Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles

📖Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance.

https://github.com/facebookresearch/hiera

StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation

📖The recent advancements in image-text diffusion models have stimulated research interest in large-scale 3D generative models.

https://github.com/icoz69/styleavatar3d

Humans in 4D: Reconstructing and Tracking Humans with Transformers

📖To analyze video, we use 3D reconstructions from HMR 2. 0 as input to a tracking system that operates in 3D.
https://github.com/shubham-goel/4D-Humans

📝DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement

https://github.com/rikorose/deepfilternet

📝SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

https://github.com/vahe1994/spqr

📝Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding


https://github.com/damo-nlp-sg/video-llama

📝Segment Anything in High Quality

https://github.com/syscv/sam-hq

Simple and Controllable Music Generation

📝We tackle the task of conditional music generation.

https://github.com/facebookresearch/audiocraft

AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities

📝In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model.

https://github.com/flagai-open/flagai

📝Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation.


https://github.com/mbzuai-oryx/video-chatgpt

🦦 📝Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.


https://github.com/luodian/otter

📝Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance


https://github.com/franxyao/chain-of-thought-hub

FinGPT: Open-Source Financial Large Language Models

📝https://github.com/ai4finance-foundation/fingpt

SqueezeLLM: Dense-and-Sparse Quantization

📝https://github.com/squeezeailab/squeezellm

MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing

📝https://github.com/osu-nlp-group/magicbrush

ChemCrow: Augmenting large-language models with chemistry tools

📝https://github.com/ur-whitelab/chemcrow-public

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

📝https://github.com/nlpxucan/wizardlm

h2oGPT: Democratizing Large Language Models

📝https://github.com/h2oai/h2ogpt

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

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

Full Parameter Fine-tuning for Large Language Models with Limited Resources

📝https://github.com/openlmlab/lomo