Decentralization and Acceleration Enables Large-Scale Bundle Adjustment

📝
https://github.com/facebookresearch/daba

StructGPT: A General Framework for Large Language Model to Reason over Structured Data

📝
https://github.com/rucaibox/structgpt

SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

📝
https://github.com/0nutation/speechgpt

CodeT5+: Open Code Large Language Models for Code Understanding and Generation

📝
https://github.com/salesforce/codet5

Reflexion: an autonomous agent with dynamic memory and self-reflection

📝
https://github.com/noahshinn024/reflexion

ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

📝
https://github.com/OFA-Sys/ONE-PEACE

Going Denser with Open-Vocabulary Part Segmentation

📝
https://github.com/facebookresearch/vlpart

Sparks of Artificial General Intelligence: Early experiments with GPT-4

📝
https://github.com/microsoft/guidance

FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention

📝
https://github.com/mit-han-lab/fastcomposer

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

📝
https://github.com/opengvlab/visionllm

Official pytorch implementation of "ControlVideo: Training-free Controllable Text-to-Video Generation"

📝
https://github.com/ybybzhang/controlvideo

EasySpider: A No-Code Visual System for Crawling the Web

📝https://github.com/NaiboWang/EasySpider

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

📝https://github.com/kyegomez/tree-of-thoughts

Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

📝https://github.com/shihaozhaozsh/uni-controlnet

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

📝https://github.com/Liuhong99/Sophia

Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models

📝https://github.com/shi-labs/prompt-free-diffusion

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

📝https://github.com/thu-ml/prolificdreamer

Gorilla: Large Language Model Connected with Massive APIs

📝https://github.com/ShishirPatil/gorilla

QLoRA: Efficient Finetuning of Quantized LLMs

📝https://github.com/artidoro/qlora

Large Language Models as Tool Makers

📝Recent research shows the potential of enhancing the problem-solving ability of large language models (LLMs) through the use of external tools. However, prior work along this line depends on the availability of existing tools. In this work, we take an initial step towards removing this dependency by proposing a closed-loop framework, referred to as LLMs A s Tool M akers (LATM), where LLMs create their own reusable tools for problem-solving
https://github.com/ctlllll/llm-toolmaker

Fine-Tuning Language Models with Just Forward Passes

📝Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but as LMs grow in size, backpropagation requires a prohibitively large amount of memory.
https://github.com/princeton-nlp/MeZO