Inference accounts for the majority of latency and energy consumption in large language model (LLM) deployments, often exceeding 90% of total cost. While training-time efficiency has seen extensive progress, runtime optimization remains a key bottleneck, particularly under autoregressive decoding. Existing approaches -- such as pruning, quantization, early exits, and speculative decoding -- often require retraining, architectural changes, or disrupt decoding compatibility. We introduce QuickSilver, a modular, token-level framework that enables semantic adaptivity at inference time without altering model weights or structure. QuickSilver integrates four synergistic mechanisms: (i) Dynamic Token Halting, which halts computation for tokens with converged representations; (ii) KV Cache Skipping, which selectively suppresses memory writes to reduce attention overhead; and (iii) Contextual Token Fusion, which collapses redundant tokens into shared paths to shrink sequence length. Unlike speculative decoding or MoE routing, QuickSilver operates entirely on frozen, dense models and requires no auxiliary networks. Applied to GPT-2 and Llama-2 across WikiText-103 and C4, QuickSilver achieves up to 39.6% FLOP reduction with negligible perplexity degradation (<=0.2).

Thompson sampling (TS) is an effective method to explore parametric uncertainties and can therefore be used for active learning-based controller design. However, TS relies on finite parametric representations, which limits its applicability to more general spaces, which are more commonly encountered in control system design. To address this issue, this work pro poses a parameterization method for control law learning using reproducing kernel Hilbert spaces and designs a data-driven active learning control approach. Specifically, the proposed method treats the control law as an element in a function space, allowing the design of control laws without imposing restrictions on the system structure or the form of the controller. A TS framework is proposed in this work to explore potential optimal control laws, and the convergence guarantees are further provided for the learning process. Theoretical analysis shows that the proposed method learns the relationship between control laws and closed-loop performance metrics at an exponential rate, and the upper bound of control regret is also derived. Numerical experiments on controlling unknown nonlinear systems validate the effectiveness of the proposed method.

--The evolution toward 6G networks demands a fundamental shift from bit-centric transmission to semantic-aware communication that emphasizes task-relevant information. This work introduces TOAST (T ask-Oriented Adaptive Semantic Transmission), a unified framework designed to address the core challenge of multi-task optimization in dynamic wireless environments through three complementary components. First, we formulate adaptive task balancing as a Markov decision process, employing deep reinforcement learning to dynamically adjust the trade-off between image reconstruction fidelity and semantic classification accuracy based on real-time channel conditions. Second, we integrate module-specific Low-Rank Adaptation (LoRA) mechanisms throughout our Swin Transformer-based joint source-channel coding architecture, enabling parameter-efficient fine-tuning that dramatically reduces adaptation overhead while maintaining full performance across diverse channel impairments including Additive White Gaussian Noise (A WGN), fading, phase noise, and impulse interference. Third, we incorporate an Elucidating diffusion model that operates in the latent space to restore features corrupted by channel noises, providing substantial quality improvements compared to baseline approaches. Extensive experiments across multiple datasets demonstrate that TOAST achieves superior performance compared to baseline approaches, with significant improvements in both classification accuracy and reconstruction quality at low Signal-to-Noise Ratio (SNR) conditions while maintaining robust performance across all tested scenarios. By seamlessly orchestrating reinforcement learning, diffusion-based enhancement, and parameter-efficient adaptation within a single coherent framework, TOAST represents a significant advancement toward adaptive semantic communication systems capable of thriving in the rigorous conditions of next-generation wireless networks. HE emergence of sixth-generation (6G) wireless networks marks a fundamental change in how communication is understood, shifting from Shannon's classical model of reliable bit transmission to a semantic-oriented approach that focuses on meaning and task relevance [1]. This development in Semantic Communication (SemCom) acknowledges that, in many practical scenarios, reconstructing every bit perfectly is neither required nor efficient. Instead, the key is to retain the information necessary for completing specific tasks, such as interpreting a scene, making a decision, or initiating an action [2]. Wang are with the Department of Electrical Engineering and Computer Science, Lassonde School of Engineering, Y ork University, Toronto, ON, Canada (e-mails: ys97@yorku.ca; J. Pei is with the School of Electrical and Electronic Engineering, Huazhong University of Science and Technology, Wuhan, China (e-mail: jianhuapei@hust.edu.cn).

Storm surge forecasting plays a crucial role in coastal disaster preparedness, yet existing machine learning approaches often suffer from limited spatial resolution, reliance on coastal station data, and poor generalization. Moreover, many prior models operate directly on unstructured spatial data, making them incompatible with modern deep learning architectures. In this work, we introduce a novel approach that projects unstructured water elevation fields onto structured Red Green Blue (RGB)-encoded image representations, enabling the application of Convolutional Long Short Term Memory (ConvLSTM) networks for end-to-end spatiotemporal surge forecasting. Our model further integrates ground-truth wind fields as dynamic conditioning signals and topo-bathymetry as a static input, capturing physically meaningful drivers of surge evolution. Evaluated on a large-scale dataset of synthetic storms in the Gulf of Mexico, our method demonstrates robust 48-hour forecasting performance across multiple regions along the Texas coast and exhibits strong spatial extensibility to other coastal areas. By combining structured representation, physically grounded forcings, and scalable deep learning, this study advances the frontier of storm surge forecasting in usability, adaptability, and interpretability.

Building damage identification shortly after a disaster is crucial for guiding emergency response and recovery efforts. Although optical satellite imagery is commonly used for disaster mapping, its effectiveness is often hampered by cloud cover or the absence of pre-event acquisitions. To overcome these challenges, we introduce a novel multimodal deep learning (DL) framework for detecting building damage using single-date very high resolution (VHR) Synthetic Aperture Radar (SAR) imagery from the Italian Space Agency (ASI) COSMO SkyMed (CSK) constellation, complemented by auxiliary geospatial data. Our method integrates SAR image patches, OpenStreetMap (OSM) building footprints, digital surface model (DSM) data, and structural and exposure attributes from the Global Earthquake Model (GEM) to improve detection accuracy and contextual interpretation. Unlike existing approaches that depend on pre and post event imagery, our model utilizes only post event data, facilitating rapid deployment in critical scenarios. The framework effectiveness is demonstrated using a new dataset from the 2023 earthquake in Turkey, covering multiple cities with diverse urban settings. Results highlight that incorporating geospatial features significantly enhances detection performance and generalizability to previously unseen areas. By combining SAR imagery with detailed vulnerability and exposure information, our approach provides reliable and rapid building damage assessments without the dependency from available pre-event data. Moreover, the automated and scalable data generation process ensures the framework's applicability across diverse disaster-affected regions, underscoring its potential to support effective disaster management and recovery efforts. Code and data will be made available upon acceptance of the paper.

We show that recurrent quantum reservoir computers (QRCs) and their recurrence-free architectures (RF-QRCs) are robust tools for learning and forecasting chaotic dynamics from time-series data. First, we formulate and interpret quantum reservoir computers as coupled dynamical systems, where the reservoir acts as a response system driven by training data; in other words, quantum reservoir computers are generalized-synchronization (GS) systems. Second, we show that quantum reservoir computers can learn chaotic dynamics and their invariant properties, such as Lyapunov spectra, attractor dimensions, and geometric properties such as the covariant Lyapunov vectors. This analysis is enabled by deriving the Jacobian of the quantum reservoir update. Third, by leveraging tools from generalized synchronization, we provide a method for designing robust quantum reservoir computers. We propose the criterion $GS=ESP$: GS implies the echo state property (ESP), and vice versa. We analytically show that RF-QRCs, by design, fulfill $GS=ESP$. Finally, we analyze the effect of simulated noise. We find that dissipation from noise enhances the robustness of quantum reservoir computers. Numerical verifications on systems of different dimensions support our conclusions. This work opens opportunities for designing robust quantum machines for chaotic time series forecasting on near-term quantum hardware.

Inference tasks with time series over graphs are of importance in applications such as urban water networks, economics, and networked neuroscience. Addressing these tasks typically relies on identifying a computationally affordable model that jointly captures the graph-temporal patterns of the data. In this work, we propose a graph-aware state space model for graph time series, where both the latent state and the observation equation are parametric graph-induced models with a limited number of parameters that need to be learned. More specifically, we consider the state equation to follow a stochastic partial differential equation driven by noise over the graphs edges accounting not only for potential edge uncertainties but also for increasing the degrees of freedom in the latter in a tractable manner. The graph structure conditioning of the noise dispersion allows the state variable to deviate from the stochastic process in certain neighborhoods. The observation model is a sampled and graph-filtered version of the state capturing multi-hop neighboring influence. The goal is to learn the parameters in both state and observation models from the partially observed data for downstream tasks such as prediction and imputation. The model is inferred first through a maximum likelihood approach that provides theoretical tractability but is limited in expressivity and scalability. To improve on the latter, we use the state-space formulation to build a principled deep learning architecture that jointly learns the parameters and tracks the state in an end-to-end manner in the spirit of Kalman neural networks.

Physics phenomena are often described by ordinary and/or partial differential equations (ODEs/PDEs), and solved analytically or numerically. Unfortunately, many real-world systems are described only approximately with missing or unknown terms in the equations. This makes the distribution of the physics model differ from the true data-generating process (DGP). Using limited and unpaired data between DGP observations and the imperfect model simulations, we investigate this particular setting by completing the known-physics model, combining theory-driven models and data-driven to describe the shifted distribution involved in the DGP. We present a novel hybrid generative model approach combining deep grey-box modelling with Optimal Transport (OT) methods to enhance incomplete physics models. Our method implements OT maps in data space while maintaining minimal source distribution distortion, demonstrating superior performance in resolving the unpaired problem and ensuring correct usage of physics parameters. Unlike black-box alternatives, our approach leverages physics-based inductive biases to accurately learn system dynamics while preserving interpretability through its domain knowledge foundation. Experimental results validate our method's effectiveness in both generation tasks and model transparency, offering detailed insights into learned physics dynamics.

Microscopy is a primary source of information on materials structure and functionality at nanometer and atomic scales. The data generated is often well-structured, enriched with metadata and sample histories, though not always consistent in detail or format. The adoption of Data Management Plans (DMPs) by major funding agencies promotes preservation and access. However, deriving insights remains difficult due to the lack of standardized code ecosystems, benchmarks, and integration strategies. As a result, data usage is inefficient and analysis time is extensive. In addition to post-acquisition analysis, new APIs from major microscope manufacturers enable real-time, ML-based analytics for automated decision-making and ML-agent-controlled microscope operation. Yet, a gap remains between the ML and microscopy communities, limiting the impact of these methods on physics, materials discovery, and optimization. Hackathons help bridge this divide by fostering collaboration between ML researchers and microscopy experts. They encourage the development of novel solutions that apply ML to microscopy, while preparing a future workforce for instrumentation, materials science, and applied ML. This hackathon produced benchmark datasets and digital twins of microscopes to support community growth and standardized workflows. All related code is available at GitHub: https://github.com/KalininGroup/Mic-hackathon-2024-codes-publication/tree/1.0.0.1

Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing to uncover potential risks in real-world scenarios. To address this, we propose a novel jailbreak attack framework, ICRT, inspired by heuristics and biases in human cognition. Leveraging the simplicity effect, we employ cognitive decomposition to reduce the complexity of malicious prompts. Simultaneously, relevance bias is utilized to reorganize prompts, enhancing semantic alignment and inducing harmful outputs effectively. Furthermore, we introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm by employing ranking aggregation methods such as Elo, HodgeRank, and Rank Centrality to comprehensively quantify the harmfulness of generated content. Experimental results show that our approach consistently bypasses mainstream LLMs' safety mechanisms and generates high-risk content, providing insights into jailbreak attack risks and contributing to stronger defense strategies.