Trending Research
STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model
In this work, we introduce Spatial-Temporal Graph Mamba (STG-Mamba) as the first exploration of leveraging the powerful selective state space models for STG learning by treating STG Network as a system, and employing the Graph Selective State Space Block (GS3B) to precisely characterize the dynamic evolution of STG networks.
Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs
We present a new approach for the approximate K-nearest neighbor search based on navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW).
SATO: Stable Text-to-Motion Framework
sato-team/stable-text-to-motion-framework
•
•
We present a methodology for constructing an SATO that satisfies the stability of attention and prediction.
Rejuvenating image-GPT as Strong Visual Representation Learners
This paper enhances image-GPT (iGPT), one of the pioneering works that introduce autoregressive pretraining to predict next pixels for visual representation learning.
Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference
To tackle the high compute requirements of LLMs, the Mixture-of-Experts (MoE) architecture was introduced which is able to scale its model size without proportionally scaling up its computational requirements.
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
Answering real-world user queries, such as product search, often requires accurate retrieval of information from semi-structured knowledge bases or databases that involve blend of unstructured (e. g., textual descriptions of products) and structured (e. g., entity relations of products) information.
Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent
The search for a general model that can operate seamlessly across multiple domains remains a key goal in machine learning research.
High-Fidelity Audio Compression with Improved RVQGAN
descriptinc/descript-audio-codec
•
•
NeurIPS 2023
Language models have been successfully used to model natural signals, such as images, speech, and music.
VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization
shadow2496/VITON-HD
•
•
CVPR 2021
The task of image-based virtual try-on aims to transfer a target clothing item onto the corresponding region of a person, which is commonly tackled by fitting the item to the desired body part and fusing the warped item with the person.
Ranked #3 on
Virtual Try-on
on VITON-HD
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
stanfordnlp/dsp
•
•
The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks.
