· ai
[Paper] Morphling: Fast, Fused, and Flexible GNN Training at Scale
Graph Neural Networks (GNNs) present a fundamental hardware challenge by fusing irregular, memory-bound graph traversals with regular, compute-intensive dense m...
-
- · ai
[Paper] In-context Inverse Optimality for Fair Digital Twins: A Preference-based approach
Digital Twins (DTs) are increasingly used as autonomous decision-makers in complex socio-technical systems. Their mathematically optimal decisions often diverge...
- · ai
[Paper] Parallel Delayed Memory Units for Enhanced Temporal Modeling in Biomedical and Bioacoustic Signal Analysis
Advanced deep learning architectures, particularly recurrent neural networks (RNNs), have been widely applied in audio, bioacoustic, and biomedical signal analy...
- · ai
[Paper] Delta Sum Learning: an approach for fast and global convergence in Gossip Learning
Federated Learning is a popular approach for distributed learning due to its security and computational benefits. With the advent of powerful devices in the net...
- · ai
[Paper] Teaching an Online Multi-Institutional Research Level Software Engineering Course with Industry - an Experience Report
Covid has made online teaching and learning acceptable and students, faculty, and industry professionals are all comfortable with this mode. This comfort can be...
- · ai
[Paper] MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification
We present Conformer-based decoders for the LibriBrain 2025 PNPL competition, targeting two foundational MEG tasks: Speech Detection and Phoneme Classification....
- · ai
[Paper] BackportBench: A Multilingual Benchmark for Automated Backporting of Patches
Many modern software projects evolve rapidly to incorporate new features and security patches. It is important for users to update their dependencies to safer v...
- · ai
[Paper] Tangram: Accelerating Serverless LLM Loading through GPU Memory Reuse and Affinity
Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through ...
- · ai
[Paper] Pascal-Weighted Genetic Algorithms: A Binomially-Structured Recombination Framework
This paper introduces a new family of multi-parent recombination operators for Genetic Algorithms (GAs), based on normalized Pascal (binomial) coefficients. Unl...
- · ai
[Paper] The Evolution of Learning Algorithms for Artificial Neural Networks
In this paper we investigate a neural network model in which weights between computational nodes are modified according to a local learning rule. To determine w...
- · ai
[Paper] Testing the Machine Consciousness Hypothesis
The Machine Consciousness Hypothesis states that consciousness is a substrate-free functional property of computational systems capable of second-order percepti...
- · ai
[Paper] Joint Partitioning and Placement of Foundation Models for Real-Time Edge AI
Inference over large-scale foundation models within heterogeneous edge environments necessitates a fundamentally reconfigurable orchestration substrate. Static ...