Time series forecasting is vital in domains where data sensitivity is paramount, such as finance and energy systems. While Differential Privacy (DP) provides theoretical guarantees to protect individual data contributions, its integration especially via DP-SGD often impairs model performance due to injected noise. In this paper, we propose Q-DPTS, a hybrid quantum-classical framework for Quantum Differentially Private Time Series Forecasting. Q-DPTS combines Variational Quantum Circuits (VQCs) with per-sample gradient clipping and Gaussian noise injection, ensuring rigorous $(ε, δ)$-differential privacy. The expressiveness of quantum models enables improved robustness against the utility loss induced by DP mechanisms. We evaluate Q-DPTS on the ETT (Electricity Transformer Temperature) dataset, a standard benchmark for long-term time series forecasting. Our approach is compared against both classical and quantum baselines, including LSTM, QASA, QRWKV, and QLSTM. Results demonstrate that Q-DPTS consistently achieves lower prediction error under the same privacy budget, indicating a favorable privacy-utility trade-off. This work presents one of the first explorations into quantum-enhanced differentially private forecasting, offering promising directions for secure and accurate time series modeling in privacy-critical scenarios.

In this study, we evaluate the performance of classical and quantum-inspired sequential models in forecasting univariate time series of incoming SMS activity (SMS-in) using the Milan Telecommunication Activity Dataset. Due to data completeness limitations, we focus exclusively on the SMS-in signal for each spatial grid cell. We compare five models, LSTM (baseline), Quantum LSTM (QLSTM), Quantum Adaptive Self-Attention (QASA), Quantum Receptance Weighted Key-Value (QRWKV), and Quantum Fast Weight Programmers (QFWP), under varying input sequence lengths (4, 8, 12, 16, 32 and 64). All models are trained to predict the next 10-minute SMS-in value based solely on historical values within a given sequence window. Our findings indicate that different models exhibit varying sensitivities to sequence length, suggesting that quantum enhancements are not universally advantageous. Rather, the effectiveness of quantum modules is highly dependent on the specific task and architectural design, reflecting inherent trade-offs among model size, parameterization strategies, and temporal modeling capabilities.

Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with adversarial multimodal inputs. To improve the safety of MLLMs during inference, we introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model. AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected. Experiments on LLaVA-OV and Chameleon across diverse safety-critical benchmarks demonstrate that AutoSteer significantly reduces the Attack Success Rate (ASR) for textual, visual, and cross-modal threats, while maintaining general abilities. These findings position AutoSteer as a practical, interpretable, and effective framework for safer deployment of multimodal AI systems.

Quantum circuits must be error-resilient, yet LLMs like Granite-20B-Code and StarCoder often output flawed Qiskit code. We fine-tuned the Qwen2.5-Coder-32B model with two RL methods, Group Relative Policy Optimization (GRPO) and Odds-Ratio Preference Optimization (ORPO), using a richly annotated synthetic dataset. On the Qiskit HumanEval benchmark, ORPO reaches 56.29% Pass@1 ($\approx+10$ pp over Granite-8B-QK) and GRPO hits 49%, both beating all general-purpose baselines; on the original HumanEval they score 65.90% and 63.00%. GRPO performs well on basic tasks (44/78) and excels on intermediate ones (41/68), but neither GRPO nor ORPO solves any of the five advanced tasks, highlighting clear gains yet room for progress in AI-assisted quantum programming.

Abstract--Software systems usually provide numerous configuration options that can affect performance metrics such as execution time, memory usage, binary size, or bitrate. On the one hand, making informed decisions is challenging and requires domain expertise in options and their combinations. On the other hand, machine learning techniques can search vast configuration spaces, but with a high computational cost, since concrete executions of numerous configurations are required. In this exploratory study, we investigate whether large language models (LLMs) can assist in performance-oriented software configuration through prompts. We evaluate several LLMs on tasks including identifying relevant options, ranking configurations, and recommending performant configurations across various configurable systems, such as compilers, video encoders, and SA T solvers. Our preliminary results reveal both positive abilities and notable limitations: depending on the task and systems, LLMs can well align with expert knowledge, whereas hallucinations or superficial reasoning can emerge in other cases. These findings represent a first step toward systematic evaluations and the design of LLM-based solutions to assist with software configuration. Modern software systems (e.g., compilers, databases, ML pipelines) expose many configuration options impacting performance trade-offs like latency or memory usage. Identifying performant configurations and key options is challenging due to combinatorial configuration spaces and complex, non-linear interactions, making analytical reasoning impractical [1]. ML-based approaches [2]-[6], especially predictive models [7], [8], assist in configuration but require empirical performance data.

Deploying deep neural networks (DNNs) on resource-constrained mobile devices presents significant challenges, particularly in achieving real-time performance while simultaneously coping with limited computational resources and battery life. While Mobile Edge Computing (MEC) offers collaborative inference with GPU servers as a promising solution, existing approaches primarily rely on layer-wise model partitioning and undergo significant transmission bottlenecks caused by the sequential execution of DNN operations. To address this challenge, we present Intra-DP, a high-performance collaborative inference system optimized for DNN inference on MEC. Intra DP employs a novel parallel computing technique based on local operators (i.e., operators whose minimum unit input is not the entire input tensor, such as the convolution kernel). By decomposing their computations (operations) into several independent sub-operations and overlapping the computation and transmission of different sub-operations through parallel execution, Intra-DP mitigates transmission bottlenecks in MEC, achieving fast and energy-efficient inference. The evaluation demonstrates that Intra-DP reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines, without sacrificing accuracy.

We present a data-domain sampling regime for quantifying CNNs' graphic perception behaviors. This regime lets us evaluate CNNs' ratio estimation ability in bar charts from three perspectives: sensitivity to training-test distribution discrepancies, stability to limited samples, and relative expertise to human observers. After analyzing 16 million trials from 800 CNNs models and 6,825 trials from 113 human participants, we arrived at a simple and actionable conclusion: CNNs can outperform humans and their biases simply depend on the training-test distance. We show evidence of this simple, elegant behavior of the machines when they interpret visualization images. osf.io/gfqc3 provides registration, the code for our sampling regime, and experimental results.

Trajectory planning in robotics is understood as generating a sequence of joint configurations that will lead a robotic agent, or its manipulator, from an initial state to the desired final state, thus completing a manipulation task while considering constraints like robot kinematics and the environment. Typically, this is achieved via sampling-based planners, which are computationally intensive. Recent advances demonstrate that trajectory planning can also be performed by supervised sequence learning of trajectories, often requiring only a single or fixed number of passes through a neural architecture, thus ensuring a bounded computation time. Such fully supervised approaches, however, perform imitation learning; they do not learn based on whether the trajectories can successfully reach a goal, but try to reproduce observed trajectories. In our work, we build on this approach and propose a cognitively inspired self-supervised learning scheme based on a recurrent architecture for building a trajectory model. We evaluate the feasibility of the proposed method on a task of kinematic planning for a robotic arm. The results suggest that the model is able to learn to generate trajectories only using given paired forward and inverse kinematics models, and indicate that this novel method could facilitate planning for more complex manipulation tasks requiring adaptive solutions.

A common assumption in probabilistic generative models for image generation is that learning the global data distribution suffices to generate novel images via sampling. We investigate the limitation of this core assumption, namely that learning global distributions leads to memorization rather than generative behavior. We propose two theoretical frameworks, the Mutually Exclusive Probability Space (MEPS) and the Local Dependence Hypothesis (LDH), for investigation. MEPS arises from the observation that deterministic mappings (e.g. We further propose a lower bound in terms of the overlap coefficient, and introduce a Binary Latent Autoencoder (BL-AE) that encodes images into signed binary latent representations. LDH formalizes dependence within a finite observation radius, which motivates our γ- Autoregressive Random V ariable Model (γ-ARVM). Using γ-ARVM, we observe that as the observation range increases, autoregressive models progressively shift toward memorization. In the limit of global dependence, the model behaves as a pure memorizer when operating on the binary latents produced by our BL-AE. Comprehensive experiments and discussions support our investigation. Figure 1: Selecting images for values in the overlap range is ambiguous. Probabilistic generative models such as V aria-tional Autoencoders (V AEs), Generative Adversarial Networks (GANs), diffusion models, and autoregressive models have achieved remarkable progress in image generation. A core assumption is that these models learn an image distribution from which new images can be generated via sampling (Bond-Taylor et al., 2022). Specifically, we focus on au-toregressive models. For this investigation, we introduce two theoretical frameworks.

The integration of external knowledge through Retrieval-Augmented Generation (RAG) has become foundational in enhancing large language models (LLMs) for knowledge-intensive tasks. However, existing RAG paradigms often overlook the cognitive step of applying knowledge, leaving a gap between retrieved facts and task-specific reasoning. In this work, we introduce RAG+, a principled and modular extension that explicitly incorporates application-aware reasoning into the RAG pipeline. RAG+ constructs a dual corpus consisting of knowledge and aligned application examples, created either manually or automatically, and retrieves both jointly during inference. This design enables LLMs not only to access relevant information but also to apply it within structured, goal-oriented reasoning processes. Experiments across mathematical, legal, and medical domains, conducted on multiple models, demonstrate that RAG+ consistently outperforms standard RAG variants, achieving average improvements of 3-5%, and peak gains up to 13.5% in complex scenarios. By bridging retrieval with actionable application, RAG+ advances a more cognitively grounded framework for knowledge integration, representing a step toward more interpretable and capable LLMs.