A structured narrative review of the latest breakthroughs achieved in the development of energy-efficient Edge AI, focusing specifically on hardware-software co-design practices aimed at improving inference quality, demonstrates that hardware-aware model optimization and heterogeneous computing significantly improve pe...
V. Govindaraj, Muthu Krishnammal P, S. S. Devi et al.· Discover Computing· 0 citations
A lightweight object-detection system based on the Jetson Nano that uses lower-resolution input, TensorRT operator fusion, and FP16 half-precision quantization to overcome the trade-off between constrained on-board computation of edge devices like AGVs in smart warehousing and logistics and the high real-time demands o...
Jun-Lin He, Wen-Bo Peng, Hong-Bo Zhou et al.· International Conference on...· 0 citations
The widespread deployment of ultra-distributed computing infrastructure and the adoption of the edge-cloud continuum architecture create an ever-increasing need for spectrum access. Database-driven cognitive radio networks (DB-CRNs) are a promising avenue to addressing spectrum scarcity in the wireless access domain. S...
Saleh Darzi, Gokcan Cantali, Dina Abdelhadi et al.· Proceedings of the 21st Work...· 0 citations
This work recovers DU-side scheduling behavior and radio-side execution, including the per-beam and per-layer beamforming weights carried on the C-plane, separating measured quantities from those conditioned on an array hypothesis, and ground an eleven-agent platform in which a language model only interprets measuremen...
Sridhar Rajagopal, Eran Pisek, Gabriele Gemmi et al.· Proceedings of the 3rd ACM W...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
ElasticScale is presented, an elastic orchestration system that organizes heterogeneous accelerators into disaggregated rollout and trainer instances, via a HeterogeneousRayWorkerGroup abstraction that manages non-uniform hardware topologies and a multi-instance Federated Weight Averaging protocol that aggregates updat...
Wei-An Lin, M. Reza, Talha Nayyar et al.· 0 citations
The rapid proliferation of Generative AI (GenAI) has catalyzed the emergence of autonomous agentic AI services, spanning large language model (LLM) or vision-language model (VLM) based digital agents to vision-language-action (VLA) based embodied intelligence. Consequently, tokens and multimodal data streams have emerg...
Cheng-Xiang Mi, Ce Wang, Kai Zhang et al.· 0 citations
The strong universality conjecture of Bobrowski and Skraba asserts that, under a prescribed data-dependent additive centering, the empirical laws of log-log transformed persistence ratios of random geometric complexes share a universal limit across sampling models, dimensions, filtrations, and homological degrees. They...
An approach that separates geometric visibility preprocessing from a portfolio of incremental combinatorial searches is described, complemented by exact discrete one-swap descent, ruin-and-recreate, and elite crossover.
Quantizer-Aligned Recalibration (QuAR), a single-pass TTA method tailored to quantized ViTs that neither backpropagates nor updates any model parameters is proposed, which achieves the highest mean accuracy among state-of-the-art backpropagates nor updates any model parameters.
Hyeong-Tae Cha, Young D. Kwon, Sung-Ju Lee· 0 citations
Structural magnetic resonance imaging reveals lateral ventricular enlargement as a prominent structural change in normal aging, with accelerated expansion in Alzheimer's disease and related dementias. In this study, we characterize ventricular shape changes and corresponding mechanical loading in cognitively normal (CN...
Lauren Cunniff, Johannes Weickenmeier· Brain Research Bulletin· 0 citations
Previous studies on proximal segment accuracy after bilateral sagittal split ramus osteotomy have mainly focused on condylar position. This retrospective cohort study evaluated landmark-specific and direction-sensitive proximal segment discrepancies relative to the virtual surgical plan in 108 skeletal Class III patien...
Kyung Lok Do, Soo-A Do, Ui Hyun Kong et al.· Journal of cranio-maxillo-fa...· 0 citations
Artificial synaptic devices capable of integrating sensing, memory, and computing functions are highly desirable for next-generation neuromorphic systems. However, most reported artificial synapses rely on single-mode electrical or optical stimulation, limiting their ability to achieve multimodal perception and adaptiv...
Di Wang, Wen-Juan Ma, Yu-Yuan Lai et al.· Nanoscale· 0 citations
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 2, 2026
