arXiv:2412.04847v2 Announce Type: replace
Abstract: Reinforcement learning (RL) has demonstrated remarkable capabilities in training agents to solve complex tasks autonomously, such as mobile robots, UAVs/UGVs, and game-playing agents). However, scaling RL to master multiple tasks simultaneously (i.e., so-called multi-task RL) remains a significant challenge. Such a multi-task RL capability especially is important for agents to adapt to changes in real-world operational environments. State-of-the-art works show that, training agents with neural networks and shared structures across tasks promises improved generalization in simultaneous multi-task RL. However, they still suffer from task interference and incur high energy consumption due to intensive computation. To address this, we propose MTSpark, a novel methodology that enables energy-efficient simultaneous multi-task RL using spiking neural networks (SNNs) equipped with active dendrites for bio-inspired generalist agents. Specifically, MTSpark enhances a Deep Spiking Q-Network (DSQN) with active dendrites, a dueling structure, and task-specific context signals to dynamically form specialized sub-networks for individual tasks, while exploiting sparse operations for energy-efficient network processing. Experimental results demonstrate that MTSpark achieves higher performance and efficiency compared to state-of-the-art by obtaining high scores across three Atari games (i.e., Pong: -5.4, Breakout: 0.6, and Enduro: 371.2), approaching human-level performance (i.e., Pong: -3, Breakout: 31, Enduro: 368), while incurring similar memory and about 2x lower energy than state-of-the-art. These results show that our MTSpark potentially advances the frontiers toward energy-efficient generalist agents by combining RL and SNNs.
Science Journals
arXiv:2412.06551v5 Announce Type: replace
Abstract: CholeskyQR has received considerable attention in recent years for its efficiency and simplicity in computing QR decomposition of the tall-skinny $X \in \mathbb{R}^{m\times n}$ with $m \ge n$ and $\mbox{rank}(X)=n$. Leveraging matrix sketching from randomized linear algebra, randomized CholeskyQR (RCholeskyQR) has been proposed to accelerate the computation by reducing the dimension of the problems. In this work, we propose RCLUPP, a new randomized CholeskyQR-type algorithm based on LU decomposition with partial pivoting (LUP decomposition). By taking LUP decomposition and the thin HouseholderQR on the sketched matrix, RCLUPP significantly improves the applicability and efficiency compared to LU-CholeskyQR2 (LC2). We present a rigorous rounding error analysis of RCLUPP, with a sharper bound of residual compared to those in the existing works. Comparative studies demonstrate that RCLUPP outperforms CholeskyQR2, Shifted CholeskyQR3 (SCholeskyQR3), and LC2 in terms of applicability while maintaining competitive accuracy and efficiency. A variant, RCLUPPr, performs LUP decomposition directly on $X \in \mathbb{R}^{m\times n}$, offering exceptional robustness and numerical stability for the ill-conditioned scenarios, which exceeds that of RCLUPP and RCholeskyQR. Numerical experiments on the synthetic and real-world matrices validate the theoretical results.
arXiv:2412.11121v4 Announce Type: replace
Abstract: Software misconfiguration has consistently been a major reason for software failures. Over the past two decades, much work has been done to detect and diagnose software misconfigurations. However, there is still a gap between real-world misconfigurations and the literature. It is desirable to investigate whether existing taxonomy and tools are applicable for real-world misconfigurations in modern software. In this paper, we conduct an empirical study on 772 real-world misconfiguration issues, based on which we propose a novel classification of the root causes of software misconfigurations, i.e., constraint violation, resource unavailability, component integration error, and configuration semantic misinterpretation. Then, we systematically review the literature on misconfiguration troubleshooting to study the trends of research and the practicality of the tools and datasets in this field. We find that the research targets have changed from system and infrastructure software to advanced applications (e.g., cloud service). Meanwhile, research on non-crash misconfigurations has also grown significantly. Despite the progress, a majority of studies lack reproducibility due to the unavailable tools and evaluation datasets. In total, only eleven tools and four datasets are publicly available. We analyze the trends of existing literature on misconfiguration troubleshooting, summarize the challenges that users are faced with, and highlight the suggestions to mitigate and diagnose software misconfigurations. We release the real-world dataset of misconfiguration issues for follow-up research.
arXiv:2503.06796v2 Announce Type: replace
Abstract: Robot design is a complex and time-consuming process that requires specialized expertise. Gaining a deeper understanding of robot design data can enable various applications, including automated design generation, retrieving example designs from text, and developing AI-powered design assistants. While recent advancements in foundation models present promising approaches to addressing these challenges, progress in this field is hindered by the lack of large-scale design datasets. In this paper, we introduce RoboDesign1M, a large-scale dataset comprising 1 million samples. Our dataset features multimodal data collected from scientific literature, covering various robotics domains. We propose a semi-automated data collection pipeline, enabling efficient and diverse data acquisition. To assess the effectiveness of RoboDesign1M, we conduct extensive experiments across multiple tasks, including design image generation, visual question answering about designs, and design image retrieval. The results demonstrate that our dataset serves as a challenging new benchmark for design understanding tasks and has the potential to advance research in this field. RoboDesign1M will be released to support further developments in AI-driven robotic design automation. Our project is available at https://airvlab.github.io/robotdesign1m/
arXiv:2505.07417v3 Announce Type: replace
Abstract: Hybrid cloud-edge infrastructures now support latency-critical workloads ranging from autonomous vehicles and surgical robotics to immersive AR/VR. However, they continue to experience crippling long-tail latency spikes whenever bursty request streams exceed the capacity of heterogeneous edge and cloud tiers. To address these long-tail latency issues, we present Latency-Aware, Predictive In-Memory Routing and Proactive Autoscaling (LA-IMR). This control layer integrates a closed-form, utilization-driven latency model with event-driven scheduling, replica autoscaling, and edge-to-cloud offloading to mitigate 99th-percentile (P99) delays. Our analytic model decomposes end-to-end latency into processing, network, and queuing components, expressing inference latency as an affine power-law function of instance utilization. Once calibrated, it produces two complementary functions that drive: (i) millisecond-scale routing decisions for traffic offloading, and (ii) capacity planning that jointly determines replica pool sizes. LA-IMR enacts these decisions through a quality-differentiated, multi-queue scheduler and a custom-metric Kubernetes autoscaler that scales replicas proactively -- before queues build up -- rather than reactively based on lagging CPU metrics. Across representative vision workloads (YOLOv5m and EfficientDet) and bursty arrival traces, LA-IMR reduces P99 latency by up to 20.7 percent compared to traditional latency-only autoscaling, laying a principled foundation for next-generation, tail-tolerant cloud-edge inference services.
arXiv:2505.16157v2 Announce Type: replace
Abstract: Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this issue with sparse or window-based attention, yet inherently limit global context modeling. Linear attention, a variant of softmax attention, demonstrates promise in global context modeling while maintaining linear complexity, offering a potential solution to the above challenge. Despite its efficiency benefits, vanilla linear attention suffers from a significant performance drop in IR, largely due to the low-rank nature of its attention map. To counter this, we propose Rank Enhanced Linear Attention (RELA), a simple yet effective method that enriches feature representations by integrating a lightweight depthwise convolution. Building upon RELA, we propose an efficient and effective Vision Transformer, named LAformer. LAformer eliminates hardware-inefficient operations such as softmax and window shifting, enabling efficient processing of high-resolution images. Extensive experiments across 7 IR tasks and 21 benchmarks demonstrate that LAformer outperforms SOTA methods and offers significant computational advantages. Furthermore, we extend LAformer to diffusion-based and flow-based visual generation, showcasing its strong potential as a competitive alternative to DiT and SiT. Code and models are available at https://github.com/shallowdream204/LAformer.
arXiv:2607.12178v1 Announce Type: new
Abstract: In this article we present a method to generate safe sets for linear discrete-time systems subject to non-convex constraints that can be represented as a union of polytopes. It is then shown how a reference governor can be implemented for safe reference tracking tasks. A theoretical analysis of the safe set is presented and properties of the reference governor scheme are derived. The guarantees include safety at any time as well as finite-time convergence of the applied reference command to any strictly admissible reference command. For the proposed reference governor, online computational overhead is low. Moreover, it is shown that for specific instances of the complex constraint sets, the safe set can be computed efficiently. Extensive simulation results demonstrating the applicability of the method and online/offline computation times are reported.
arXiv:2607.12227v1 Announce Type: new
Abstract: We revisit the evaluation of automatic harness evolution for LLM agents. Existing harness evolution methods use unit test cases to search for harness configurations and then report final performance on the same public benchmark. This protocol raises two fundamental concerns. First, harness evolution is itself an iterative search procedure that repeatedly evaluates and revises candidate harnesses using task feedback. As in agentic test-time scaling, it should therefore be compared with simple task-level search baselines under matched feedback and inference budgets to determine whether its gains arise from improved harness design or from additional search alone. Second, because the search and the final evaluation share the same benchmark, the reported gains risk overfitting to that specific task set. To address these concerns, we conduct an extensive evaluation comparing harness evolution with simple test-time scaling and discovery baselines under comparable feedback and inference budgets, and also evaluate evolved harnesses on held-out tasks to assess whether the discovered improvements generalize. Experiments on Terminal-Bench 2.1 with GPT-5.4 and Claude Opus 4.6 show that automatic harness evolution does not consistently outperform simple test-time scaling methods and exhibits limited generalization. Our results raise important questions about the effectiveness of automatic harness evolution and highlight the need for fairer evaluation protocols and benchmarks for automatic harness design. Our code is available at https://github.com/rethinking-harness-evolution.
arXiv:2507.11498v3 Announce Type: replace
Abstract: Humanoid robots have seen remarkable advances in dexterity, balance, and locomotion, yet their role in expressive domains such as music performance remains largely unexplored. Musical tasks, like drumming, present unique challenges such as split-second timing, rapid contacts, and multi-limb coordination over performances lasting minutes. In this paper, we introduce Robot Drummer, a simulation framework for humanoid drumming across a diverse repertoire of songs. We formulate humanoid drumming as the realization of timed contact events encoded as a Rhythmic Contact Chain. To handle the long-horizon nature of musical performance, we decompose each track into fixed-length segments and train a single policy across all segments in parallel using reinforcement learning. Through extensive experiments on over thirty popular tracks, our results demonstrate that Robot Drummer consistently achieves high F1 scores and enables efficient learning of long-horizon musical performances. The learned behaviors exhibit emergent human-like drumming strategies, such as cross-arm strikes, and adaptive stick assignments, demonstrating the potential of reinforcement learning to bring humanoid robots into the domain of creative musical performance. Project page: robotdrummer.github.io
arXiv:2507.15833v3 Announce Type: replace
Abstract: Human vision is a highly active process driven by gaze, which directs attention to task-relevant regions through foveation, dramatically reducing visual processing. In contrast, robot learning systems typically rely on passive, uniform processing of raw camera images. In this work, we explore how incorporating human-like active gaze into robotic policies can enhance efficiency and robustness. We develop GIAVA (Gaze Integrated Active-Vision ALOHA), a robot vision system that emulates human head and neck movement, and gaze adjustment for foveated processing. Extending the AV-ALOHA robot platform, we introduce a framework for simultaneously collecting eye-tracking, perspective control, and robot manipulation demonstration data from a human operator. We also open-source a simulation benchmark and dataset for training robot policies that incorporate human gaze. Inspired by recent work in foveated image segmentation and given the widespread use of Vision Transformers (ViTs) in robot learning, we integrate gaze information into ViTs using a foveated patch tokenization scheme. Compared to uniform patch tokenization, this significantly reduces the number of tokens, and thus computation. Our results show that our method for foveated robot vision drastically reduces computational overhead, and enhances robustness to background distractors. Notably, on certain high-precision tasks, foveated vision also improves performance, as reflected in higher success rates. Together, these findings suggest that human-inspired foveated visual processing offers untapped potential and should be further considered as a useful inductive bias in robotic vision systems. https://soltanilara.github.io/giava/
arXiv:2507.21245v2 Announce Type: replace
Abstract: An accurate initial heading angle is essential for efficient and safe navigation across diverse domains. Unlike magnetometers, gyroscopes can provide accurate heading reference independent of the magnetic disturbances in a process known as gyrocompassing. Yet, accurate and timely gyrocompassing, using low-cost gyroscopes, remains a significant challenge in scenarios where external navigation aids are unavailable. Such challenges are commonly addressed in real-world applications such as autonomous vehicles, where size, weight, and power limitations restrict sensor quality, and noisy measurements severely degrade gyrocompassing performance. To cope with this challenge, we propose a novel diffusion denoiser-aided gyrocompass approach. It integrates a diffusion-based denoising framework with an enhanced learning-based heading estimation model. The diffusion denoiser processes raw inertial sensor signals before input to the deep learning model, resulting in accurate gyrocompassing. Experiments using both simulated and real sensor data demonstrate that our proposed approach improves gyrocompassing accuracy by 26% compared to model-based gyrocompassing and by 15% compared to other learning-driven approaches. This advancement holds particular significance for ensuring accurate and robust navigation in autonomous platforms that incorporate low-cost gyroscopes within their navigation systems.
arXiv:2509.02117v4 Announce Type: replace
Abstract: We present a necessary condition for an infinite language to be multiple context-free, which we call a Substitution Lemma. We apply it to show a sample selection of languages are not multiple context-free, including the word problem of the group $F_2\times F_2$. We also show that groups with multiple context-free word problem have decidable rational subset membership problem.
Our result contrasts with previous work showing that the standard pumping lemma for context-free languages cannot be generalised to multiple context-free languages, and that weak variants of generalised Ogden's lemma do not apply to multiple context-free languages.
arXiv:2509.19242v2 Announce Type: replace
Abstract: We study multivariate linear regression under Gaussian covariates in two settings, where data may be erased or corrupted by an adversary under a coordinate-wise budget. In the incomplete data setting, an adversary may inspect the dataset and delete entries in up to an $\eta$-fraction of samples per coordinate; a strong form of the Missing Not At Random model. In the corrupted data setting, the adversary instead replaces values arbitrarily, and the corruption locations are unknown to the learner. Despite substantial work on missing data, linear regression under such adversarial missingness remains poorly understood, even information-theoretically. Unlike the clean setting, where estimation error vanishes with more samples, here the optimal error remains a positive function of the problem parameters. Our main contribution is to characterize this error up to constant factors across essentially the entire parameter range. Specifically, we establish novel information-theoretic lower bounds on the achievable error that match the error of (computationally efficient) algorithms. A key implication is that, perhaps surprisingly, the optimal error in the missing data setting matches that in the corruption setting-so knowing the corruption locations offers no general advantage.
arXiv:2511.00526v4 Announce Type: replace
Abstract: Micro-electro-mechanical systems (MEMS)-based (chip-scale) alkali vapor cells are key components in emerging quantum technologies, where device performance critically depends on the atomic number density. Thus, it is important to have an accurate estimate of the atomic number density in MEMS-based alkali vapor cells to optimize light-matter interactions and design efficient quantum sensing systems. Here, a quantitatively validated method is presented for determining the rubidium (Rb) atomic number density in warm vapor using Single-Pass Absorption Spectroscopy (SPAS). The absolute transmission spectra are measured and modeled using the 780.24~nm and 420.29~nm transitions in Rb-filled MEMS vapor. The theoretical model employs a density-matrix formalism within the Lindblad framework and incorporates directly measurable experimental parameters, such as laser beam power, diameter, and cell temperature. The model explicitly accounts for optical pumping, Doppler broadening, and transit-time broadening effects and exhibits quantitative agreement ($> 99\%$) with experimental spectra over a broad range of temperatures (293-353~K), laser probe powers of approximately 10~$\mu$W-100~$\mu$W at the 780.24~nm transition and 8~$\mu$W-80~$\mu$W at the 420.29~nm transition, and cell lengths (2--100~mm). This method demonstrates a practical and reliable approach for determining the density of alkali vapor cells for quantum sensing, metrology, and quantum communication applications.
arXiv:2511.00623v3 Announce Type: replace
Abstract: Data centers play an increasingly critical role in societal digitalization, yet their rapidly growing energy demand poses significant challenges for sustainable operation. To enhance the energy efficiency of geographically distributed data centers, this paper formulates a multi-period optimization model that captures the interdependence of electricity, heat, and data flows. The optimization of such integrated multi-domain flows inherently involves mixed-integer formulations and the access to proprietary or sensitive datasets, which correspondingly exacerbate computational complexity and raise data-privacy concerns. To address these challenges, an adaptive federated learning-to-optimization approach is proposed, accounting for the heterogeneity of datasets across distributed data centers. To safeguard privacy, cryptography techniques are leveraged in both the learning and optimization processes. A model acceptance criterion with convergence guarantee is developed to improve learning performance and filter out potentially contaminated data, while a verifiable double aggregation mechanism is further proposed to simultaneously ensure privacy and integrity of shared data during optimization. Theoretical analysis and numerical simulations demonstrate that the proposed approach preserves the privacy and integrity of shared data, achieves near-optimal performance, and exhibits high computational efficiency, making it suitable for large-scale data center optimization under privacy constraints.
arXiv:2510.00492v3 Announce Type: replace
Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic. Prior work has studied both outcome reward models (ORMs), which assess only the final answer, and process reward models (PRMs), which score intermediate reasoning steps. Although PRMs are often viewed as advantageous due to their finer-grained supervision, much of the supporting evidence comes from math-adjacent settings, and their relative benefits across broader domains remain unclear. We present the first unified evaluation of four reward model variants, discriminative ORM and PRM (dORM, dPRM) and generative ORM and PRM (gORM, gPRM), across 14 diverse domains. Contrary to conventional wisdom, we find that (i) dORM performs on par with dPRM, (ii) gPRM is not competitive, and (iii) overall, gORM is the most robust, yielding significant and consistent gains across every tested domain. We attribute the worse performance of gPRM to the stepwise scoring process, which inherits label noise from LLM-based automatic labeling, leading to difficulties in evaluating long reasoning trajectories, including those involving self-correcting reasoning. Both our theoretical analysis and empirical observations indicate that stepwise aggregation compounds errors as reasoning length increases. These findings challenge the common assumption that fine-grained supervision is always better and support generative outcome verification for multi-domain deployment. Our \href{https://github.com/db-Lee/Multi-RM}{\underline{code}} is publicly available to facilitate future research in multi-domain settings.
arXiv:2511.07836v5 Announce Type: replace
Abstract: The curse of dimensionality remains a persistent challenge in modern optimization problems. Expanding the search space into higher dimensions exponentiates the difficulty of finding optimal solutions, rendering traditional algorithms inefficient. An efficient sampling strategy is presented to accelerate high-dimensional optimization as an alternative to uniform quasi-Monte Carlo (QMC) methods.
This method, referred to as Hyperellipsoid Density Sampling (HDS), generates sequences by defining multiple hyperellipsoids throughout the search space. HDS utilizes three types of unsupervised learning algorithms to bypass high-dimensional geometric calculations, producing a non-uniform sample sequence that exploits statistically promising regions of the parameter space. The ability to influence its distribution towards regions of interest makes HDS versatile for applications beyond global optimization, where models benefit from samples focused in specific regions.
HDS was evaluated against Sobol, a highly uniform QMC sampling method, using differential evolution (DE) on the challenging set of 29 CEC2017 benchmark test functions. The results show statistically significant improvements in final solution geometric mean error (p<0.05), with average performance gains ranging from 37% in 10D to 11% in 100D. This paper demonstrates the efficacy of HDS as a robust alternative to uniform QMC sampling in high-dimensional optimization.
arXiv:2511.10033v3 Announce Type: replace
Abstract: Transformer has emerged as a powerful deep-learning technique for two-dimensional (2D) seismic data interpolation, owing to its global modeling ability. However, its core operation introduces heavy computational burden due to the quadratic complexity, hindering its further application to higher-dimensional data. To achieve Transformer-based three-dimensional (3D) seismic interpolation, we propose a 2.5-dimensional Transformer network (T-2.5D) that adopts a cross-dimensional transfer learning (TL) strategy, so as to adapt the 2D Transformer encoders to 3D seismic data. The proposed T-2.5D is mainly composed of 2D Transformer encoders and 3D seismic dimension adapters (SDAs). Each 3D SDA is placed before a Transformer encoder to learn spatial correlation information across seismic lines. The proposed cross-dimensional TL strategy comprises two stages: 2D pre-training and 3D fine-tuning. In the first stage, we optimize the 2D Transformer encoders using a large amount of 2D data patches. In the second stage, we freeze the 2D Transformer encoders and fine-tune the 3D SDAs using limited 3D data volumes. Extensive experiments on multiple datasets are conducted to assess the effectiveness and efficiency of T-2.5D. Experimental results demonstrate that the proposed method achieves comparable performance to that of full 3D Transformer at a significantly low cost.
arXiv:2511.11132v4 Announce Type: replace
Abstract: Knowledge-based Visual Question Answering (KBVQA) necessitates external knowledge incorporation beyond cross-modal understanding. Existing KBVQA methods either utilize implicit knowledge in multimodal large language models via in-context learning or explicit knowledge via retrieval augmented generation. However, their reasoning processes remain implicit, without explicit multi-step trajectories. To address this gap, we propose a Self-Encouraged Hindsight Distillation Reasoning (HinD) framework, aiming at eliciting reasoning ability inside the MLLM by constructing a Hindsight Teacher with privileged information to teach the Foresight Student. First, we construct the Hindsight Teacher by prompting the MLLM with the reasoning target as privileged information to complete the reasoning process, obtaining Hindsight-Zero training data. Then, the Foresight Student, without knowing the answer, learns the golden trajectories from Hindsight in two ways: (1) Hindsight Distillation Fine-Tuning to self-distill the Hindsight-Zero into a modularized Chain-of-Thought Generator and a Knowledge Generator for sequential steps and discrete facts generation, respectively; (2) Knowledge Encouragement Preference Optimization to encourage the under-confident but relevant knowledge inside the MLLM and suppress the over-confident but irrelevant one. Experiments on OK-VQA and A-OKVQA validate the effectiveness of HinD, showing that HinD with 7-8B MLLM achieves superior performance without commercial model APIs or retrieved knowledge.
arXiv:2512.01241v4 Announce Type: replace
Abstract: Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a 1,100-task benchmark of primary care-to-specialist consultation cases to measure the frequency and severity of potentially harmful errors from LLM-generated medical consultation recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 20 notable LLMs and 4 widely used retrieval-augmented generation (RAG) clinical AI tools, direct application of recommendations carried potential for severe harm in up to 24.6% of cases, with errors of omission accounting for more than 80% of severe errors. Harm potential was not uniform across systems, with clinical AI tools outperforming generalist LLMs, and multi-agent AI teaming further improving performance in generalist models. In a randomized study of 101 U.S.-licensed generalist physicians, AI assistance improved physician performance compared to conventional resources. However, AI-assisted physicians frequently omitted valuable AI-generated recommendations and still scored lower than many AI systems alone. Had those recommendations been incorporated, combined human-AI responses would have outperformed both the human and AI system as used, suggesting complementary strengths and unrealized potential in human-AI teaming. Collectively, these results show that despite strong performance on medical knowledge benchmarks, widely used AI tools can produce medical consultation advice with the potential for severe harm, and highlight the need for explicit measurement of clinical safety. The benchmark and leaderboard are publicly available to support ongoing evaluation and improvement of AI systems used for clinical care.
arXiv:2602.14539v1 Announce Type: cross
Abstract: Advances in quantum computing increasingly threaten the security and privacy of data protected by current cryptosystems, particularly those relying on public-key cryptography. In response, the international cybersecurity community has prioritized the implementation of Post-Quantum Cryptography (PQC), a new cryptographic standard designed to resist quantum attacks while operating on classical computers. The National Institute of Standards and Technology (NIST) has already standardized several PQC algorithms and plans to deprecate classical asymmetric schemes, such as RSA and ECDSA, by 2035. Despite this urgency, PQC adoption remains slow, often due to limited developer expertise. Application Programming Interfaces (APIs) are intended to bridge this gap, yet prior research on classical security APIs demonstrates that poor usability of cryptographic APIs can lead developers to introduce vulnerabilities during implementation of the applications, a risk amplified by the novelty and complexity of PQC. To date, the usability of PQC APIs has not been systematically studied. This research presents an empirical evaluation of the usability of the PQC APIs, observing how developers interact with APIs and documentation during software development tasks. The study identifies cognitive factors that influence the developer's performance when working with PQC primitives with minimal onboarding. The findings highlight opportunities across the PQC ecosystem to improve developer-facing guidance, terminology alignment, and workflow examples to better support non-specialists.
arXiv:2506.21324v3 Announce Type: replace
Abstract: Neuromorphic and quantum computing have recently emerged as promising paradigms for advancing artificial intelligence, each offering complementary strengths. Neuromorphic systems built on spiking neurons excel at processing time series data efficiently through sparse, event-driven computation, consuming energy only upon input events. Quantum computing, on the other hand, operates on state spaces that grow exponentially in dimension with the number of qubits -- as a consequence of tensor-product composition -- with quantum states admitting superposition across basis states and entanglement between subsystems. Hybrid approaches combining these paradigms have begun to show potential, but existing quantum spiking models have important limitations. Notably, they implement classical memory mechanisms on single qubits, requiring repeated measurements to estimate firing probabilities, while relying on conventional backpropagation for training. In this paper, we propose a novel stochastic quantum spiking (SQS) neuron model that addresses these challenges. The SQS neuron uses multi-qubit quantum circuits to realize a spiking unit with internal quantum memory, enabling event-driven probabilistic spike generation in a single shot during inference. Furthermore, we study networks of SQS neurons, dubbed SQS neural networks (SQSNN), and demonstrate that they can be trained via a hardware-friendly local learning rule, eliminating the need for global classical backpropagation. The proposed SQSNN model is shown via experiments with both conventional and neuromorphic datasets to improve over previous quantum spiking neural networks, as well as over classical counterparts, when fixing the overall number of trainable parameters, highlighting its potential for event-driven applications such as neuromorphic integrated sensing and communications (N-ISAC).
arXiv:2512.03207v2 Announce Type: replace
Abstract: The Privacy Sandbox, launched in 2019, is a series of proposals from Google to reduce ``cross-site and cross-app tracking while helping to keep online content and services free for all''. Over the years, Google implemented, experimented, and deprecated some of these APIs into their own products (Chrome, Android, etc.) which raised concerns about the potential of these mechanisms to fundamentally disrupt the advertising, mobile, and web ecosystems. As a result, it is paramount for researchers to understand the consequences that these new technologies, and future ones, will have on billions of users if and when deployed. In this report, we outline our call for privacy, security, usability, and utility evaluations of these APIs, our efforts materialized through the creation and operation of Privacy Sandstorm (https://privacysandstorm.github.io); a research portal to systematically gather resources (overview, analyses, artifacts, etc.) about such proposals. We find that our inventory provides a better visibility and broader perspective on the research findings in that space than what Google lets show through official channels.
arXiv:2601.11443v3 Announce Type: replace
Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful approach for enhancing large language models' question-answering capabilities through the integration of external knowledge. However, when adapting RAG systems to specialized domains, challenges arise from distribution shifts, resulting in suboptimal generalization performance. In this work, we propose TTARAG, a test-time adaptation method that dynamically updates the language model's parameters during inference to improve RAG system performance in specialized domains. Our method introduces a simple yet effective approach where the model learns to predict retrieved content, enabling automatic parameter adjustment to the target domain. Through extensive experiments across six specialized domains, we demonstrate that TTARAG achieves substantial performance improvements over baseline RAG systems. Code available at https://github.com/sunxin000/TTARAG.
arXiv:2602.06486v4 Announce Type: replace
Abstract: Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while LLM-as-a-judge approaches adapt to individual responses yet suffer from instability and bias. Human experts address this dilemma by combining domain-grounded principles with dynamic, claim-level assessment. Inspired by this process, we propose JADE, a two-layer evaluation framework. Layer 1 encodes expert knowledge as a predefined set of evaluation skills, providing stable evaluation criteria. Layer 2 performs report-specific, claim-level evaluation to flexibly assess diverse reasoning strategies, with evidence-dependency gating to invalidate conclusions built on refuted claims. Experiments on BizBench show that JADE improves evaluation stability and reveals critical agent failure modes missed by holistic LLM-based evaluators. We further demonstrate strong alignment with expert-authored rubrics and effective transfer to HealthBench and DR.BENCH, covering medical and 10-domain professional evaluation settings. Code and data are available at https://github.com/smiling-world/JADE.