NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images

📝We present a neural rendering-based method called NeRO for reconstructing the geometry and the BRDF of reflective objects from multiview images captured in an unknown environment.
https://github.com/liuyuan-pal/NeRO

SoundStorm: Efficient Parallel Audio Generation

📝We present SoundStorm, a model for efficient, non-autoregressive audio generation.
https://github.com/rishikksh20/SoundStorm-pytorch

CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

📖In this paper, we present CodeTF, an open-source Transformer-based library for state-of-the-art Code LLMs and code intelligence.

https://github.com/salesforce/codetf

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

📖Large language models (LLMs) have shown excellent performance on various tasks, but the astronomical model size raises the hardware barrier for serving (memory size) and slows down token generation (memory bandwidth).

https://github.com/mit-han-lab/llm-awq

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