MobileNMT: Enabling Translation in 15MB and 30ms paper page: https://
huggingface.co/papers/2306.04
235
… Deploying NMT models on mobile devices is essential for privacy, low latency, and offline scenarios. For high model capacity, NMT models are rather large. Running these models on devices is
MACHINE LEARNING
-
MobileNMT: Neural Machine Translation for Mobile Devices
By
–
-
LLMZip: Lossless Text Compression Using Large Language Models
By
–
LLMZip: Lossless Text Compression using Large Language Models paper page: https://
huggingface.co/papers/2306.04
050
… provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor for the next token given a window of past -
ARTIC3D: Learning Robust Articulated 3D Shapes from Web Images
By
–
ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections
— AK (@_akhaliq) 8 juin 2023
paper page: https://t.co/UGFpZ1Rce6
Estimating 3D articulated shapes like animal bodies from monocular images is inherently challenging due to the ambiguities of camera viewpoint, pose, texture,… pic.twitter.com/nbhred7HDPARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections paper page: https://
huggingface.co/papers/2306.04
619
… Estimating 3D articulated shapes like animal bodies from monocular images is inherently challenging due to the ambiguities of camera viewpoint, pose, texture, -
Designing a Better Asymmetric VQGAN for Stable Diffusion
By
–
Designing a Better Asymmetric VQGAN for StableDiffusion paper page: https://
huggingface.co/papers/2306.04
632
… StableDiffusion is a revolutionary text-to-image generator that is causing a stir in the world of image generation and editing. Unlike traditional methods that learn a diffusion model in -
Reliability of Watermarks for Large Language Models
By
–
On the Reliability of Watermarks for Large Language Models paper page: https://
huggingface.co/papers/2306.04
634
… Large language models (LLMs) are now deployed to everyday use and positioned to produce large quantities of text in the coming decade. Machine-generated text may displace -
PromptBench: Evaluating LLM Robustness Against Adversarial Prompts
By
–
PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts paper page: https://
huggingface.co/papers/2306.04
528
… The increasing reliance on Large Language Models (LLMs) across academia and industry necessitates a comprehensive understanding of their robustness -
Youku-mPLUG: 10M Chinese Video-Language Dataset for Pre-training
By
–
Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks paper page: https://
huggingface.co/papers/2306.04
362
… To promote the development of Vision-Language Pre-training (VLP) and multimodal Large Language Model (LLM) in the Chinese community, we -
Generating Diverse Text Data with LLMs and Human Input
By
–
Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions paper page: https://
huggingface.co/papers/2306.04
140
… Large language models (LLMs) can be used to generate text data for training and evaluating other models. However, -
Text-only Domain Adaptation for Speech Recognition using Unified Representation
By
–
Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer paper page: https://
huggingface.co/papers/2306.04
076
… Domain adaptation using text-only corpus is challenging in end-to-end(E2E) speech recognition. Adaptation by synthesizing audio from text through TTS is -
Certified Reasoning with Language Models for Sound Step-by-Step Reasoning
By
–
Certified Reasoning with Language Models paper page: https://
huggingface.co/papers/2306.04
031
… Language models often achieve higher accuracy when reasoning step-by-step in complex tasks. However, their reasoning can be unsound, inconsistent, or rely on undesirable prior assumptions. To tackle