Search Results for author:
Found 37 papers, 16 papers with code
Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity
With the growing use of large language models (LLMs) hosted on cloud platforms to offer inference services, privacy concerns about the potential leakage of sensitive information are escalating.
Autoregressive Stochastic Clock Jitter Compensation in Analog-to-Digital Converters
This paper deals with the mathematical modeling and compensation of stochastic discrete time clock jitter in Analog-to-Digital Converters (ADCs).
Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder
We prove that SAEs can serve as a good alternative to diversity measure and design our method to be scalable for potential industrial large-scale pruning, and we will also release our trained SAEs for use by the broader community.
A Systematic Examination of Preference Learning through the Lens of Instruction-Following
In this work we systematically investigate how specific attributes of preference datasets affect the alignment and downstream performance of LLMs in instruction-following tasks.
Self-Generated Critiques Boost Reward Modeling for Language Models
Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF).
Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
We focus on mathematical reasoning and without in-language math data, facilitate cross-lingual transfer by composing language and math capabilities.
Law of the Weakest Link: Cross Capabilities of Large Language Models
The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Question Answering
on PeerQA
Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model
In this work we introduce VistaLLM a powerful visual system that addresses coarse- and fine grained VL tasks over single and multiple input images using a unified framework.
Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model
In this work, we introduce VistaLLM, a powerful visual system that addresses coarse- and fine-grained VL tasks over single and multiple input images using a unified framework.
Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction
Specifically, our framework involves a symmetrical contrastive objective that encompasses both sentence-anchored and label-anchored contrastive losses.
RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training
Under a unified evaluation of fine-tuned LMs by incorporating four representative perspectives of model robustness, we demonstrate the effectiveness of RoAST compared to state-of-the-art fine-tuning methods on six different types of LMs, which indicates its usefulness in practice.
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming
Specifically, an adversarial LLM and a target LLM interplay with each other in an iterative manner, where the adversarial LLM aims to generate challenging prompts that elicit unsafe responses from the target LLM, while the target LLM is fine-tuned with safety aligned data on these adversarial prompts.
Co-training and Co-distillation for Quality Improvement and Compression of Language Models
2) The enhanced performance of the larger model further boosts the performance of the smaller model.
Effective Long-Context Scaling of Foundation Models
We also examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- our ablation experiments suggest that having abundant long texts in the pretrain dataset is not the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.
Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification
In addition, we design a multi-perspective attention mechanism that align relevant opinion information with respect to the given aspect.
Llama 2: Open Foundation and Fine-Tuned Chat Models
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters.
Ranked #2 on
Question Answering
on PubChemQA
A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models
Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance.
Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefixes
Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward passes.
Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization
In this work, we introduce Residual Prompt Tuning - a simple and efficient method that significantly improves the performance and stability of prompt tuning.
MMViT: Multiscale Multiview Vision Transformers
Our model encodes different views of the input signal and builds several channel-resolution feature stages to process the multiple views of the input at different resolutions in parallel.
SVT: Supertoken Video Transformer for Efficient Video Understanding
Whether by processing videos with fixed resolution from start to end or incorporating pooling and down-scaling strategies, existing video transformers process the whole video content throughout the network without specially handling the large portions of redundant information.
Progressive Prompts: Continual Learning for Language Models
We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models.
XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Large multilingual language models typically rely on a single vocabulary shared across 100+ languages.
Uniform Masking Prevails in Vision-Language Pretraining
Masked Language Modeling (MLM) has proven to be an essential component of Vision-Language (VL) pretraining.
Query Rewriting for Effective Misinformation Discovery
We propose a novel system to help fact-checkers formulate search queries for known misinformation claims and effectively search across multiple social media platforms.
IDPG: An Instance-Dependent Prompt Generation Method
Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage.
UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
Recent parameter-efficient language model tuning (PELT) methods manage to match the performance of fine-tuning with much fewer trainable parameters and perform especially well when training data is limited.
Weakly Supervised 3D Classification of Chest CT using Aggregated Multi-Resolution Deep Segmentation Features
Second, segmentation and classification models are connected with two different feature aggregation strategies to enhance the classification performance.
Classification of Multiple Diseases on Body CT Scans using Weakly Supervised Deep Learning
Purpose: To design multi-disease classifiers for body CT scans for three different organ systems using automatically extracted labels from radiology text reports. Materials & Methods: This retrospective study included a total of 12, 092 patients (mean age 57 +- 18; 6, 172 women) for model development and testing (from 2012-2017).
Semantically-Guided Representation Learning for Self-Supervised Monocular Depth
Instead of using semantic labels and proxy losses in a multi-task approach, we propose a new architecture leveraging fixed pretrained semantic segmentation networks to guide self-supervised representation learning via pixel-adaptive convolutions.
Measuring the Utilization of Public Open Spaces by Deep Learning: a Benchmark Study at the Detroit Riverfront
It is appealing to make use of surveillance cameras and to extract user-related information through computer vision.
Real-Time Panoptic Segmentation from Dense Detections
Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution.
Towards Automatic Detection of Misinformation in Online Medical Videos
Recent years have witnessed a significant increase in the online sharing of medical information, with videos representing a large fraction of such online sources.
An Efficient 3D CNN for Action/Object Segmentation in Video
Convolutional Neural Network (CNN) based image segmentation has made great progress in recent years.
Ranked #64 on
Semi-Supervised Video Object Segmentation
on DAVIS 2016
An End-to-end 3D Convolutional Neural Network for Action Detection and Segmentation in Videos
A video is first divided into equal length clips and next for each clip a set of tube proposals are generated based on 3D CNN features.
Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos
A video is first divided into equal length clips and for each clip a set of tube proposals are generated next based on 3D Convolutional Network (ConvNet) features.
Ranked #1 on
Action Detection
on UCF Sports
