Trending Research
GIVT: Generative Infinite-Vocabulary Transformers
google-research/big_vision
•
•
We introduce generative infinite-vocabulary transformers (GIVT) which generate vector sequences with real-valued entries, instead of discrete tokens from a finite vocabulary.
Ranked #13 on
Image Generation
on ImageNet 256x256
LOHO: Latent Optimization of Hairstyles via Orthogonalization
dukebw/LOHO
•
•
CVPR 2021
Therefore, we propose Latent Optimization of Hairstyles via Orthogonalization (LOHO), an optimization-based approach using GAN inversion to infill missing hair structure details in latent space during hairstyle transfer.
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
We present InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability.
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
We first decompose the video scene by using open-vocabulary mask trackers and an adapted image diffusion model to segment, track, and amodally complete the objects and background in the video.
State-Free Inference of State-Space Models: The Transfer Function Approach
ruke1ire/RTF
•
•
We approach designing a state-space model for deep learning applications through its dual representation, the transfer function, and uncover a highly efficient sequence parallel inference algorithm that is state-free: unlike other proposed algorithms, state-free inference does not incur any significant memory or computational cost with an increase in state size.
FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering
To investigate these aspects, we create and publish a novel TQA evaluation benchmark in English.
ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
hiyouga/llama-efficient-tuning
•
•
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e. g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.
SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing
modelscope/swift
•
•
Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable image synthesis.
Make Your LLM Fully Utilize the Context
While many contemporary large language models (LLMs) can process lengthy input, they still struggle to fully utilize information within the long context, known as the lost-in-the-middle challenge.
Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models
Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from various LMs.
