Modern edge Systems-on-Chip (SoCs) integrate heterogeneous processing units (PUs) such as CPUs, GPUs, and NPUs, each with distinct performance and energy characteristics. Deploying AI inference workloads on them under real-time latency and energy constraints requires jointly mapping workloads to PUs and configuring eac...
Aggregating the preferences of diverse user groups into a collective outcome raises fundamental challenges of equity, diversity, and inclusion (EDI): classical aggregation rules such as Borda and Condorcet have no mechanism to prevent results from systematically favoring majority groups, collapsing onto homogeneous ite...
Adji Marieme Sita Ciss\'e, Malek Mouhoub· 0 citations
Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the successor consolidates the update, although pre- and post-update models may retain complementary ranking decisions. We term this \emph{distribute...
Jin-Feng Xu, Zhe-Yu Chen, Zi-Yue Peng et al.· 0 citations
Large transformer-based models increasingly depend on multi-GPU execution, which requires frequent collective communication among GPUs. Existing communication libraries often rely on many GPU threads to achieve high bandwidth or low latency, resulting in a large streaming multiprocessor (SM)-side resource footprint. Th...
Keyvan Dadashzadeh, Yuehong Zhou, Minyu Cui et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Driver fatigue poses a significant challenge to railway safety, with traditional systems like the dead-man switch offering limited and basic alertness checks. This study presents a vision-based monitoring system that relies solely on a single front-facing RGB camera and a graph neural network to classify simulated trai...
Olivia Nocentini, Marta Lagomarsino, Gokhan Solak et al.· 0 citations
An electromagnetic (EM) digital twin gives mobile robots wireless situational awareness but depends on material conductivities that change with the environment. Online calibration faces initialization sensitivity and measurement travel costs. We demonstrate a vision-language model (VLM)-guided framework using a Unitree...
Zerui Kang, Yishen Lim, Zhouyou Gu et al.· 0 citations
Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising platform for processing massively memory intensive matrix-vector multiplications of neural networks in parallel domain, due to its capability of analog computation, ultra-high density, near-zero leakage current, and non-v...
Aniseh Dorostkar, Hamed Farbeh, Hamid R. Zarandi· 0 citations
In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly prompts difficult to learn from these samples alone. Some vision-language methods therefore use manually specified descriptions to supply explicit anomaly semantics. However, constructing these de...
Mengyang Zhao, Teng Fu, Haiyang Yu et al.· 0 citations
Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the poisoned victim alone, the drop cannot separate removal from what the defense does to any model, and inherits the victim's start, which for three of BackdoorBench's sixteen attacks is a configuration file: WaNet, BPP...
Atomistic foundation models triage millions of hypothetical materials but are used as slow simulators, their thresholded energies taken at face value. They are better read as fast decision-makers. CrystalJev queries a frozen interatomic potential once per unrelaxed structure and answers typed questions with calibrated...
Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-source surrogate models are accessible. Existing targeted transfer attacks mainly align adversarial and target samples using global image-level features, such as encoder [CLS...
Xiaojun Jia, Simeng Qin, Yiming Li et al.· 0 citations
Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose heterogeneous capability units, including Tools, MCP servers, and Skills, the carriers of injection multiply, and defenses built to recognize attack patterns fall behind th...
Xinran Zheng, Xin Fan Guo, Zhiqiang Hao et al.· 0 citations
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
