MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

buaacyw/meshanything 14 Jun 2024

Recently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement.

Decoder

290
5.09 stars / hour

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

trotsky1997/mathblackbox 11 Jun 2024

This paper introduces the MCT Self-Refine (MCTSr) algorithm, an innovative integration of Large Language Models (LLMs) with Monte Carlo Tree Search (MCTS), designed to enhance performance in complex mathematical reasoning tasks.

Decision Making GSM8K +2

231
2.35 stars / hour

TextGrad: Automatic "Differentiation" via Text

zou-group/textgrad 11 Jun 2024

Without modifying the framework, TextGrad improves the zero-shot accuracy of GPT-4o in Google-Proof Question Answering from $51\%$ to $55\%$, yields $20\%$ relative performance gain in optimizing LeetCode-Hard coding problem solutions, improves prompts for reasoning, designs new druglike small molecules with desirable in silico binding, and designs radiation oncology treatment plans with high specificity.

 Ranked #1 on on GPQA

Question Answering Specificity

403
2.04 stars / hour

Scalable MatMul-free Language Modeling

ridgerchu/matmulfreellm 4 Jun 2024

Our experiments show that our proposed MatMul-free models achieve performance on-par with state-of-the-art Transformers that require far more memory during inference at a scale up to at least 2. 7B parameters.

Language Modelling

2,104
1.98 stars / hour

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

damo-nlp-sg/videollama2 11 Jun 2024

In this paper, we present the VideoLLaMA 2, a set of Video Large Language Models (Video-LLMs) designed to enhance spatial-temporal modeling and audio understanding in video and audio-oriented tasks.

Multiple-choice Question Answering +3

276
1.50 stars / hour

Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

microsoft/Samba 11 Jun 2024

When trained on 4K length sequences, Samba can be efficiently extrapolated to 256K context length with perfect memory recall and show improved token predictions up to 1M context length.

4k Language Modelling

519
1.37 stars / hour

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

foundationvision/llamagen 10 Jun 2024

(3) A text-conditional image generation model with 775M parameters, from two-stage training on LAION-COCO and high aesthetics quality images, demonstrating competitive performance of visual quality and text alignment.

Conditional Image Generation

728
1.02 stars / hour

OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation

foundationvision/omnitokenizer 13 Jun 2024

To exploit the complementary nature of image and video data, we further propose a progressive training strategy, where OmniTokenizer is first trained on image data on a fixed resolution to develop the spatial encoding capacity and then jointly trained on image and video data on multiple resolutions to learn the temporal dynamics.

Language Modelling

97
1.02 stars / hour

X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design

ericlbuehler/mistral.rs 11 Feb 2024

Starting with a set of pre-trained LoRA adapters, our gating strategy uses the hidden states to dynamically mix adapted layers, allowing the resulting X-LoRA model to draw upon different capabilities and create never-before-used deep layer-wise combinations to solve tasks.

graph construction Knowledge Graphs +2

2,601
0.99 stars / hour

Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers

alpha-vllm/lumina-t2x 9 May 2024

Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details.

1,624
0.84 stars / hour