· software
Fine-tuning vision-language models on memory-constrained devices
A new hybrid optimization approach allows edge devices to fine-tune vision-language models using only forward passes, achieving up to 7% higher accuracy than ex...
-
- · devops
[Paper] Asynchronous Secure Federated Learning with Byzantine aggregators
Privacy-preserving federated averaging is a central approach for protecting client privacy in federated learning. In this paper, we study this problem in an asy...
- · software
[Paper] AVX / NEON Intrinsic Functions: When Should They Be Used?
A cross-configuration benchmark is proposed to explore the capacities and limitations of AVX / NEON intrinsic functions in a generic context of development proj...
- · devops
[Paper] Parallel Quadratic Selected Inversion in Quantum Transport Simulation
Driven by Moore's Law, the dimensions of transistors have been pushed down to the nanometer scale. Advanced quantum transport (QT) solvers are required to accur...
- · ai
[Paper] Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests
Pull request (PR) descriptions generated by AI coding agents are the primary channel for communicating code changes to human reviewers. However, the alignment b...
- · software
[Paper] A Longitudinal Analysis of Gamification in Untappd: Ethical Reflections on a Social Drinking Application
This paper presents a longitudinal ethical analysis of Untappd, a social drinking application that gamifies beer consumption through badges, streaks, and social...
- · devops
[Paper] Proof of Commitment: A Human-Centric Resource for Permissionless Consensus
Permissionless consensus protocols require a scarce resource to regulate leader election and provide Sybil resistance. Existing paradigms such as Proof of Work ...
- · ai
[Paper] Neural-Symbolic Integration with Evolvable Policies
Neural-Symbolic (NeSy) Artificial Intelligence has emerged as a promising approach for combining the learning capabilities of neural networks with the interpret...
- · devops
[Paper] Cognitive Infrastructure: A Unified DCIM Framework for AI Data Centers
This work presents DCIM 3.0, a unified framework integrating semantic reasoning, predictive analytics, autonomous orchestration, and unified connectivity for ne...
- · ai
[Paper] Training a Custom CNN on Five Heterogeneous Image Datasets
Deep learning has transformed visual data analysis, with Convolutional Neural Networks (CNNs) becoming highly effective in learning meaningful feature represent...
- · ai
[Paper] MoEBlaze: Breaking the Memory Wall for Efficient MoE Training on Modern GPUs
The pervasive 'memory wall' bottleneck is significantly amplified in modern large-scale Mixture-of-Experts (MoE) architectures. MoE's inherent architectural spa...
- · ai
[Paper] MQ-GNN: A Multi-Queue Pipelined Architecture for Scalable and Efficient GNN Training
Graph Neural Networks (GNNs) are powerful tools for learning graph-structured data, but their scalability is hindered by inefficient mini-batch generation, data...