Trending Research
InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions
We study the problem of completing various visual document understanding (VDU) tasks, e. g., question answering and information extraction, on real-world documents through human-written instructions.
Neuro-GPT: Towards A Foundation Model for EEG
To handle the scarcity and heterogeneity of electroencephalography (EEG) data for Brain-Computer Interface (BCI) tasks, and to harness the power of large publicly available data sets, we propose Neuro-GPT, a foundation model consisting of an EEG encoder and a GPT model.
ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
hiyouga/llama-efficient-tuning
•
•
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e. g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.
Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generation
dunni3/flowmol
•
•
In this work, we explore the use of flow matching, a recently proposed generative modeling framework that generalizes diffusion models, for the task of de novo molecule generation.
Trafilatura: A Web Scraping Library and Command-Line Tool for Text Discovery and Extraction
The tool performs significantly better than other open-source solutions in this evaluation and in external benchmarks.
Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging
eth-siplab/ultrainertialposer
•
•
Our method then fuses these inter-sensor distances with the 3D states estimated from each sensor Our graph-based machine learning model processes the 3D states and distances to estimate a person's 3D full body pose and translation.
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
hustvl/vim
•
•
The results demonstrate that Vim is capable of overcoming the computation & memory constraints on performing Transformer-style understanding for high-resolution images and it has great potential to be the next-generation backbone for vision foundation models.
StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control
ironjr/streammultidiffusion
•
•
The enormous success of diffusion models in text-to-image synthesis has made them promising candidates for the next generation of end-user applications for image generation and editing.
ReFT: Representation Finetuning for Language Models
LoReFT is a drop-in replacement for existing PEFTs and learns interventions that are 10x-50x more parameter-efficient than prior state-of-the-art PEFTs.
Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees
atong01/conditional-flow-matching
•
•
Through empirical evaluation across the benchmark, we demonstrate that our approach outperforms deep-learning generation methods in data generation tasks and remains competitive in data imputation.
