Elastic Decision Transformer paper page: https://
huggingface.co/papers/2307.02
484
… paper introduces Elastic Decision Transformer (EDT), a significant advancement over the existing Decision Transformer (DT) and its variants. Although DT purports to generate an optimal trajectory, empirical
MACHINE LEARNING
-
Elastic Decision Transformer: Advancement Over Decision Transformer
By
–
-
Physics-based Motion Retargeting from Sparse Inputs for Virtual Avatars
By
–
Physics-based Motion Retargeting from Sparse Inputs
— AK (@_akhaliq) 6 juillet 2023
paper page: https://t.co/UySmlAwj7I
Avatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user's motion is that commercial AR/VR… pic.twitter.com/lJeVhLji4gPhysics-based Motion Retargeting from Sparse Inputs paper page: https://
huggingface.co/papers/2307.01
938
… Avatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user's motion is that commercial AR/VR -
EmoGen: Eliminating Subjective Bias in Emotional Music Generation
By
–
EmoGen: Eliminating Subjective Bias in Emotional Music Generation paper page: https://
huggingface.co/papers/2307.01
229
… Music is used to convey emotions, and thus generating emotional music is important in automatic music generation. Previous work on emotional music generation directly uses -
MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers
By
–
MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers paper page: https://
huggingface.co/papers/2307.02
321
… The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content. However, -
SDXL: Advanced Latent Diffusion Model for High-Resolution Image Synthesis
By
–
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis paper page: https://
huggingface.co/papers/2307.01
952
… present SDXL, a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet -
DiT-3D: Diffusion Transformers for 3D Shape Generation
By
–
DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation paper page: https://
huggingface.co/papers/2307.01
831
… Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined -
Training GPT-4 Style Language Models with Multimodal Inputs
By
–
What Matters in Training a GPT4-Style Language Model with Multimodal Inputs? paper page: https://
huggingface.co/papers/2307.02
469
… Recent advancements in Large Language Models (LLMs) such as GPT4 have displayed exceptional multi-modal capabilities in following open-ended instructions given -
Robots Asking for Help: Uncertainty Alignment for LLM Planners
By
–
Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
— AK (@_akhaliq) 6 juillet 2023
paper page: https://t.co/h9SdV0Drac
Large language models (LLMs) exhibit a wide range of promising capabilities — from step-by-step planning to commonsense reasoning — that may provide utility… pic.twitter.com/9JH4nAABYJRobots That Ask For Help: Uncertainty Alignment for Large Language Model Planners paper page: https://
huggingface.co/papers/2307.01
928
… Large language models (LLMs) exhibit a wide range of promising capabilities — from step-by-step planning to commonsense reasoning — that may provide utility -
Embodied Task Planning with Large Language Models for Robots
By
–
Embodied Task Planning with Large Language Models paper page: https://
huggingface.co/papers/2307.01
848
… Equipping embodied agents with commonsense is important for robots to successfully complete complex human instructions in general environments. Recent large language models (LLM) can embed -
LongNet: Scaling Transformers to Handle Billion Tokens
By
–
LongNet: Scaling Transformers to 1,000,000,000 Tokens paper page: https://
huggingface.co/papers/2307.02
486
… Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity,