Federated learning (FL) enables collaborative model training without sharing raw data but is vulnerable to gradient inversion attacks (GIAs), where adversaries reconstruct private data from shared gradients. Existing defenses either incur impractical computational overhead for embedded platforms or fail to achieve privacy protection and good model utility at the same time. Moreover, many defenses can be easily bypassed by adaptive adversaries who have obtained the defense details. To address these limitations, we propose SVDefense, a novel defense framework against GIAs that leverages the truncated Singular Value Decomposition (SVD) to obfuscate gradient updates. SVDefense introduces three key innovations, a Self-Adaptive Energy Threshold that adapts to client vulnerability, a Channel-Wise Weighted Approximation that selectively preserves essential gradient information for effective model training while enhancing privacy protection, and a Layer-Wise Weighted Aggregation for effective model aggregation under class imbalance. Our extensive evaluation shows that SVDefense outperforms existing defenses across multiple applications, including image classification, human activity recognition, and keyword spotting, by offering robust privacy protection with minimal impact on model accuracy. Furthermore, SVDefense is practical for deployment on various resource-constrained embedded platforms. We will make our code publicly available upon paper acceptance.

We study transformer language models, analyzing attention heads whose attention patterns are spread out, and whose attention scores depend weakly on content. We argue that the softmax denominators of these heads are stable when the underlying token distribution is fixed. By sampling softmax denominators from a "calibration text", we can combine together the outputs of multiple such stable heads in the first layer of GPT2-Small, approximating their combined output by a linear summary of the surrounding text. This approximation enables a procedure where from the weights alone - and a single calibration text - we can uncover hundreds of first layer neurons that respond to high-level contextual properties of the surrounding text, including neurons that didn't activate on the calibration text.

Ensuring the safety of vulnerable road users (VRUs), such as pedestrians and cyclists, remains a critical global challenge, as conventional infrastructure-based measures often prove inadequate in dynamic urban environments. Recent advances in artificial intelligence (AI), particularly in visual perception and reasoning, open new opportunities for proactive and context-aware VRU protection. However, existing surveys on AI applications for VRUs predominantly focus on detection, offering limited coverage of other vision-based tasks that are essential for comprehensive VRU understanding and protection. This paper presents a state-of-the-art review of recent progress in camera-based AI sensing systems for VRU safety, with an emphasis on developments from the past five years and emerging research trends. We systematically examine four core tasks, namely detection and classification, tracking and reidentification, trajectory prediction, and intent recognition and prediction, which together form the backbone of AI-empowered proactive solutions for VRU protection in intelligent transportation systems. To guide future research, we highlight four major open challenges from the perspectives of data, model, and deployment. By linking advances in visual AI with practical considerations for real-world implementation, this survey aims to provide a foundational reference for the development of next-generation sensing systems to enhance VRU safety.

LLMs are emerging tools for simulating human behavior in business, economics, and social science, offering a lower-cost complement to laboratory experiments, field studies, and surveys. This paper evaluates how well LLMs replicate human behavior in operations management. Using nine published experiments in behavioral operations, we assess two criteria: replication of hypothesis-test outcomes and distributional alignment via Wasserstein distance. LLMs reproduce most hypothesis-level effects, capturing key decision biases, but their response distributions diverge from human data, including for strong commercial models. We also test two lightweight interventions -- chain-of-thought prompting and hyperparameter tuning -- which reduce misalignment and can sometimes let smaller or open-source models match or surpass larger systems.

We present VLCAP, an Arabic image captioning framework that integrates CLIP-based visual label retrieval with multimodal text generation. Rather than relying solely on end-to-end captioning, VLCAP grounds generation in interpretable Arabic visual concepts extracted with three multilingual encoders, mCLIP, AraCLIP, and Jina V4, each evaluated separately for label retrieval. A hybrid vocabulary is built from training captions and enriched with about 21K general domain labels translated from the Visual Genome dataset, covering objects, attributes, and scenes. The top-k retrieved labels are transformed into fluent Arabic prompts and passed along with the original image to vision-language models. In the second stage, we tested Qwen-VL and Gemini Pro Vision for caption generation, resulting in six encoder-decoder configurations. The results show that mCLIP + Gemini Pro Vision achieved the best BLEU-1 (5.34%) and cosine similarity (60.01%), while AraCLIP + Qwen-VL obtained the highest LLM-judge score (36.33%). This interpretable pipeline enables culturally coherent and contextually accurate Arabic captions.

Mixture-of-Experts (MoE) models can scale parameter capacity by routing each token to a subset of experts through a learned gate function. While conditional routing reduces training costs, it shifts the burden on inference memory: expert parameters and activations consume memory, limiting the number of experts per device. As tokens are routed, some experts become overloaded while others are underutilized. Because experts are mapped to GPUs, this imbalance translates directly into degraded system performance in terms of latency, throughput, and cost. We present LASER, a plug-and-play, inference-time routing algorithm that balances load while preserving accuracy. LASER adapts to the shape of the gate's score distribution. When scores provide a clear preference, it routes to the strongest experts; when scores are more uniform, it broadens the set of viable experts and routes to the least-loaded among them. Because LASER relies only on gate scores from a trained model, it integrates directly into existing MoE inference pipelines without retraining or finetuning. We evaluate LASER on Mixtral-8x7B and DeepSeek-MoE-16b-chat across four datasets (ARC-Easy, ARC-Challenge, MMLU, and GSM8K). LASER improves load balancing, translating into lower latency and higher throughput, while keeping the accuracy changes negligible.

Within the growing interest in the physical sciences in developing networks with equivariance properties, Clifford neural layers shine as one approach that delivers $E(n)$ and $O(n)$ equivariances given specific group actions. In this paper, we analyze the inner structure of the computation within Clifford convolutional layers and propose and implement several optimizations to speed up the inference process while maintaining correctness. In particular, we begin by analyzing the theoretical foundations of Clifford algebras to eliminate redundant matrix allocations and computations, then systematically apply established optimization techniques to enhance performance further. We report a final average speedup of 21.35x over the baseline implementation of eleven functions and runtimes comparable to and faster than the original PyTorch implementation in six cases. In the remaining cases, we achieve performance in the same order of magnitude as the original library.

Recent advances in browser-based LLM agents have shown promise for automating tasks ranging from simple form filling to hotel booking or online shopping. Current benchmarks measure agent performance in controlled environments, such as containers or stable networks, where websites behave deterministically. However, in the real world, users access websites over networks and HTTPS connections that introduce instability from multiple sources: client-side, server-side issues or broader system failures. Moreover, live websites are prone to web attacks such Cross-Site Scripting, as well as general site modifications which can cause unexpected or malicious pop-ups or improper functionality. Our experiments show that introducing WAREX leads to significant drops in task success rates, highlighting the limited robustness of state-of-the-art agents. W eb agents are leaving the lab and entering the wild, but benchmarks give a false sense of reliability. Web agents have emerged as a promising paradigm for automating complex online tasks, attracting significant attention across academia and industry. Recent advances have produced state-of-the-art web agents with diverse designs, ranging from variations in prompting and observation spaces to reinforcement learning-based action policies. Notable examples include SteP (Sodhi et al., 2024), WebNaviX (Shlomov et al., 2024), Agent Q (Putta et al., 2024), and GUI-Owl (Y e et al., 2025), among a myriad others. Large technology companies have also begun deploying production-grade agents, such as OpenAI (2025); Perplexity (2025) and TinyFish (2025).

This paper proposes Edge-FIT (Federated Instruction Tuning on the Edge), a scalable framework for Federated Instruction Tuning (FIT) of Large Language Models (LLMs). Traditional Federated Learning (TFL) methods, like FedAvg, fail when confronted with the massive parameter size of LLMs [3], [6]. Our Edge-FIT framework combines federated learning with 4-bit Quantized Low-Rank Adaptation (QLORA), mitigating the core issues of communication and computational overhead. We demonstrate this by filtering the general-purpose Databricks Dolly 15k dataset for the IoT domain. Experimental results show the Edge-FIT tuned Llama 2(7B) achieves an F1-Score of 0.89. We also demonstrate a viable trade-off using the 3.8B Phi-3-mini model, validating Edge-FIT as a scalable framework for decentralized LLM deployment on home compute gateways.

Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data necessitates frequent retraining, which introduces a fundamental tension between inference latency and model accuracy under constrained GPU resources. Existing retraining strategies either delay model updates, over-commit resources to retraining, or overlook iteration-level retraining granularity. In this paper, we identify that iteration-level scheduling is crucial for adapting retraining frequency to model drift without violating service-level objectives (SLOs). We propose MACE, a hybrid LLM system that colocates concurrent inference (prefill, decode) and fine-tuning, with intelligent memory management to maximize task performance while promising inference throughput. MACE leverages the insight that not all model updates equally affect output alignment and allocates GPU cycles accordingly to balance throughput, latency, and update freshness. Our trace-driven evaluation shows that MACE matches or exceeds continuous retraining while reducing inference latency by up to 63% and maintaining throughput under resource constraints. Compared to periodic retraining, MACE improves latency breakdown across prefill, decode, and finetune stages, and sustains GPU utilization above 85% in NVIDIA AGX Orin. These results demonstrate that iteration-level hybrid scheduling is a promising direction for deploying LLMs with continual learning capabilities on edge platforms.