research
∙
09/20/2023
Kosmos-2.5: A Multimodal Literate Model
We present Kosmos-2.5, a multimodal literate model for machine reading o...
share
research
∙
09/11/2023
Large Language Model for Science: A Study on P vs. NP
In this work, we use large language models (LLMs) to augment and acceler...
research
∙
09/03/2023
Large AI Model Empowered Multimodal Semantic Communications
Multimodal signals, including text, audio, image and video, can be integ...
research
∙
08/29/2023
LAMBO: Large Language Model Empowered Edge Intelligence
Next-generation edge intelligence is anticipated to bring huge benefits ...
research
∙
08/08/2023
Evil Operation: Breaking Speaker Recognition with PaddingBack
Machine Learning as a Service (MLaaS) has gained popularity due to advan...
research
∙
08/04/2023
Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition
Optical Character Recognition (OCR) enables automatic text extraction fr...
research
∙
07/17/2023
Retentive Network: A Successor to Transformer for Large Language Models
In this work, we propose Retentive Network (RetNet) as a foundation arch...
research
∙
07/07/2023
Large AI Model-Based Semantic Communications
Semantic communication (SC) is an emerging intelligent paradigm, offerin...
research
∙
07/05/2023
LongNet: Scaling Transformers to 1,000,000,000 Tokens
Scaling sequence length has become a critical demand in the era of large...
research
∙
06/28/2023
Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion
Deep speech classification has achieved tremendous success and greatly p...
research
∙
06/26/2023
Kosmos-2: Grounding Multimodal Large Language Models to the World
We introduce Kosmos-2, a Multimodal Large Language Model (MLLM), enablin...
research
∙
06/14/2023
Knowledge Distillation of Large Language Models
Knowledge Distillation (KD) is a promising technique for reducing the hi...
research
∙
06/12/2023
Augmenting Language Models with Long-Term Memory
Existing large language models (LLMs) can only afford fix-sized inputs d...
research
∙
05/16/2023
Pre-Training to Learn in Context
In-context learning, where pre-trained language models learn to perform ...
research
∙
02/28/2023
Generic-to-Specific Distillation of Masked Autoencoders
Large vision Transformers (ViTs) driven by self-supervised pre-training ...
research
∙
02/27/2023
Language Is Not All You Need: Aligning Perception with Language Models
A big convergence of language, multimodal perception, action, and world ...
research
∙
12/21/2022
Language Models as Inductive Reasoners
Inductive reasoning is a core component of human intelligence. In the pa...
research
∙
12/20/2022
Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers
Large pretrained language models have shown surprising In-Context Learni...
research
∙
12/20/2022
A Length-Extrapolatable Transformer
Position modeling plays a critical role in Transformers. In this paper, ...
research
∙
12/20/2022
GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator
Pre-trained models have achieved remarkable success in natural language ...
research
∙
12/19/2022
Optimizing Prompts for Text-to-Image Generation
Well-designed prompts can guide text-to-image models to generate amazing...
research
∙
12/13/2022
Structured Prompting: Scaling In-Context Learning to 1,000 Examples
Large language models have exhibited intriguing in-context learning capa...
research
∙
12/01/2022
Extensible Prompts for Language Models
We propose eXtensible Prompt (X-Prompt) for prompting a large language m...
research
∙
11/23/2022
TorchScale: Transformers at Scale
Large Transformers have achieved state-of-the-art performance across man...
research
∙
10/27/2022
Joint Optimization of Deployment and Trajectory in UAV and IRS-Assisted IoT Data Collection System
Unmanned aerial vehicles (UAVs) can be applied in many Internet of Thing...
research
∙
10/26/2022
Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning
In this paper, we elaborate upon recipes for building multilingual repre...
research
∙
10/19/2022
A Unified View of Masked Image Modeling
Masked image modeling has demonstrated great potential to eliminate the ...
research
∙
10/17/2022
Non-Contrastive Learning Meets Language-Image Pre-Training
Contrastive language-image pre-training (CLIP) serves as a de-facto stan...
research
∙
10/13/2022
CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation
Named entity recognition (NER) suffers from the scarcity of annotated tr...
research
∙
10/12/2022
Foundation Transformers
A big convergence of model architectures across language, vision, speech...
research
∙
09/26/2022
Exploiting Hybrid Active and Passive Multiple Access via Slotted ALOHA-Driven Backscatter Communications
In conventional backscatter communication (BackCom) systems, time divisi...
research
∙
09/03/2022
Semi-Supervised Semantic Segmentation with Cross Teacher Training
Convolutional neural networks can achieve remarkable performance in sema...
research
∙
08/22/2022
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
A big convergence of language, vision, and multimodal pretraining is eme...
research
∙
08/12/2022
BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers
Masked image modeling (MIM) has demonstrated impressive results in self-...
research
∙
06/30/2022
Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations
Deep neural networks (DNNs) have been shown to be vulnerable against adv...
research
∙
06/13/2022
Language Models are General-Purpose Interfaces
Foundation models have received much attention due to their effectivenes...
research
∙
06/02/2022
VL-BEiT: Generative Vision-Language Pretraining
We introduce a vision-language foundation model called VL-BEiT, which is...
research
∙
06/01/2022
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption
As more and more pre-trained language models adopt on-cloud deployment, ...
research
∙
05/22/2022
Exploiting Constructive Interference for Backscatter Communication Systems
Backscatter communication (BackCom), one of the core technologies to rea...
research
∙
05/20/2022
Prototypical Calibration for Few-shot Learning of Language Models
In-context learning of GPT-like models has been recognized as fragile ac...
research
∙
05/20/2022
Visually-Augmented Language Modeling
Human language is grounded on multimodal knowledge including visual know...
research
∙
05/16/2022
Transferability of Adversarial Attacks on Synthetic Speech Detection
Synthetic speech detection is one of the most important research problem...
research
∙
05/01/2022
Many a little Makes a Mickle: Probing Backscattering Energy Recycling for Backscatter Communications
In this paper, we investigate and analyze full-duplex-based backscatter ...
research
∙
04/20/2022
On the Representation Collapse of Sparse Mixture of Experts
Sparse mixture of experts provides larger model capacity while requiring...
research
∙
04/18/2022
StableMoE: Stable Routing Strategy for Mixture of Experts
The Mixture-of-Experts (MoE) technique can scale up the model size of Tr...
research
∙
03/14/2022
CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment
CLIP has shown a remarkable zero-shot capability on a wide range of visi...
research
∙
03/01/2022
DeepNet: Scaling Transformers to 1,000 Layers
In this paper, we propose a simple yet effective method to stabilize ext...
research
∙
02/27/2022
Controllable Natural Language Generation with Contrastive Prefixes
To guide the generation of large pretrained language models (LM), previo...
research
∙
02/17/2022
A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models
With the increasing of model capacity brought by pre-trained language mo...
research
∙
02/07/2022