Search Results for author:
Found 15 papers, 10 papers with code
Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts
Pretrained Language Models (PLMs) have advanced Natural Language Processing (NLP) tasks significantly, but finetuning PLMs on low-resource datasets poses significant challenges such as instability and overfitting.
Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
Large language models generate high-quality responses with potential misinformation, underscoring the need for regulation by distinguishing AI-generated and human-written texts.
BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM
Secondly, SAM faces challenges in excelling at specific downstream tasks, like medical imaging, due to a disparity between the distribution of its pretraining data, which predominantly consists of general-domain images, and the data used in downstream tasks.
Rich Human Feedback for Text-to-Image Generation
We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions.
UniAR: Unifying Human Attention and Response Prediction on Visual Content
Such a model would enable predicting subjective feedback such as overall satisfaction or aesthetic quality ratings, along with the underlying human attention or interaction heatmaps and viewing order, enabling designers and content-creation models to optimize their creation for human-centric improvements.
Large Language Models for Compiler Optimization
We explore the novel application of Large Language Models to code optimization.
DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs
The DrugChat system consists of a graph neural network (GNN), a large language model (LLM), and an adaptor.
Learning Compiler Pass Orders using Coreset and Normalized Value Prediction
Finding the optimal pass sequence of compilation can lead to a significant reduction in program size and/or improvement in program efficiency.
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations
Second, by maintaining the same computational cost, our method empowers ViTs to take more image tokens as input for recognition accuracy improvement, where the image tokens are from higher resolution images.
Ranked #4 on
Efficient ViTs
on ImageNet-1K (with DeiT-S)
Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning
Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL.
Improving Differentiable Architecture Search with a Generative Model
We introduce a training strategy called ``Differentiable Architecture Search with a Generative Model(DASGM)."
Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL.
EViT: Expediting Vision Transformers via Token Reorganizations
Second, by maintaining the same computational cost, our method empowers ViTs to take more image tokens as input for recognition accuracy improvement, where the image tokens are from higher resolution images.
Large Norms of CNN Layers Do Not Hurt Adversarial Robustness
Since the Lipschitz properties of convolutional neural networks (CNNs) are widely considered to be related to adversarial robustness, we theoretically characterize the $\ell_1$ norm and $\ell_\infty$ norm of 2D multi-channel convolutional layers and provide efficient methods to compute the exact $\ell_1$ norm and $\ell_\infty$ norm.
Multi-view Graph Learning by Joint Modeling of Consistency and Inconsistency
To overcome this limitation, we propose a new multi-view graph learning framework, which for the first time simultaneously and explicitly models multi-view consistency and multi-view inconsistency in a unified objective function, through which the consistent and inconsistent parts of each single-view graph as well as the unified graph that fuses the consistent parts can be iteratively learned.
