Social-Transmotion: Promptable Human Trajectory Prediction

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Laser material processing (LMP) has revolutionized modern manufacturing, emerging as a cornerstone technology valued for its precision, speed, and versatility, especially in high-stakes sectors like aerospace, automotive, and medical device production. Des ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Our understanding of the generalization capabilities of neural networks (NNs) is still incomplete. Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from gradient-free metho ...

Macroscopic fundamental diagrams (MFDs) have been widely adopted to model the traffic flow of large-scale urban networks. Coupling perimeter control and regional route guidance (PCRG) is a promising strategy to decrease congestion heterogeneity and reduce ...

Generative language models (LMs) have become omnipresent across data science. For a wide variety of tasks, inputs can be phrased as natural language prompts for an LM, from whose output the solution can then be extracted. LM performance has consistently be ...

The ongoing electrification of the transportation fleet will increase the load on the electric power grid. Since both the transportation network and the power grid already experience periods of significant stress, joint analyses of both infrastructures wil ...

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

The increasing complexity of transformer models in artificial intelligence expands their computational costs, memory usage, and energy consumption. Hardware acceleration tackles the ensuing challenges by designing processors and accelerators tailored for t ...

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimen ...

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

Beliefs inform the behaviour of forward-thinking agents in complex environments. Recently, sequential Bayesian inference has emerged as a mechanism to study belief formation among agents adapting to dynamical conditions. However, we lack critical theory to ...

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast vi ...

Recent transformer language models achieve outstanding results in many natural language processing (NLP) tasks. However, their enormous size often makes them impractical on memory-constrained devices, requiring practitioners to compress them to smaller net ...

We propose a novel system leveraging deep learning-based methods to predict urban traffic accidents and estimate their severity. The major challenge is the data imbalance problem in traffic accident prediction. The problem is caused by numerous zero values ...

Microscopic traffic flow models can be distinguished in lane-based or lane-free depending on the degree of lane-discipline. This distinction holds true only if motorcycles are neglected in lane-based traffic. In cities, as opposed to highways, this is an o ...

Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

Ridesourcing has driven a lot of attention in recent years with the expansion of companies like Uber, Lift, and many others around the world. Companies use mobile applications connected through the internet to match drivers and their passengers real-time. ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

Social-Transmotion: Promptable Human Trajectory Prediction

Chat with Graph Search

Toward Autonomous Laser Manufacturing: Solving Key Challenges in Optimization, Monitoring, and Control

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Neural Redshift: Random Networks are not Random Functions

An Iterative Adaptive Dynamic Programming Approach for Macroscopic Fundamental Diagram-Based Perimeter Control and Route Guidance

Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling

GreenEVT: Greensboro Electric Vehicle Testbed

Driving and suppressing the human language network using large language models

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

The multimodality cell segmentation challenge: toward universal solutions

Augmenting large language models with chemistry tools

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Stochastic pairwise preference convergence in Bayesian agents

SoccerNet 2023 challenges results

Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models

From Prediction to Prevention: Leveraging Deep Learning in Traffic Accident Prediction Systems

A hybrid microscopic model for multimodal traffic with empirical observations from aerial footage

Modeling Structured Data in Attention-based Models

Improving Generalization of Pretrained Language Models

Modeling and Optimization of Ridesplitting Operations

Transformer Models for Vision