Search Results for author:
Found 10 papers, 7 papers with code
Laying Anchors: Semantically Priming Numerals in Language Modeling
Off-the-shelf pre-trained language models have become the de facto standard in NLP pipelines for a multitude of downstream tasks.
Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image Segmentation
On the real-world task of battery material phase segmentation, PaSeR yields a minimum performance improvement of 174% on the IoU/GigaFlop metric with respect to baselines.
Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems
Diverging from NLP-based foundation models, the proposed framework promotes the design of large multi-modal models (LMMs) fostered by three key capabilities: 1) processing of multi-modal sensing data, 2) grounding of physical symbol representations in real-world wireless systems using causal reasoning and retrieval-augmented generation (RAG), and 3) enabling instructibility from the wireless environment feedback to facilitate dynamic network adaptation thanks to logical and mathematical reasoning facilitated by neuro-symbolic AI.
Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency
The field of Math-NLP has witnessed significant growth in recent years, motivated by the desire to expand LLM performance to the learning of non-linguistic notions (numerals, and subsequently, arithmetic reasoning).
Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic
Through their transfer learning abilities, highly-parameterized large pre-trained language models have dominated the NLP landscape for a multitude of downstream language tasks.
Detecting Irregular Network Activity with Adversarial Learning and Expert Feedback
Specifically, CAAD employs contrastive learning in an adversarial setup to learn effective representations of normal and anomalous behavior in wireless networks.
Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores
The availability of wide-ranging third-party intellectual property (3PIP) cores enables integrated circuit (IC) designers to focus on designing high-level features in ASICs/SoCs.
Using AntiPatterns to avoid MLOps Mistakes
We describe lessons learned from developing and deploying machine learning models at scale across the enterprise in a range of financial analytics applications.
Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19
Our experiments demonstrate that our approach is successful in adapting a historical forecasting model to the current pandemic.
Physics-guided Design and Learning of Neural Networks for Predicting Drag Force on Particle Suspensions in Moving Fluids
In such situations, it is often useful to rely on machine learning methods to fill in the gap by learning a model of the complex physical process directly from simulation data.
