Search

We present a novel framework for online learning in Stackelberg general-sum games, where two agents, the leader and follower, engage in sequential turn-based interactions. At the core of this approach is a learned diffeomorphism that maps the joint action space to a smooth Riemannian manifold, referred to as the Stackelberg manifold. This mapping, facilitated by neural normalizing flows, ensures the formation of tractable isoplanar subspaces, enabling efficient techniques for online learning. By assuming linearity between the agents' reward functions on the Stackelberg manifold, our construct allows the application of standard bandit algorithms. We then provide a rigorous theoretical basis for regret minimization on convex manifolds and establish finite-time bounds on simple regret for learning Stackelberg equilibria. This integration of manifold learning into game theory uncovers a previously unrecognized potential for neural normalizing flows as an effective tool for multi-agent learning. We present empirical results demonstrating the effectiveness of our approach compared to standard baselines, with applications spanning domains such as cybersecurity and economic supply chain optimization., Comment: Stackelberg games. Manifold learning. Online learning

This paper investigates the finite-horizon distributionally robust mixed-integer control (DRMIC) of uncertain linear systems. However, deriving an optimal causal feedback control policy to this DRMIC problem is computationally formidable for most ambiguity sets. To address the computational challenge, we propose a novel distributionally robust lifted control policy (DR-LCP) method to derive a high-quality approximate solution to this DRMIC problem for a rich class of Wasserstein metric-based ambiguity sets, including the Wasserstein ambiguity set and its variants. In theory, we analyze the asymptotic performance and establish a tight non-asymptotic bound of the proposed method. In numerical experiments, the proposed DR-LCP method empirically demonstrates superior performance compared with existing methods in the literature., Comment: 11 pages

The ability to automatically complete a partial sketch that depicts a complex scene, e.g., "a woman chatting with a man in the park", is very useful. However, existing sketch generation methods create sketches from scratch; they do not complete a partial sketch in the style of the original. To address this challenge, we introduce AutoSketch, a styleaware vector sketch completion method that accommodates diverse sketch styles. Our key observation is that the style descriptions of a sketch in natural language preserve the style during automatic sketch completion. Thus, we use a pretrained vision-language model (VLM) to describe the styles of the partial sketches in natural language and replicate these styles using newly generated strokes. We initially optimize the strokes to match an input prompt augmented by style descriptions extracted from the VLM. Such descriptions allow the method to establish a diffusion prior in close alignment with that of the partial sketch. Next, we utilize the VLM to generate an executable style adjustment code that adjusts the strokes to conform to the desired style. We compare our method with existing methods across various sketch styles and prompts, performed extensive ablation studies and qualitative and quantitative evaluations, and demonstrate that AutoSketch can support various sketch scenarios., Comment: 11 pages

Despite the success of Gaussian process based Model Predictive Control (MPC) in robotic control, its applicability scope is greatly hindered by multimodal disturbances that are prevalent in real-world settings. Here we propose a novel Mixture of Gaussian Processes based Distributionally Robust MPC (MoGP-DR-MPC) framework for linear time invariant systems subject to potentially multimodal state-dependent disturbances. This framework utilizes MoGP to automatically determine the number of modes from disturbance data. Using the mean and variance information provided by each mode-specific predictive distribution, it constructs a data-driven state-dependent ambiguity set, which allows for flexible and fine-grained disturbance modeling. Based on this ambiguity set, we impose Distributionally Robust Conditional Value-at Risk (DR-CVaR) constraints to effectively achieve distributional robustness against errors in the predictive distributions. To address the computational challenge posed by these constraints in the resulting MPC problem, we equivalently reformulate the DR-CVaR constraints into tractable second-order cone constraints. Furthermore, we provide theoretical guarantees on the recursive feasibility and stability of the proposed framework. The enhanced control performance of MoGP-DR-MPC is validated through both numerical experiments and simulations on a quadrotor system, demonstrating notable reductions in closed-loop cost by 17% and 4% respectively compared against Gaussian process based MPC., Comment: 6 pages

The rapid proliferation of large language models has driven the need for efficient GPU training clusters. However, ensuring high-performance training in these clusters is challenging due to the complexity of software-hardware interactions and the frequent occurrence of training anomalies. Since existing diagnostic tools are narrowly tailored to specific issues, there are gaps in their ability to address anomalies spanning the entire training stack. In response, we introduce XPUTimer, a real-time diagnostic framework designed for distributed LLM training at scale. XPUTimer first integrates a lightweight tracing daemon to monitor key code segments with minimal overhead. Additionally, it features a diagnostic engine that employs novel intra-kernel tracing and holistic aggregated metrics to efficiently identify and resolve anomalies. Deployment of XPUTimer across 6,000 GPUs over eight months demonstrated significant improvements across the training stack, validating its effectiveness in real-world scenarios.

Entanglement has the ability to enhance the transmission of classical information over a quantum channel. However, fully harvesting this advantage typically requires complex entangling measurements, which are challenging to implement and scale with the system's size. In this work, we consider a natural quantum information primitive in which the message to be communicated is selected stochastically. We introduce a protocol that leverages high-dimensional entanglement to perform this task perfectly, without requiring quantum interference between particles at the measurement station. We experimentally demonstrate the protocol's scalability in an optical setup using 8-dimensional entanglement and multi-outcome detection, providing a practical solution for stochastic communication and a robust method for certifying the dimensionality of entanglement in communication experiments., Comment: 16 pages,7 figures

We consider the problem of finding an $\epsilon$-stationary point of a nonconvex function with a Lipschitz continuous Hessian and propose a quadratic regularized Newton method incorporating a new class of regularizers constructed from the current and previous gradients. The method leverages a recently developed linear conjugate gradient approach with a negative curvature monitor to solve the regularized Newton equation. Notably, our algorithm is adaptive, requiring no prior knowledge of the Lipschitz constant of the Hessian, and achieves a global complexity of $O(\epsilon^{-\frac{3}{2}}) + \tilde O(1)$ in terms of the second-order oracle calls, and $\tilde O(\epsilon^{-\frac{7}{4}})$ for Hessian-vector products, respectively. Moreover, when the iterates converge to a point where the Hessian is positive definite, the method exhibits quadratic local convergence. Preliminary numerical results illustrate the competitiveness of our algorithm.

Federated learning (FL) has garnered significant attention as a prominent privacy-preserving Machine Learning (ML) paradigm. Decentralized FL (DFL) eschews traditional FL's centralized server architecture, enhancing the system's robustness and scalability. However, these advantages of DFL also create new vulnerabilities for malicious participants to execute adversarial attacks, especially model poisoning attacks. In model poisoning attacks, malicious participants aim to diminish the performance of benign models by creating and disseminating the compromised model. Existing research on model poisoning attacks has predominantly concentrated on undermining global models within the Centralized FL (CFL) paradigm, while there needs to be more research in DFL. To fill the research gap, this paper proposes an innovative model poisoning attack called DMPA. This attack calculates the differential characteristics of multiple malicious client models and obtains the most effective poisoning strategy, thereby orchestrating a collusive attack by multiple participants. The effectiveness of this attack is validated across multiple datasets, with results indicating that the DMPA approach consistently surpasses existing state-of-the-art FL model poisoning attack strategies., Comment: 8 pages, 3 figures

XuanLong-50 (EXL-50) is the first medium-size spherical torus (ST) in China, with the toroidal field at major radius at 50 cm around 0.5T. CS-free and non-inductive current drive via electron cyclotron resonance heating (ECRH) was the main physics research issue for EXL-50. Discharges with plasma currents of 50 kA - 180 kA were routinely obtained in EXL-50, with the current flattop sustained for up to or beyond 2 s. The current drive effectiveness on EXL-50 was as high as 1 A/W for low-density discharges using 28GHz ECRH alone for heating power less than 200 kW. The plasma current reached Ip>80 kA for high-density (5*10e18m-2) discharges with 150 kW 28GHz ECRH. Higher performance discharge (Ip of about 120 kA and core density of about 1*10e19m-3) was achieved with 150 kW 50GHz ECRH. The plasma current in EXL-50 was mainly carried by the energetic electrons.Multi-fluid equilibrium model has been successfully applied to reconstruct the magnetic flux surface and the measured plasma parameters of the EXL-50 equilibrium. The physics mechanisms for the solenoid-free ECRH current drive and the energetic electrons has also been investigated. Preliminary experimental results show that 100 kW of lower hybrid current drive (LHCD) waves can drive 20 kA of plasma current. Several boron injection systems were installed and tested in EXL-50, including B2H6 gas puffing, boron powder injection, boron pellet injection. The research plan of EXL-50U, which is the upgrade machine of EXL-50, is also presented.

Large language model (LLM)-based agents have recently shown impressive progress in a variety of domains, including open-ended conversation and multi-step decision-making. However, applying these agents to social deduction games such as Werewolf, which requires both strategic decision-making and free-form language interaction, remains non-trivial. Traditional methods based on Counterfactual Regret Minimization (CFR) or reinforcement learning (RL) typically depend on a predefined action space, making them unsuitable for language games with unconstrained text action space. Meanwhile, pure LLM-based agents often suffer from intrinsic biases and require prohibitively large datasets for fine-tuning. We propose Latent Space Policy Optimization (LSPO), an iterative framework that addresses these challenges by first mapping free-form text to a discrete latent space, where methods like CFR and RL can learn strategic policy more effectively. We then translate the learned policy back into natural language dialogues, which are used to fine-tune an LLM via Direct Preference Optimization (DPO). By iteratively alternating between these stages, our LSPO agent progressively enhances both strategic reasoning and language communication. Experiment results on the Werewolf game show that our method improves the agent's performance in each iteration and outperforms existing Werewolf agents, underscoring its promise for free-form language decision-making.

Efficiently fulfilling coverage tasks in non-convex regions has long been a significant challenge for multi-agent systems (MASs). By leveraging conformal mapping, this paper introduces a novel sectorial coverage formulation to transform a non-convex annulus region into a topologically equivalent one. This approach enables the deployment of MASs in a non-star-shaped region while optimizing coverage performance and achieving load balance among sub-regions. It provides a unique perspective on the partitioned sub-regions to highlight the geodesic convex property of the non-star-shaped region. By utilizing the sectorial partition mechanism and the diffeomorphism property of conformal mapping, a decentralized control law is designed to drive MASs towards a desired configuration, which not only optimizes the global coverage cost but also ensures exponential convergence of equitable workload. Moreover, an iterative search algorithm is developed to identify the optimal approximation of multi-agent deployment in the non-star-shaped region. Theoretical analysis is conducted to confirm the asymptotic stability and global convergence with arbitrary small tolerance of the closed-loop system. Finally, numerical simulations demonstrate the practicality of the proposed coverage formulation with conformal mapping.

M17 is a well-known massive star-forming region, and its Gas-to-Dust Ratio (GDR) may vary significantly compared to the other areas. The mass of gas can be traced by the ${\rm CO}$ emission observed in the \emph{Milky Way Imaging Scroll Painting (MWISP) project}. The dust mass can be traced by analyzing the interstellar extinction magnitude obtained from the \emph{United Kingdom Infrared Telescope (UKIRT)}. We computed the ratio ${W({\rm CO})/A_V}$: for ${A_V \le }$ 10 mag, ${{ W(^{12}{\rm CO})/ A_V}= (6.27 \pm 0.19)}$ ${\mathrm{{K \cdot km/s} \cdot mag^{-1}}}$ and ${{ W(^{13}{\rm CO})/ A_V} = (0.75 \pm 0.72)}$ ${ \mathrm{{K \cdot km/s} \cdot mag^{-1}}}$; whereas for ${{A_V} \ge 10}$ mag, ${{ W(^{12}{\rm CO})/ A_V} = (15.8 \pm 0.06) }$ ${\mathrm{{K \cdot km/s} \cdot mag^{-1}}}$ and ${{ W(^{13}{\rm CO})/ A_V} = (3.11 \pm 0.25)}$ ${ \mathrm{{K \cdot km/s} \cdot mag^{-1}}}$. Then, we converted the ${W({\rm CO})/A_V}$ into ${N(\rm H)/A_V}$. Using the WD01 model, we derived the GDR: for ${A_V \le }$ 10 mag, the GDRs were ${118 \pm 9}$ for ${^{12}{\rm CO}}$ and ${83 \pm 62}$ for ${^{13}{\rm CO}}$, comparable to those of the Milky Way; however, for ${A_V \ge }$ 10 mag, the GDRs increased significantly to ${296 \pm 3}$ for ${^{12}{\rm CO}}$ and ${387 \pm 40}$ for ${^{13}{\rm CO}}$, approximately three times higher than those of the Milky Way. In the discussion, we compared the results of this work with previous studies and provided a detailed discussion of the influence of massive stars and other factors on GDR., Comment: 10 pages, 14 figures, 2 tables, Accepted for publication in MNRAS

By analyzing 7.93 $\rm fb^{-1}$ of $e^+e^-$ collision data collected at the center-of-mass energy of 3.773 GeV with the BESIII detector operated at the BEPCII collider, we report the observation of the semimuonic decays of $D^+\to \bar K_1(1270)^0\mu^+\nu_\mu$ and $D^0\to K_1(1270)^-\mu^+\nu_\mu$ with statistical significances of $12.5\sigma$ and $6.0\sigma$, respectively. Their decay branching fractions are determined to be ${\mathcal B}[D^{+}\to \bar{K}_1(1270)^0 \mu^{+}\nu_{\mu}]=(2.36\pm0.20^{+0.18}_{-0.27}\pm 0.48)\times10^{-3}$ and ${\mathcal B}[D^{0}\to K_1(1270)^{-} \mu^{+}\nu_{\mu}]=(0.78\pm0.11^{+0.05}_{-0.09}\pm 0.15)\times10^{-3}$, where the first and second uncertainties are statistical and systematic, respectively, and the third originates from the input branching fraction of $\bar K_{1}(1270)^0\to K^- \pi^+\pi^0$ or $K_1(1270)^-\to K^-\pi^+\pi^-$. Combining our branching fractions with the previous measurements of ${\mathcal B}[D^+\to \bar K_1(1270)^0e^+\nu_{e}]$ and ${\mathcal B}[D^0\to K_1(1270)^-e^+\nu_{e}]$, we determine the branching fraction ratios to be ${\mathcal B}[D^+\to \bar K_1(1270)^0\mu^+\nu_{\mu}]/{\mathcal B}[D^+\to \bar K_1(1270)^0e^+\nu_{e}]=1.03 \pm 0.14 \substack{+0.11\\-0.15}$ and ${\mathcal B}[D^0\to K_1(1270)^-\mu^+\nu_{\mu}]/{\mathcal B}[D^0\to K_1(1270)^-e^+\nu_{e}]=0.74\pm 0.13 \substack{+0.08\\-0.13}$. Using the branching fractions measured in this work and the world-average lifetimes of the $D^+$ and $D^0$ mesons, we determine the semimuonic partial decay width ratio to be $\Gamma [D^+\to \bar K_1(1270)^0 \mu^+\nu_\mu]/\Gamma [D^0\to K_1(1270)^- \mu^+\nu_\mu]=1.22\pm 0.10\substack{+0.06\\-0.09}$, which is consistent with unity as predicted by isospin conservation., Comment: 10 pages, 2 figures

Knowledge Graph-based recommendations have gained significant attention due to their ability to leverage rich semantic relationships. However, constructing and maintaining Knowledge Graphs (KGs) is resource-intensive, and the accuracy of KGs can suffer from noisy, outdated, or irrelevant triplets. Recent advancements in Large Language Models (LLMs) offer a promising way to improve the quality and relevance of KGs for recommendation tasks. Despite this, integrating LLMs into KG-based systems presents challenges, such as efficiently augmenting KGs, addressing hallucinations, and developing effective joint learning methods. In this paper, we propose the Confidence-aware KG-based Recommendation Framework with LLM Augmentation (CKG-LLMA), a novel framework that combines KGs and LLMs for recommendation task. The framework includes: (1) an LLM-based subgraph augmenter for enriching KGs with high-quality information, (2) a confidence-aware message propagation mechanism to filter noisy triplets, and (3) a dual-view contrastive learning method to integrate user-item interactions and KG data. Additionally, we employ a confidence-aware explanation generation process to guide LLMs in producing realistic explanations for recommendations. Finally, extensive experiments demonstrate the effectiveness of CKG-LLMA across multiple public datasets.

In this paper, it is shown that the syndromes of generalized Reed-Solomon (GRS) codes and alternant codes can be characterized in terms of inverse fast Fourier transform, regardless of code definitions. Then a fast decoding algorithm is proposed, which has a computational complexity of $O(n\log(n-k) + (n-k)\log^2(n-k))$ for all $(n,k)$ GRS codes and $(n,k)$ alternant codes. Particularly, this provides a new decoding method for Goppa codes, which is an important subclass of alternant codes. When decoding the binary Goppa code with length $8192$ and correction capability $128$, the new algorithm is nearly 10 times faster than traditional methods. The decoding algorithm is suitable for the McEliece cryptosystem, which is a candidate for post-quantum cryptography techniques.

Lieb-Robinson bounds demonstrate the emergence of locality in many-body quantum systems. Intuitively, Lieb-Robinson bounds state that with local or exponentially decaying interactions, the correlation that can be built up between two sites separated by distance $r$ after a time $t$ decays as $\exp(vt-r)$, where $v$ is the emergent Lieb-Robinson velocity. In many problems, it is important to also capture how much of an operator grows to act on $r^d$ sites in $d$ spatial dimensions. Perturbation theory and cluster expansion methods suggest that at short times, these volume-filling operators are suppressed as $\exp(-r^d)$ at short times. We confirm this intuition, showing that for $r > vt$, the volume-filling operator is suppressed by $\exp(-(r-vt)^d/(vt)^{d-1})$. This closes a conceptual and practical gap between the cluster expansion and the Lieb-Robinson bound. We then present two very different applications of this new bound. Firstly, we obtain improved bounds on the classical computational resources necessary to simulate many-body dynamics with error tolerance $\epsilon$ for any finite time $t$: as $\epsilon$ becomes sufficiently small, only $\epsilon^{-O(t^{d-1})}$ resources are needed. A protocol that likely saturates this bound is given. Secondly, we prove that disorder operators have volume-law suppression near the "solvable (Ising) point" in quantum phases with spontaneous symmetry breaking, which implies a new diagnostic for distinguishing many-body phases of quantum matter., Comment: 32 pages, 8 figures

The exploration of cellular heterogeneity within the tumor microenvironment (TME) via single-cell RNA sequencing (scRNA-seq) is essential for understanding cancer progression and response to therapy. Current scRNA-seq approaches, however, lack spatial context and rely on incomplete datasets of ligand-receptor interactions (LRIs), limiting accurate cell type annotation and cell-cell communication (CCC) inference. This study addresses these challenges using a novel graph neural network (GNN) model that enhances cell type prediction and cell interaction analysis. Our study utilized a dataset consisting of 49,020 cells from 19 patients across three cancer types: Leukemia, Breast Invasive Carcinoma, and Colorectal Cancer. The proposed scGSL model demonstrated robust performance, achieving an average accuracy of 84.83%, precision of 86.23%, recall of 81.51%, and an F1 score of 80.92% across all datasets. These metrics represent a significant enhancement over existing methods, which typically exhibit lower performance metrics. Additionally, by reviewing existing literature on gene interactions within the TME, the scGSL model proves to robustly identify biologically meaningful gene interactions in an unsupervised manner, validated by significant expression differences in key gene pairs across various cancers. The source code and data used in this paper can be found in https://github.com/LiYuechao1998/scGSL., Comment: 29 pages, 6 figures

Functional MRI (fMRI) and single-cell transcriptomics are pivotal in Alzheimer's disease (AD) research, each providing unique insights into neural function and molecular mechanisms. However, integrating these complementary modalities remains largely unexplored. Here, we introduce scBIT, a novel method for enhancing AD prediction by combining fMRI with single-nucleus RNA (snRNA). scBIT leverages snRNA as an auxiliary modality, significantly improving fMRI-based prediction models and providing comprehensive interpretability. It employs a sampling strategy to segment snRNA data into cell-type-specific gene networks and utilizes a self-explainable graph neural network to extract critical subgraphs. Additionally, we use demographic and genetic similarities to pair snRNA and fMRI data across individuals, enabling robust cross-modal learning. Extensive experiments validate scBIT's effectiveness in revealing intricate brain region-gene associations and enhancing diagnostic prediction accuracy. By advancing brain imaging transcriptomics to the single-cell level, scBIT sheds new light on biomarker discovery in AD research. Experimental results show that incorporating snRNA data into the scBIT model significantly boosts accuracy, improving binary classification by 3.39% and five-class classification by 26.59%. The codes were implemented in Python and have been released on GitHub (https://github.com/77YQ77/scBIT) and Zenodo (https://zenodo.org/records/11599030) with detailed instructions., Comment: 31 pages, 5 figures

The advent of 6G communication demands seamlessly integrated terminals operating above 100 GHz with low power consumption for human-centric applications. In this work, we report high-performance, flexible radio-frequency (RF) transistors based on aligned carbon nanotube (CNT) arrays, achieving, for the first time, as-measured current gain cutoff frequency ($f_{\mathrm{T}}$) and power gain cutoff frequency ($f_{\mathrm{max}}$) both exceeding 100 GHz. Electro-thermal co-design improves both heat dissipation and RF performance, despite the low thermal conductivity of the flexible substrate. The transistors deliver 0.947 mA/ $\mathrm{\mu}$m on-state current and 0.728 mS/ $\mathrm{\mu}$m transconductance. Peak extrinsic $f_{\mathrm{T}}$ and $f_{\mathrm{max}}$ reach 152 GHz and 102 GHz, with low power consumption of 199 mW/mm and 147 mW/mm, respectively, setting new performance records for flexible CNT-based RF transistors by nearly 100$\times$, outperforming all other flexible RF devices. Additionally, flexible RF amplifiers achieve output power of 64 mW/mm and power gain of 11 dB in the K-band (18 GHz), marking a significant milestone in the development of flexible RF technologies for next-generation wireless communication systems., Comment: 34 pages, 15 figures

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared embedding space with the LLM while preserving semantic similarity. Existing connectors, such as multilayer perceptrons (MLPs), often produce out-of-distribution or noisy inputs, leading to misalignment between the modalities. In this work, we propose a novel vision-text alignment method, AlignVLM, that maps visual features to a weighted average of LLM text embeddings. Our approach leverages the linguistic priors encoded by the LLM to ensure that visual features are mapped to regions of the space that the LLM can effectively interpret. AlignVLM is particularly effective for document understanding tasks, where scanned document images must be accurately mapped to their textual content. Our extensive experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods. We provide further analysis demonstrating improved vision-text feature alignment and robustness to noise.

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized tasks, can inadvertently degrade their safety alignment, even when the datasets are benign. This phenomenon makes models more susceptible to providing inappropriate responses. In this study, we systematically examine the factors contributing to safety alignment degradation in benign fine-tuning scenarios. Our analysis identifies three critical factors affecting aligned LLMs: answer structure, identity calibration, and role-play. Additionally, we evaluate the reliability of state-of-the-art reward models (RMs), which are often used to guide alignment processes. Our findings reveal that these RMs frequently fail to accurately reflect human preferences regarding safety, underscoring their limitations in practical applications. By uncovering these challenges, our work highlights the complexities of maintaining safety alignment during fine-tuning and offers guidance to help developers balance utility and safety in LLMs. Datasets and fine-tuning code used in our experiments can be found in https://github.com/GuanlinLee/llm_instruction_tuning.

End-to-end human animation, such as audio-driven talking human generation, has undergone notable advancements in the recent few years. However, existing methods still struggle to scale up as large general video generation models, limiting their potential in real applications. In this paper, we propose OmniHuman, a Diffusion Transformer-based framework that scales up data by mixing motion-related conditions into the training phase. To this end, we introduce two training principles for these mixed conditions, along with the corresponding model architecture and inference strategy. These designs enable OmniHuman to fully leverage data-driven motion generation, ultimately achieving highly realistic human video generation. More importantly, OmniHuman supports various portrait contents (face close-up, portrait, half-body, full-body), supports both talking and singing, handles human-object interactions and challenging body poses, and accommodates different image styles. Compared to existing end-to-end audio-driven methods, OmniHuman not only produces more realistic videos, but also offers greater flexibility in inputs. It also supports multiple driving modalities (audio-driven, video-driven and combined driving signals). Video samples are provided on the ttfamily project page (https://omnihuman-lab.github.io), Comment: https://omnihuman-lab.github.io/

Large Visual Language Models (LVLMs) integrate visual and linguistic modalities, exhibiting exceptional performance across various multimodal tasks. Nevertheless, LVLMs remain vulnerable to the issue of object hallucinations. Previous efforts to mitigate this issue focus on supervised fine-tuning (SFT) or incorporating external knowledge, both of which entail significant costs related to training and the acquisition of external data. To address these challenges, we propose a novel model-agnostic approach termed Internal Fact-based Contrastive Decoding (IFCD), designed to mitigate and suppress hallucinations during the inference process of LVLMs by exploiting the LVLMs' own hallucinations. IFCD is grounded in experimental observations that alterations to the LVLMs' internal representations tend to amplify hallucinations caused by language bias. By contrasting disturbed distribution, IFCD calibrates the LVLMs' output and effectively removes the hallucinatory logits from the final predictions. Experimental results validate that IFCD significantly alleviates both object-level and attribute-level hallucinations while achieving an average 9% accuracy improvement on POPE and 8% accuracy improvement on MME object hallucinations subset compared with direct decoding, respectively.

Recently, the field of text-guided 3D scene generation has garnered significant attention. High-quality generation that aligns with physical realism and high controllability is crucial for practical 3D scene applications. However, existing methods face fundamental limitations: (i) difficulty capturing complex relationships between multiple objects described in the text, (ii) inability to generate physically plausible scene layouts, and (iii) lack of controllability and extensibility in compositional scenes. In this paper, we introduce LayoutDreamer, a framework that leverages 3D Gaussian Splatting (3DGS) to facilitate high-quality, physically consistent compositional scene generation guided by text. Specifically, given a text prompt, we convert it into a directed scene graph and adaptively adjust the density and layout of the initial compositional 3D Gaussians. Subsequently, dynamic camera adjustments are made based on the training focal point to ensure entity-level generation quality. Finally, by extracting directed dependencies from the scene graph, we tailor physical and layout energy to ensure both realism and flexibility. Comprehensive experiments demonstrate that LayoutDreamer outperforms other compositional scene generation quality and semantic alignment methods. Specifically, it achieves state-of-the-art (SOTA) performance in the multiple objects generation metric of T3Bench.

Multi-agent reinforcement learning (MARL) has made significant progress, largely fueled by the development of specialized testbeds that enable systematic evaluation of algorithms in controlled yet challenging scenarios. However, existing testbeds often focus on purely virtual simulations or limited robot morphologies such as robotic arms, quadrupeds, and humanoids, leaving high-mobility platforms with real-world physical constraints like drones underexplored. To bridge this gap, we present VolleyBots, a new MARL testbed where multiple drones cooperate and compete in the sport of volleyball under physical dynamics. VolleyBots features a turn-based interaction model under volleyball rules, a hierarchical decision-making process that combines motion control and strategic play, and a high-fidelity simulation for seamless sim-to-real transfer. We provide a comprehensive suite of tasks ranging from single-drone drills to multi-drone cooperative and competitive tasks, accompanied by baseline evaluations of representative MARL and game-theoretic algorithms. Results in simulation show that while existing algorithms handle simple tasks effectively, they encounter difficulty in complex tasks that require both low-level control and high-level strategy. We further demonstrate zero-shot deployment of a simulation-learned policy to real-world drones, highlighting VolleyBots' potential to propel MARL research involving agile robotic platforms. The project page is at https://sites.google.com/view/thu-volleybots/home.

Linguistic steganography aims to conceal information within natural language text without being detected. An effective steganography approach should encode the secret message into a minimal number of language tokens while preserving the natural appearance and fluidity of the stego-texts. We present a new framework to enhance the embedding efficiency of stego-texts generated by modifying the output of a large language model (LLM). The novelty of our approach is in abstracting the sequential steganographic embedding process as a Constrained Markov Decision Process (CMDP), which takes into consideration the long-term dependencies instead of merely the immediate effects. We constrain the solution space such that the discounted accumulative total variation divergence between the selected probability distribution and the original distribution given by the LLM is below a threshold. To find the optimal policy, we first show that the functional optimization problem can be simplified to a convex optimization problem with a finite number of variables. A closed-form solution for the optimal policy is then presented to this equivalent problem. It is remarkable that the optimal policy is deterministic and resembles water-filling in some cases. The solution suggests that usually adjusting the probability distribution for the state that has the least random transition probability should be prioritized, but the choice should be made by taking into account the transition probabilities at all states instead of only the current state., Comment: 13 pages

Retrieval-Augmented Generation (RAG) has demonstrated remarkable success in enhancing Large Language Models (LLMs) through external knowledge integration, yet its application has primarily focused on textual content, leaving the rich domain of multi-modal video knowledge predominantly unexplored. This paper introduces VideoRAG, the first retrieval-augmented generation framework specifically designed for processing and understanding extremely long-context videos. Our core innovation lies in its dual-channel architecture that seamlessly integrates (i) graph-based textual knowledge grounding for capturing cross-video semantic relationships, and (ii) multi-modal context encoding for efficiently preserving visual features. This novel design empowers VideoRAG to process unlimited-length videos by constructing precise knowledge graphs that span multiple videos while maintaining semantic dependencies through specialized multi-modal retrieval paradigms. Through comprehensive empirical evaluation on our proposed LongerVideos benchmark-comprising over 160 videos totaling 134+ hours across lecture, documentary, and entertainment categories-VideoRAG demonstrates substantial performance compared to existing RAG alternatives and long video understanding methods. The source code of VideoRAG implementation and the benchmark dataset are openly available at: https://github.com/HKUDS/VideoRAG.

The discovery of superconductivity with onset temperature of ~80 K in pressurized bilayer Ruddlesden-Popper La3Ni2O7-d has attracted much attention. Despite intense research, determination of the exact oxygen content and understanding of the relationship between superconductivity and oxygen content remain a big challenge. Here, we report a systematical study on the structure and physical properties of La3Ni2O7-d polycrystalline powders which were prepared using sol-gel method at ambient pressure and then annealed under various oxygen pressure. We found that high pO2 annealing with slow cooling results in a new phase, which can be modeled using the hybrid single-layer-trilayer La3Ni2O7 or the tetragonal bilayer La3Ni2O7. Scanning transmission electron microscopy (STEM) measurements revealed significant single layers and trilayers after high oxygen pressure annealing, evidencing damage of the bilayer structure. The superconducting transition under high pressure became weak for high pO2 annealed samples, which is consistent with the damage of the bilayer structure. Our results reveal that the bilayer structure is fragile and post-annealing under near atmosphere pressure of oxygen is suitable to maintain bilayer structure and increase oxygen content at the same time., Comment: 5 figures and 1 table

The Hong-Ou-Mandel effect is a paradigmatic quantum phenomenon demonstrating the interference of two indistinguishable photons that are linearly coupled at a 50:50 beam splitter. Here, we transpose such a two-particle quantum interference effect to the nonlinear regime, when two single photons are impinging on a parametric down-conversion crystal. Formally, this transposition amounts to exchanging space and time variables, giving rise to an unknown form of timelike quantum interference. The two-photon component of the output state is a superposition of the incident photons being either transmitted or reborn, that is, replaced by indistinguishable substitutes due to their interaction with the nonlinear crystal. We experimentally demonstrate the suppression of the probability of detecting precisely one photon pair when the amplification gain is tuned to 2, which arises from the destructive interference between the transmitted and reborn photon pairs. This heretofore unobserved quantum manifestation of indistinguishability in time pushes nonlinear quantum interference towards a new regime with multiple photons. Hence, composing this effect with larger linear optical circuits should provide a tool to generate multimode quantum non-Gaussian states, which are essential resources for photonic quantum computers.

Hallucination has been a long-standing and inevitable problem that hinders the application of Large Vision-Language Models (LVLMs) in domains that require high reliability. Various methods focus on improvement depending on data annotations or training strategies, yet place less emphasis on LLM's inherent problems. To fill this gap, we delve into the attention mechanism of the decoding process in the LVLM. Intriguingly, our investigation uncovers the prevalent attention redundancy within the hierarchical architecture of the LVLM, manifesting as overextended image processing in deep layers and an overabundance of non-essential image tokens. Stemming from the observation, we thus propose MINT, a novel training-free decoding strategy, MItigating hallucinations via tokeN reducTion. Specifically, we dynamically intensify the LVLM's local perception capability by masking its attention to irrelevant image tokens. In addition, we use contrastive decoding that pushes the model to focus more on those key image regions. Our full method aims to guide the model in concentrating more on key visual elements during generation. Extensive experimental results on several popular public benchmarks show that our approach achieves a 4% improvement in mitigating hallucinations caused by distracted perception compared to original models. Meanwhile, our approach is demonstrated to make the model perceive 5% more visual points even though we reduce a suite of image tokens., Comment: 8 pages, 5 figures, 4 tables

Visual reasoning refers to the task of solving questions about visual information. Current visual reasoning methods typically employ pre-trained vision-language model (VLM) strategies or deep neural network approaches. However, existing efforts are constrained by limited reasoning interpretability, while hindering by the phenomenon of underspecification in the question text. Additionally, the absence of fine-grained visual knowledge limits the precise understanding of subject behavior in visual reasoning tasks. To address these issues, we propose VIKSER (Visual Knowledge-Driven Self-Reinforcing Reasoning Framework). Specifically, VIKSER, trained using knowledge distilled from large language models, extracts fine-grained visual knowledge with the assistance of visual relationship detection techniques. Subsequently, VIKSER utilizes fine-grained visual knowledge to paraphrase the question with underspecification. Additionally, we design a novel prompting method called Chain-of-Evidence (CoE), which leverages the power of ``evidence for reasoning'' to endow VIKSER with interpretable reasoning capabilities. Meanwhile, the integration of self-reflection technology empowers VIKSER with the ability to learn and improve from its mistakes. Experiments conducted on widely used datasets demonstrate that VIKSER achieves new state-of-the-art (SOTA) results in relevant tasks., Comment: 17 pages,12 figures

Text-to-3D asset generation has achieved significant optimization under the supervision of 2D diffusion priors. However, when dealing with compositional scenes, existing methods encounter several challenges: 1). failure to ensure that composite scene layouts comply with physical laws; 2). difficulty in accurately capturing the assets and relationships described in complex scene descriptions; 3). limited autonomous asset generation capabilities among layout approaches leveraging large language models (LLMs). To avoid these compromises, we propose a novel framework for compositional scene generation, PhiP-G, which seamlessly integrates generation techniques with layout guidance based on a world model. Leveraging LLM-based agents, PhiP-G analyzes the complex scene description to generate a scene graph, and integrating a multimodal 2D generation agent and a 3D Gaussian generation method for targeted assets creation. For the stage of layout, PhiP-G employs a physical pool with adhesion capabilities and a visual supervision agent, forming a world model for layout prediction and planning. Extensive experiments demonstrate that PhiP-G significantly enhances the generation quality and physical rationality of the compositional scenes. Notably, PhiP-G attains state-of-the-art (SOTA) performance in CLIP scores, achieves parity with the leading methods in generation quality as measured by the T$^3$Bench, and improves efficiency by 24x., Comment: 13 pages.8 figures

Recent advances in mathematical problem-solving with language models (LMs) integrate chain-of-thought (CoT) reasoning and code execution to harness their complementary strengths. However, existing hybrid frameworks exhibit a critical limitation: they depend on externally dictated instructions or rigid code-integration templates, lacking metacognitive awareness -- the capacity to dynamically evaluate intrinsic capabilities and autonomously determine when and how to integrate tools. This rigidity motivates our study of autonomous code integration, enabling models to adapt tool-usage strategies as their reasoning abilities evolve during training. While reinforcement learning (RL) shows promise for boosting LLM reasoning at scale (e.g., DeepSeek-R1), we demonstrate its inefficiency in learning autonomous code integration due to inadequate exploration of the vast combinatorial space of CoT-code interleaving patterns. To address this challenge, we propose a novel Expectation-Maximization (EM) framework that synergizes structured exploration (E-step) with off-policy RL optimization (M-step), creating a self-reinforcing cycle between metacognitive tool-use decisions and evolving capabilities. Experiments reveal our method achieves superior results through improved exploration. Notably, our 7B model improves over 11% on MATH500 and 9.4% on AIME without o1-like CoT.

The rise of single-cell sequencing technologies has revolutionized the exploration of drug resistance, revealing the crucial role of cellular heterogeneity in advancing precision medicine. By building computational models from existing single-cell drug response data, we can rapidly annotate cellular responses to drugs in subsequent trials. To this end, we developed scGSDR, a model that integrates two computational pipelines grounded in the knowledge of cellular states and gene signaling pathways, both essential for understanding biological gene semantics. scGSDR enhances predictive performance by incorporating gene semantics and employs an interpretability module to identify key pathways contributing to drug resistance phenotypes. Our extensive validation, which included 16 experiments covering 11 drugs, demonstrates scGSDR's superior predictive accuracy, when trained with either bulk-seq or scRNA-seq data, achieving high AUROC, AUPR, and F1 Scores. The model's application has extended from single-drug predictions to scenarios involving drug combinations. Leveraging pathways of known drug target genes, we found that scGSDR's cell-pathway attention scores are biologically interpretable, which helped us identify other potential drug-related genes. Literature review of top-ranking genes in our predictions such as BCL2, CCND1, the AKT family, and PIK3CA for PLX4720; and ICAM1, VCAM1, NFKB1, NFKBIA, and RAC1 for Paclitaxel confirmed their relevance. In conclusion, scGSDR, by incorporating gene semantics, enhances predictive modeling of cellular responses to diverse drugs, proving invaluable for scenarios involving both single drug and combination therapies and effectively identifying key resistance-related pathways, thus advancing precision medicine and targeted therapy development.

Data-driven research is becoming a new paradigm in transportation, but the natural lack of individual socio-economic attributes in transportation data makes research such as activity purpose inference and mobility pattern identification lack convincingness and verifiability. In this paper, a two-stage trip purpose and socio-economic attributes inference model is proposed based on travel resident survey and smart card data. In the first stage, the trip purpose of each trip is inferred by a combination of rule-based and XGBoost models. In the second stage, based on the trip purpose, a machine-learning model is built to inference the socio-economic attributes of individuals. A teacher-student model based on self-training is then applied on the models above to transfer them to smart card data. The impact of independent variables of socio-economic attributes inference model is also investigated. The results show that models for inferring trip purposes and socio-economic attributes have overall accuracies of 92.7% and 76.3%, respectively. Travel time, arrival time, departure time and purpose of the first two trips are most important factors on age and job status, while the land price of jobs-housing are significant to the inference of individual incomes.

We study superfluid drag in the two-component, two-dimensional Bose-Hubbard model with infinitely strong repulsive interactions. We demonstrate, with a combination of analytic and numeric techniques, that the motion of holes leads to strong dissipationless coupling between currents in the two components. We show that this behavior is attributable to polaronic correlations that emerge in the presence of spin currents, and which can be observed in experiments., Comment: 9 pages, 5 figures

Large Language Model (LLM) agents frameworks often employ modular architectures, incorporating components such as planning, reasoning, action execution, and reflection to tackle complex tasks. However, quantifying the contribution of each module to overall system performance remains a significant challenge, impeding optimization and interpretability. To address this, we introduce CapaBench (Capability-level Assessment Benchmark), an evaluation framework grounded in cooperative game theory's Shapley Value, which systematically measures the marginal impact of individual modules and their interactions within an agent's architecture. By replacing default modules with test variants across all possible combinations, CapaBench provides a principle method for attributing performance contributions. Key contributions include: (1) We are the first to propose a Shapley Value-based methodology for quantifying the contributions of capabilities in LLM agents; (2) Modules with high Shapley Values consistently lead to predictable performance gains when combined, enabling targeted optimization; and (3) We build a multi-round dataset of over 1,500 entries spanning diverse domains and practical task scenarios, enabling comprehensive evaluation of agent capabilities. CapaBench bridges the gap between component-level evaluation and holistic system assessment, providing actionable insights for optimizing modular LLM agents and advancing their deployment in complex, real-world scenarios.

Reinforcement learning (RL) for continuous control often requires large amounts of online interaction data. Value-based RL methods can mitigate this burden by offering relatively high sample efficiency. Some studies further enhance sample efficiency by incorporating offline demonstration data to "kick-start" training, achieving promising results in continuous control. However, they typically compute the Q-function independently for each action dimension, neglecting interdependencies and making it harder to identify optimal actions when learning from suboptimal data, such as non-expert demonstration and online-collected data during the training process. To address these issues, we propose Auto-Regressive Soft Q-learning (ARSQ), a value-based RL algorithm that models Q-values in a coarse-to-fine, auto-regressive manner. First, ARSQ decomposes the continuous action space into discrete spaces in a coarse-to-fine hierarchy, enhancing sample efficiency for fine-grained continuous control tasks. Next, it auto-regressively predicts dimensional action advantages within each decision step, enabling more effective decision-making in continuous control tasks. We evaluate ARSQ on two continuous control benchmarks, RLBench and D4RL, integrating demonstration data into online training. On D4RL, which includes non-expert demonstrations, ARSQ achieves an average $1.62\times$ performance improvement over SOTA value-based baseline. On RLBench, which incorporates expert demonstrations, ARSQ surpasses various baselines, demonstrating its effectiveness in learning from suboptimal online-collected data.

The attosecond light source provides an advanced tool for investigating electron motion using time-resolved-spectroscopy techniques. Isolated attosecond pulses, especially, will significantly advance the study of electron dynamics. However, achieving high-intensity isolated attosecond pulses is still challenging at the present stage. In this paper, we propose a novel scheme for generating high-intensity, isolated attosecond soft X-ray free-electron lasers (FELs) using a mid-infrared (MIR) sub-cycle modulation laser from gas-filled hollow capillary fibers (HCFs). The multi-cycle MIR pulses are first compressed to sub-cycle using a helium-filled HCF with decreasing pressure gradient due to soliton self-compression effect. By utilizing such sub-cycle MIR laser pulse to modulate the electron beam, we can obtain a quasi-isolated current peak, which can then produce an isolated FEL pulse with high signal-to-noise ratio (SNR), naturally synchronizing with the sub-cycle MIR laser pulse. Numerical simulations have been carried out, including the sub-cycle pulse generation, electron beam modulation and FEL radiation processes. The simulation results indicate that an isolated attosecond pulse with wavelength of 1 nm, peak power of ~28 GW, pulse duration of ~600 attoseconds and SNR of ~96.4% can be generated by our proposed method. The numerical results demonstrated here pave a new way for generating the high-intensity isolated attosecond soft X-ray pulse, which may have many applications in nonlinear spectroscopy and atomic-site electronic process.

Image denoising of low-dose computed tomography (LDCT) is an important problem for clinical diagnosis with reduced radiation exposure. Previous methods are mostly trained with pairs of synthetic or misaligned LDCT and normal-dose CT (NDCT) images. However, trained with synthetic noise or misaligned LDCT/NDCT image pairs, the denoising networks would suffer from blurry structure or motion artifacts. Since non-contrast CT (NCCT) images share the content characteristics to the corresponding NDCT images in a three-phase scan, they can potentially provide useful information for real-world LDCT image denoising. To exploit this aspect, in this paper, we propose to incorporate clean NCCT images as useful guidance for the learning of real-world LDCT image denoising networks. To alleviate the issue of spatial misalignment in training data, we design a new Patch Triplet Similarity Purification (PTSP) strategy to select highly similar patch (instead of image) triplets of LDCT, NDCT, and NCCT images for network training. Furthermore, we modify two image denoising transformers of SwinIR and HAT to accommodate the NCCT image guidance, by replacing vanilla self-attention with cross-attention. On our collected clinical dataset, the modified transformers trained with the data selected by our PTSP strategy show better performance than 15 comparison methods on real-world LDCT image denoising. Ablation studies validate the effectiveness of our NCCT image guidance and PTSP strategy. We will publicly release our data and code.

Balancing competing objectives remains a fundamental challenge in multi-task learning (MTL), primarily due to conflicting gradients across individual tasks. A common solution relies on computing a dynamic gradient update vector that balances competing tasks as optimization progresses. Building on this idea, we propose ConicGrad, a principled, scalable, and robust MTL approach formulated as a constrained optimization problem. Our method introduces an angular constraint to dynamically regulate gradient update directions, confining them within a cone centered on the reference gradient of the overall objective. By balancing task-specific gradients without over-constraining their direction or magnitude, ConicGrad effectively resolves inter-task gradient conflicts. Moreover, our framework ensures computational efficiency and scalability to high-dimensional parameter spaces. We conduct extensive experiments on standard supervised learning and reinforcement learning MTL benchmarks, and demonstrate that ConicGrad achieves state-of-the-art performance across diverse tasks., Comment: 16 pages, 7 figures, 5 tables

The training and fine-tuning of large language models (LLMs) often involve diverse textual data from multiple sources, which poses challenges due to conflicting gradient directions, hindering optimization and specialization. These challenges can undermine model generalization across tasks, resulting in reduced downstream performance. Recent research suggests that fine-tuning LLMs on carefully selected, task-specific subsets of data can match or even surpass the performance of using the entire dataset. Building on these insights, we propose the Ensembles of Low-Rank Expert Adapters (ELREA) framework to improve the model's capability to handle diverse tasks. ELREA clusters the training instructions based on their gradient directions, representing different areas of expertise and thereby reducing conflicts during optimization. Expert adapters are then trained on these clusters, utilizing the low-rank adaptation (LoRA) technique to ensure training efficiency and model scalability. During inference, ELREA combines predictions from the most relevant expert adapters based on the input data's gradient similarity to the training clusters, ensuring optimal adapter selection for each task. Experiments show that our method outperforms baseline LoRA adapters trained on the full dataset and other ensemble approaches with similar training and inference complexity across a range of domain-specific tasks., Comment: 29 pages, 5 figures, 5 tables; proceedings in ICLR 2025

In Transformer-based sequence-to-sequence generation, beam search has proven effective in enhancing the quality of generated sequences compared to greedy decoding. Conventional beam search methods typically adopt either a sequential or batch-based approach. The sequential approach, while memory-efficient, requires multiple decoding passes to construct a complete search tree, leading to significantly slower inference. On the other hand, the batch-based approach enables parallel computation across beams, but at the expense of high memory consumption due to the need to maintain separate key-value (KV) caches for each beam. In this study, we introduce a novel trie (prefix-tree)-based parallel decoding method that addresses the memory inefficiency of batch-based beam search. By sharing a single KV cache among all beams that share the same prefix, the proposed method not only reduces memory consumption dramatically but also enables parallel decoding across all branches. This innovative use of a prefix tree offers an efficient alternative for beam search, achieving significant memory savings while preserving inference speed, making it particularly well-suited for memory-constrained environments or large-scale model deployments., Comment: 9 pages

Brain-inspired computing architectures attempt to emulate the computations performed in the neurons and the synapses in human brain. Memristors with continuously tunable resistances are ideal building blocks for artificial synapses. Through investigating the memristor behaviors in a La0.7Sr0.3MnO3/BaTiO3/La0.7Sr0.3MnO3 multiferroic tunnel junction, it was found that the ferroelectric domain dynamics characteristics are influenced by the relative magnetization alignment of the electrodes, and the interfacial spin polarization is manipulated continuously by ferroelectric domain reversal, enriching our understanding of the magnetoelectric coupling fundamentally. This creates a functionality that not only the resistance of the memristor but also the synaptic plasticity form can be further manipulated, as demonstrated by the spike-timing-dependent plasticity investigations. Density functional theory calculations are carried out to describe the obtained magnetoelectric coupling, which is probably related to the Mn-Ti intermixing at the interfaces. The multiple and controllable plasticity characteristic in a single artificial synapse, to resemble the synaptic morphological alteration property in a biological synapse, will be conducive to the development of artificial intelligence., Comment: 5 figures, 20 pages

Functionalities in crystalline materials are determined by 3-dimensional collective interactions of atoms. The confinement of dimensionality in condensed matter provides an exotic research direction to understand the interaction of atoms, thus can be used to tailor or create new functionalities in material systems. In this study, a 2-dimensional transition metal oxide monolayer is constructed inside complex oxide heterostructures based on the theoretical predictions. The electrostatic boundary conditions of oxide monolayer in the heterostructure is carefully designed to tune the chemical, electronic, and magnetic states of oxide monolayer. The challenge of characterizing such an oxide monolayer is overcome by a combination of transmission electron microscopy, x-ray absorption spectroscopy, cross-sectional scanning tunneling microscopy, and electrical transport measurements. An intriguing metal-insulator transition associated with a magnetic transition is discovered in the MnO2 monolayer. This study paves a new route to understand the confinement of dimensionality and explore new intriguing phenomena in condensed matters., Comment: 23 pages, 6 figures

Decentralized Federated Learning (DFL) enables collaborative, privacy-preserving model training without relying on a central server. This decentralized approach reduces bottlenecks and eliminates single points of failure, enhancing scalability and resilience. However, DFL also introduces challenges such as suboptimal models with non-IID data distributions, increased communication overhead, and resource usage. Thus, this work proposes S-VOTE, a voting-based client selection mechanism that optimizes resource usage and enhances model performance in federations with non-IID data conditions. S-VOTE considers an adaptive strategy for spontaneous local training that addresses participation imbalance, allowing underutilized clients to contribute without significantly increasing resource costs. Extensive experiments on benchmark datasets demonstrate the S-VOTE effectiveness. More in detail, it achieves lower communication costs by up to 21%, 4-6% faster convergence, and improves local performance by 9-17% compared to baseline methods in some configurations, all while achieving a 14-24% energy consumption reduction. These results highlight the potential of S-VOTE to address DFL challenges in heterogeneous environments., Comment: Submitted to IJCNN

Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also posed limitations on their application. Building upon the tremendous success of autoregressive models in the language domain, we propose \textbf{VARSR}, a novel visual autoregressive modeling for ISR framework with the form of next-scale prediction. To effectively integrate and preserve semantic information in low-resolution images, we propose using prefix tokens to incorporate the condition. Scale-aligned Rotary Positional Encodings are introduced to capture spatial structures and the diffusion refiner is utilized for modeling quantization residual loss to achieve pixel-level fidelity. Image-based Classifier-free Guidance is proposed to guide the generation of more realistic images. Furthermore, we collect large-scale data and design a training process to obtain robust generative priors. Quantitative and qualitative results show that VARSR is capable of generating high-fidelity and high-realism images with more efficiency than diffusion-based methods. Our codes will be released at https://github.com/qyp2000/VARSR., Comment: 20 pages; 17 figures

Dissociated neuronal cultures provide a simplified yet effective model system for investigating self-organized prediction and information processing in neural networks. This review consolidates current research demonstrating that these in vitro networks display fundamental computational capabilities, including predictive coding, adaptive learning, goal-directed behavior, and deviance detection. We examine how these cultures develop critical dynamics optimized for information processing, detail the mechanisms underlying learning and memory formation, and explore the relevance of the free energy principle within these systems. Building on these insights, we discuss how findings from dissociated neuronal cultures inform the design of neuromorphic and reservoir computing architectures, with the potential to enhance energy efficiency and adaptive functionality in artificial intelligence. The reduced complexity of neuronal cultures allows for precise manipulation and systematic investigation, bridging theoretical frameworks with practical implementations in bio-inspired computing. Finally, we highlight promising future directions, emphasizing advancements in three-dimensional culture techniques, multi-compartment models, and brain organoids that deepen our understanding of hierarchical and predictive processes in both biological and artificial systems. This review aims to provide a comprehensive overview of how dissociated neuronal cultures contribute to neuroscience and artificial intelligence, ultimately paving the way for biologically inspired computing solutions., Comment: 39 pages, 4 figures

Large Language Models (LLMs) have been extensively applied in time series analysis. Yet, their utility in the few-shot classification (i.e., a crucial training scenario due to the limited training data available in industrial applications) concerning multivariate time series data remains underexplored. We aim to leverage the extensive pre-trained knowledge in LLMs to overcome the data scarcity problem within multivariate time series. Specifically, we propose LLMFew, an LLM-enhanced framework to investigate the feasibility and capacity of LLMs for few-shot multivariate time series classification. This model introduces a Patch-wise Temporal Convolution Encoder (PTCEnc) to align time series data with the textual embedding input of LLMs. We further fine-tune the pre-trained LLM decoder with Low-rank Adaptations (LoRA) to enhance its feature representation learning ability in time series data. Experimental results show that our model outperformed state-of-the-art baselines by a large margin, achieving 125.2% and 50.2% improvement in classification accuracy on Handwriting and EthanolConcentration datasets, respectively. Moreover, our experimental results demonstrate that LLM-based methods perform well across a variety of datasets in few-shot MTSC, delivering reliable results compared to traditional models. This success paves the way for their deployment in industrial environments where data are limited.

The emergence of the Next Generation Sequencing increases drastically the volume of transcriptomic data. Although many standalone algorithms and workflows for novel microRNA (miRNA) prediction have been proposed, few are designed for processing large volume of sequence data from large genomes, and even fewer further annotate functional miRNAs by analyzing multiple libraries. We propose an improved pipeline for a high volume data facility by implementing mirLibSpark based on the Apache Spark framework. This pipeline is the fastest actual method, and provides an accuracy improvement compared to the standard. In this paper, we deliver the first distributed functional miRNA predictor as a standalone and fully automated package. It is an efficient and accurate miRNA predictor with functional insight. Furthermore, it compiles with the gold-standard requirement on plant miRNA predictions., Comment: 13 pages, 4 figures, 2 tables, published in conference proceedings