Trending Research
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
LongLoRA adopts LLaMA2 7B from 4k context to 100k, or LLaMA2 70B to 32k on a single 8x A100 machine.
Communicative Agents for Software Development
At the core of this paradigm lies ChatDev, a virtual chat-powered software development company that mirrors the established waterfall model, meticulously dividing the development process into four distinct chronological stages: designing, coding, testing, and documenting.
The Rise and Potential of Large Language Model Based Agents: A Survey
Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks.
Agents: An Open-source Framework for Autonomous Language Agents
Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language interfaces.
QLoRA: Efficient Finetuning of Quantized LLMs
QwenLM/Qwen-7B
•
•
Our best model family, which we name Guanaco, outperforms all previous openly released models on the Vicuna benchmark, reaching 99. 3% of the performance level of ChatGPT while only requiring 24 hours of finetuning on a single GPU.
Ranked #2 on
Sentence Completion
on HellaSwag
ProPainter: Improving Propagation and Transformer for Video Inpainting
sczhou/propainter
•
•
ICCV 2023
We also propose a mask-guided sparse video Transformer, which achieves high efficiency by discarding unnecessary and redundant tokens.
Ranked #1 on
Video Inpainting
on DAVIS
FreeU: Free Lunch in Diffusion U-Net
ChenyangSi/FreeU
•
•
In this paper, we uncover the untapped potential of diffusion U-Net, which serves as a "free lunch" that substantially improves the generation quality on the fly.
NExT-GPT: Any-to-Any Multimodal LLM
While recently Multimodal Large Language Models (MM-LLMs) have made exciting strides, they mostly fall prey to the limitation of only input-side multimodal understanding, without the ability to produce content in multiple modalities.
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
This shows a failure of logical deduction that we hypothesize is caused by the Reversal Curse.
UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation
A holistic human dataset inevitably has insufficient and low-resolution information on local parts.
