Work Force

MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation

Generating high-fidelity 3D content from text prompts remains a significant challenge in computer vision due to the limited size, diversity, and annotation depth of the existing datasets. To address this, we introduce MARVEL-40M+, an extensive dataset with 40 million text annotations for over 8.9 million 3D assets aggregated from seven major 3D datasets. Our contribution is a novel multi-stage a...

Spines and Inclines: Bioinspired Spines on an Insect-Scale Robot Facilitate Locomotion on Rough and Inclined Terrain.

To navigate complex terrains, insects use diverse tarsal structures (adhesive pads, claws, spines) to reliably attach to and locomote across substrates. This includes surfaces of variable roughness and inclination, which often require reliable transitions from ambulatory to scansorial locomotion. Using bioinspired physical models as a means for comparative research, our study specifically focused ...

Trojan Cleansing with Neural Collapse

Trojan attacks are sophisticated training-time attacks on neural networks that embed backdoor triggers which force the network to produce a specific...

ADV2E: Bridging the Gap Between Analogue Circuit and Discrete Frames in the Video-to-Events Simulator

Event cameras operate fundamentally differently from traditional Active Pixel Sensor (APS) cameras, offering significant advantages. Recent research...

Machine learning-enabled computer vision for plant phenotyping: a primer on AI/ML and a case study on stomatal patterning.

Artificial intelligence and machine learning (AI/ML) can be used to automatically analyze large image datasets. One valuable application of this appro...

A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL

To tackle the challenges of large language model performance in natural language to SQL tasks, we introduce XiYan-SQL, an innovative framework that ...

Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach

Back propagation (BP) is the default solution for gradient computation in neural network training. However, implementing BP-based training on variou...

Conditional Vendi Score: An Information-Theoretic Approach to Diversity Evaluation of Prompt-based Generative Models

Text-conditioned generation models are commonly evaluated based on the quality of the generated data and its alignment with the input text prompt. O...

[HIPPOCRATES AND LANGUAGE MODELS - PRIMUM NON NOCERE - FIRST, DO NO HARM].

For millennia, the ethos of "First, Do No Harm", attributed to Hippocrates, has been a cornerstone of medicine. This principle emphasizes the responsi...

RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models

The development of large language models (LLMs) has significantly enhanced the capabilities of multimodal LLMs (MLLMs) as general assistants. Howeve...

Xeno-learning: knowledge transfer across species in deep learning-based spectral image analysis

Novel optical imaging techniques, such as hyperspectral imaging (HSI) combined with machine learning-based (ML) analysis, have the potential to revo...

Personas with Attitudes: Controlling LLMs for Diverse Data Annotation

We present a novel approach for enhancing diversity and control in data annotation tasks by personalizing large language models (LLMs). We investiga...

Diversity-Aware Reinforcement Learning for de novo Drug Design

Fine-tuning a pre-trained generative model has demonstrated good performance in generating promising drug molecules. The fine-tuning task is often f...

IMAS: A Comprehensive Agentic Approach to Rural Healthcare Delivery

Since the onset of COVID-19, rural communities worldwide have faced significant challenges in accessing healthcare due to the migration of experienc...

A GEN AI Framework for Medical Note Generation

The increasing administrative burden of medical documentation, particularly through Electronic Health Records (EHR), significantly reduces the time ...

Precision DNA methylation typing via hierarchical clustering of Nanopore current signals and attention-based neural network.

Decoding DNA methylation sites through nanopore sequencing has emerged as a cutting-edge technology in the field of DNA methylation research, as it en...

DFDG: Data-Free Dual-Generator Adversarial Distillation for One-Shot Federated Learning

Federated Learning (FL) is a distributed machine learning scheme in which clients jointly participate in the collaborative training of a global mode...

Large language models and generative AI in telehealth: a responsible use lens.

OBJECTIVE: This scoping review aims to assess the current research landscape of the application and use of large language models (LLMs) and generative...

Method for remaining useful life prediction of rolling bearings based on deep reinforcement learning.

In contemporary industrial systems, the prediction of remaining useful life (RUL) is recognized as a valuable maintenance strategy for health manageme...

Toward Large Language Models as a Therapeutic Tool: Comparing Prompting Techniques to Improve GPT-Delivered Problem-Solving Therapy

While Large Language Models (LLMs) are being quickly adapted to many domains, including healthcare, their strengths and pitfalls remain under-explor...