Search Results for author:
Found 7 papers, 3 papers with code
A Concept-Centric Approach to Multi-Modality Learning
In an effort to create a more efficient AI system, we introduce a new multi-modality learning framework that leverages a modality-agnostic concept space possessing abstract knowledge and a set of modality-specific projection models tailored to process distinct modality inputs and map them onto the concept space.
Optimizing queues with deadlines under infrequent monitoring
In this paper, we aim to improve the percentage of packets meeting their deadline in discrete-time M/M/1 queues with infrequent monitoring.
StarCoder 2 and The Stack v2: The Next Generation
Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size.
Ranked #35 on
Code Generation
on MBPP
Optimal Compression for Minimizing Classification Error Probability: an Information-Theoretic Approach
We then provide analytical and computational methods to characterize the optimal trade-off between data compression and classification error probability.
Task-Aware Network Coding Over Butterfly Network
Classical network coding is largely task-agnostic -- the coding schemes mainly aim to faithfully reconstruct data at the receivers, regardless of what ultimate task the received data is used for.
Task-aware Privacy Preservation for Multi-dimensional Data
Local differential privacy (LDP) can be adopted to anonymize richer user data attributes that will be input to sophisticated machine learning (ML) tasks.
Data Sharing and Compression for Cooperative Networked Control
Sharing forecasts of network timeseries data, such as cellular or electricity load patterns, can improve independent control applications ranging from traffic scheduling to power generation.
