph{target} domain.
Region-level Active Detector Learning
Active learning for object detection is conventionally achieved by applying techniques developed for classification in a way that aggregates individual detections into image-level selection criteria.
Predicting with Confidence on Unseen Distributions
Our work connects techniques from domain adaptation and predictive uncertainty literature, and allows us to predict model accuracy on challenging unseen distributions without access to labeled data.
Self-Supervised Pretraining Improves Self-Supervised Pretraining
Through experimentation on 16 diverse vision datasets, we show HPT converges up to 80x faster, improves accuracy across tasks, and improves the robustness of the self-supervised pretraining process to changes in the image augmentation policy or amount of pretraining data.
Minimax Active Learning
Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator.
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting.
Adversarial Continual Learning
We show that shared features are significantly less prone to forgetting and propose a novel hybrid continual learning framework that learns a disjoint representation for task-invariant and task-specific features required to solve a sequence of tasks.
WiCV 2019: The Sixth Women In Computer Vision Workshop
In this paper we present the Women in Computer Vision Workshop - WiCV 2019, organized in conjunction with CVPR 2019.
Uncertainty-guided Continual Learning with Bayesian Neural Networks
Continual learning aims to learn new tasks without forgetting previously learned ones.
Variational Adversarial Active Learning
Unlike conventional active learning algorithms, our approach is task agnostic, i. e., it does not depend on the performance of the task for which we are trying to acquire labeled data.
Compositional GAN (Extended Abstract): Learning Image-Conditional Binary Composition
Generative Adversarial Networks (GANs) can produce images of surprising complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene.
Cross-Linked Variational Autoencoders for Generalized Zero-Shot Learning
While following the same direction, we also take artificial feature generation one step further and propose a model where a shared latent space of image features and class embeddings is learned by aligned variational autoencoders, for the purpose of generating latent features to train a softmax classifier.
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space.
Ranked #2 on
Generalized Few-Shot Learning
on AwA2
Uncertainty-guided Lifelong Learning in Bayesian Networks
Sequentially learning of tasks arriving in a continuous stream is a complex problem and becomes more challenging when the model has a fixed capacity.
Compositional GAN: Learning Image-Conditional Binary Composition
Generative Adversarial Networks (GANs) can produce images of remarkable complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene.
Gradient-free Policy Architecture Search and Adaptation
We develop a method for policy architecture search and adaptation via gradient-free optimization which can learn to perform autonomous driving tasks.
