Deep Learning
Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation Jiawei Wang
This paper introduces a novel approach using Large Language Models (LLMs) integrated into an agent framework for flexible and effective personal mobility generation. LLMs overcome the limitations of previous models by effectively processing semantic data and offering versatility in modeling various tasks.
Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking
Significant progress has been made in the past decade thanks to the availability of pedestrian trajectory datasets, which enable trajectory prediction methods to learn from pedestrians' past movements and predict future trajectories.
diversity of artistic styles make it impractical to compile comprehensive datasets
Firstly, obtaining a large dataset of high-quality stylized images is difficult.
FairWire: Fair Graph Generation
The volume of graph-structured data has been explosively growing due to the advancement in interconnected systems.
Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers Lirui Wang 1 Xinlei Chen
One of the roadblocks for training generalist robotic models today is heterogeneity.
Moving Off-the-Grid: Scene-Grounded Video Representations
Current vision models typically maintain a fixed correspondence between their representation structure and image space. Each layer comprises a set of tokens arranged "on-the-grid," which biases patches or tokens to encode information at
SimPO: Simple Preference Optimization with a Reference-Free Reward Y u Meng
Additionally, we introduce a target reward margin to the Bradley-Terry objective to encourage a larger margin between the winning and losing responses, further improving the algorithm's performance.
Crafting Interpretable Embeddings for Language Neuroscience by Asking LLMs Questions
Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks.