arXiv:2602.00423v3 Announce Type: replace
Abstract: Single-cell integration workflows often construct low-dimensional cell embeddings and then refine them with post-hoc methods to reduce batch effects. This refinement process can become unstable when cell-type compositions vary across batches, with some populations underrepresented or absent in particular batches. The problem becomes more consequential in dynamic single-cell data systems, where newly acquired batches can change both technical conditions and cell-type composition. Such instability can reduce downstream cell-type classification performance and weaken stability under imbalance perturbations. We introduce scBatchProx, a lightweight post-hoc refinement method for stabilizing single-cell latent embeddings in these heterogeneous and evolving settings. scBatchProx operates directly on precomputed embeddings and treats each batch or study as a client in a federated-inspired optimization procedure. A batch-conditioned FiLM adapter learns local latent updates, while proximal and identity-preserving regularization keep these updates conservative. Experiments on multi-batch and cross-study single-cell datasets show that scBatchProx improves downstream cell-type classification across different upstream embeddings. In controlled imbalance perturbations, scBatchProx maintains more stable affected-cell-type F1 when selected populations are downsampled or ablated from one batch. In cumulative retraining and continual integration settings, scBatchProx remains effective as new datasets arrive over time. Together, these results suggest that conservative, federated-inspired refinement can help maintain stable single-cell embeddings as batch compositions change across datasets and over time.
Science Journals
arXiv:2606.03950v1 Announce Type: new
Abstract: Two-dimensional higher-order topological insulators are typically classified either as dipolar or quadrupolar depending on the relevant invariant. These two classes were previously considered non-overlapping. Here we put forward an example system exhibiting dipolar and quadrupolar higher-order topology simultaneously, suggest its implementation using the arrays of laser-written evanescently coupled optical waveguides and support our conclusions by the full-wave numerical simulations.
arXiv:2606.02992v1 Announce Type: new
Abstract: Graph indexes are widely used for high-recall approximate nearest neighbor search (ANNS), but many real-time applications require streaming ANNS. In these real-time applications, continuously arriving embeddings must search the existing graph for candidate neighbors before updating graph edges, which makes repeated index construction a bottleneck for streaming ingestion workloads. We propose Slipstream, a new method that significantly reduces the computational cost of frequent insertions in graph indexes for ANNS. The core idea of Slipstream is exploiting the continuity in vector streams: the newly arrived point starts from promising candidates found during the previous insertion rather than searching from the entry point. More technically, Slipstream evaluates distinct subsets of starting candidates followed by an adaptive controller that narrows or widens the range according to the stream's stability. We further show that Slipstream is beyond heuristic: We derive an abstract model to characterize Slipstream's performance and analyze its theoretical bounds. We have implemented Slipstream in two popular open-source libraries (Faiss, HNSWLib) and compared it with four baseline methods on five streaming vector datasets. Experimental results show that Slipstream achieves up to 30.8$\times$ higher end-to-end throughput than baselines while maintaining at least 0.95 recall@10.
arXiv:2512.17575v2 Announce Type: replace
Abstract: We present an analytical model for the frequency response of a gas microbubble oscillating near a spherical inclusion of arbitrary size and mechanical nature (rigid, fluid, or viscoelastic) immersed in a viscous compressible fluid. The model considers both radial and nonspherical oscillations in the linear regime and predicts how their resonance frequencies and oscillation amplitudes are altered by the bubble size, material properties, and distance to the nearby sphere. As a key application, we demonstrate that scanning the frequency response of a bubble near a viscoelastic object, such as an erythrocyte-like particle mimicking a biological cell, offers a way to recover its mechanical properties through inverse modeling, opening new possibilities for high-resolution elastography at the microscale.
arXiv:2605.18106v3 Announce Type: replace-cross
Abstract: A striking geometric disparity has long persisted in the practice of deep learning. While modern neural network architectures naturally exhibit rich symmetry and equivariance properties, popular optimizers such as Adam and its variants operate inherently coordinate-wise, rendering them unable to respect the equivariance structures of the parameter space. We address this disparity by introducing a symmetry-compatible principle for optimizer design: the gradient update rule should be equivariant under the symmetry group acting on the corresponding weight block. Following this principle, we first provide a unified perspective on bi-orthogonally equivariant updates for general matrix layers, as employed by stochastic spectral descent, Muon, Scion, and polar gradient methods. More importantly, by moving from orthogonal groups to permutation and shared-shift symmetries, we derive symmetry-compatible optimizers for parameter blocks whose symmetries differ from those of general matrix layers: embedding and LM head matrices, SwiGLU MLP projections, and MoE router matrices. These constructions include one-sided spectral, row-norm, hybrid row-norm/spectral, row-aware, column-aware, centered row-norm, and left-spectral updates. They yield an end-to-end layerwise optimizer stack in which each major matrix-valued parameter class is assigned an update whose equivariance matches its symmetry group. We corroborate this principle through pre-training experiments on dense and sparse MoE language models, including Qwen3-0.6B-style, Gemma 3 1B-style, OLMoE-1B-7B-style, and downsized gpt-oss architectures. Across these experiments, symmetry-compatible update rules consistently improve final validation loss, reduce load imbalance in sparse MoE models, and in several cases improve training stability over the corresponding AdamW updates.
arXiv:2605.11607v2 Announce Type: replace-cross
Abstract: Probabilistic partial least squares (PPLS) is a central likelihood-based model for two-view learning when one needs both interpretable latent factors and calibrated uncertainty. Building on the identifiable parameterization of Bouhaddani et al.\ (2018), existing fitting pipelines still face two practical bottlenecks: noise--signal coupling under joint EM/ECM updates and nontrivial handling of orthogonality constraints. Following the fixed-noise scalar-likelihood protocol, we develop an end-to-end framework that combines noise pre-estimation, constrained likelihood optimization, and prediction calibration in one pipeline. We estimate the observation noise from the low-eigenvalue noise subspace and enforce orthogonality through exact Stiefel-manifold optimization. The noise-subspace estimator attains a signal-strength-independent leading finite-sample rate and matches a minimax lower bound, whereas a full-spectrum noise estimator carries a deterministic bias under the same model. We further extend the framework to sub-Gaussian settings via optional Gaussianization and provide closed-form standard errors through a block-structured Fisher analysis. Across synthetic high-noise settings and two multi-omics benchmarks (TCGA-BRCA and PBMC CITE-seq), the method achieves near-nominal coverage without post-hoc recalibration, reaches Ridge-level point accuracy on TCGA-BRCA at rank $r=3$, matches or exceeds PO2PLS on cross-view prediction while providing native calibrated uncertainty, and improves stability of parameter recovery.
arXiv:2605.05629v3 Announce Type: replace-cross
Abstract: We study the problem of learning generative models for discrete sequences in a continuous embedding space. Whereas prior approaches typically operate in Euclidean space or on the probability simplex, we instead work on the sphere $\mathbb S^{d-1}$. There the von Mises-Fisher (vMF) distribution induces a natural noise process and admits a closed-form conditional score. The conditional velocity is in general intractable. Exploiting the radial symmetry of the vMF density we reduce the continuity equation on $\mathbb S^{d-1}$ to a scalar ODE in the cosine similarity, whose unique bounded solution determines the velocity. The marginal velocity and marginal score on $(\mathbb S^{d-1})^L$ both decompose into posterior-weighted tangent sums that differ only by per-token scalar weights. This gives access to both ODE and predictor-corrector (PC) sampling. The posterior is the only learned object, trained by a cross-entropy loss. Experiments compare the vMF path against geodesic and Euclidean alternatives. The combination of vMF and PC sampling significantly improves results on Sudoku and language modeling.
arXiv:2606.03014v1 Announce Type: new
Abstract: Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently executing this workload on limited GPU resources has bottlenecks. Skill-based routing creates skewed expert demand, and combining instruction-tuned LLMs with long-reasoning models results in extreme variability in generation lengths. Consequently, traditional scheduling strategies suffer from significant GPU idling and throughput collapse due to load imbalances. We present MOSAIC, a scheduling framework to accelerate MoA workloads. First, we formulate an Integer Linear Program (ILP) based scheduler that jointly optimizes expert placement and per-worker prompt assignment from offline-profiled costs, replicating reasoning experts across workers while pinning lightweight ones. Second, MOSAIC uses confidence-aware adaptive aggregation, leveraging inter-expert agreement to bypass the heavy final aggregator LLM for consensus queries. In our 4-GPU system, MOSAIC achieves up to 2.5x expert-stage, 4.23x aggregator-stage and 1.7~2.3x end-to-end speedups over the baseline scheduler, while matching accuracy within 0.1pp.
arXiv:2605.04235v2 Announce Type: replace-cross
Abstract: Classroom dynamics depend on various elements that influence teaching performance and learning activities. A key challenge is to determine the most effective seating plan, where students will seat in a specific classroom setting to achieve the best learning environment. This paper introduces the Student Seat Allocation Problem (SSAP) for strategically organizing student seating in traditional classrooms to minimize interpersonal conflicts. We propose a mathematical model and an Iterated Local Search (ILS) heuristic to solve the SSAP. Computational experiments demonstrated that ILS outperformed in more complex scenarios when compared to the results obtained by a commercial solver on the introduced mathematical model. ILS was particularly efficient in real and artificial instances that exhibited a higher number of conflicts.
arXiv:2603.25180v2 Announce Type: replace-cross
Abstract: Plasticity is a fundamental property of complex systems, such as the brain or an organism. Yet it typically remains a descriptive concept inferred retrospectively from observed outcomes, such as modifications in activity or morphology. Here, the network-based operationalization of plasticity is further formalized as the ratio between system size and connectivity strength among system elements. Within this framework, system size determines the dimensionality of the accessible state space, while connectivity strength tunes the system's regime. An optimal range of plasticity -- balancing capacity for change and capacity to maintain coherence -- emerges at intermediate connectivity strength. Notably, this balance coincides with the critical regime, which provides a theoretically motivated benchmark that enables a normalized unit of measure, termed effective plasticity, and comparisons of adaptive efficacy across diverse systems. Plasticity is thus transformed into a predictive tool that quantifies a system's capacity for change before it occurs. Its validity is supported across disciplines and, in particular, by evidence from psychopathology where it anticipates transitions between mental states. At a mechanistic level, plasticity acts as a structural tuning parameter for criticality, reframing their relationship as causal, with plasticity driving criticality rather than merely accompanying it. Furthermore, this network-based operationalization explains how larger systems can more robustly maintain critical dynamics. Crucially, the proposed perspective distinguishes functional regime shifts from thermodynamic phase changes, identifying plasticity as the system-level regulator that shapes and constrains the dynamic repertoire. This framework is applicable across domains, including ecology, economics, and social systems, and may foster cross-disciplinary integration within complexity science.
arXiv:2603.19551v2 Announce Type: replace-cross
Abstract: We develop horizon-aware anytime-valid tests and confidence sequences for bounded means under a strict deadline $N$. Using the betting/e-process framework, we cast horizon-aware betting as a finite-horizon optimal control problem with state space $(t, \log W_t)$, where $t$ is the time and $W_t$ is the test martingale value. We first show that in certain interior regions of the state space, policies that deviate significantly from Kelly betting are provably suboptimal, while Kelly betting reaches the threshold with high probability. We then identify sufficient conditions showing that outside this region, more aggressive betting than Kelly can be better if the bettor is behind schedule, and less aggressive can be better if the bettor is ahead. Taken together these results suggest a simple phase diagram in the $(t, \log W_t)$ plane, delineating regions where Kelly, fractional Kelly, and aggressive betting may be preferable. Guided by this phase diagram, we introduce a Deep Reinforcement Learning approach based on a universal Deep Q-Network (DQN) agent that learns a single policy from synthetic experience and maps simple statistics of past observations to bets across horizons and null values. In limited-horizon experiments, the learned DQN policy yields state-of-the-art results.
arXiv:2603.11148v2 Announce Type: replace-cross
Abstract: Spin and polarization are central to precision tests of fundamental physics and for interpreting radiation from astrophysical sources and ultraintense laser-matter experiments. Here, focusing on the fundamental process of nonlinear Compton scattering, we demonstrate that a key assumption underlying current strong-field quantum electrodynamics (SFQED) models, i.e., that emission can be treated as an instantaneous random event sampled from a local differential rate, is inconsistent once emission angles, electron spin, and/or photon polarization are resolved. Namely, \emph{even in strictly constant and uniform fields}, the resulting fully differential distribution is sign-indefinite, yielding negative inferred probabilities. The physical reason is that the photon emission probability builds up over a finite length of the electron trajectory, the formation region, during which the electron direction changes by roughly the same small angle that defines the radiation cone. Therefore, we put forward a new method where we integrate over this formation region analytically to obtain a physically consistent electron spin and photon polarization model. Simulations of a GeV-class electron-laser collision accessible at current petawatt facilities and of emission in a pulsar-like magnetic field are shown to reveal spin and polarization patterns that differ even qualitatively from state-of-the-art local models. In particular, our new model predicts substantial angle-dependent circular photon polarization where the well-known collinear-emission approach yields none, and a pronounced helicity bias in the recoiling electrons absent from current predictions. These findings have direct implications for upcoming strong-field QED experiments and for interpreting polarized radiation from extreme astrophysical environments.
arXiv:2602.18690v2 Announce Type: replace-cross
Abstract: Humans rehearse possible futures offline, as in mental practice and perhaps dreaming, suggesting that world models may support task learning away from the environment. Standard machine learning world models compress visual input into latent vectors, discarding the spatial structure that characterizes sensory cortex. We propose isomorphic world models: architectures that preserve sensory topology, so physics prediction becomes geometric propagation rather than abstract state transition. We implement this idea with motor-gated neural fields, where activity evolves through local lateral connectivity and motor commands multiplicatively modulate specific channels. Across three experiments, the same architecture learns ballistic prediction without ``teleporting,'' improves a catching policy offline by propagating task error through a frozen learned world model, and develops body-selective motor channels without body labels. These results provide preliminary evidence that physical prediction, offline task learning, and body-linked representation share a common computational substrate: action-conditional prediction within a spatial map.
arXiv:2601.18627v2 Announce Type: replace-cross
Abstract: Cross-correlations between 21cm observations and galaxy surveys provide a powerful probe of reionization by providing robustness against foreground contamination while linking ionization morphology to galaxies. We quantified the constraining power of 21cm galaxy cross-power spectra for inferring the neutral hydrogen fraction, $x_\mathrm{HI}(z),$ and mean overdensity, $\langle 1+\delta_\mathrm{HI} \rangle(z)$, exploring dependence on the field of view; redshift precision, $\sigma_z$; and minimum halo mass, $M_\mathrm{h,min}$. We employed our simulation-based inference framework EoRFlow for likelihood-free parameter estimation. Mock observations include thermal noise for 100h of SKA-Low with foreground avoidance and realistic galaxy-survey effects. For a fiducial survey ($\mathrm{FOV}=100\,\mathrm{deg}^2$, $\sigma_z=0.001$, $M_\mathrm{h,min}=10^{11}\mathrm{M}_\odot$), cross-power spectra yield unbiased constraints with posterior volumes (PVs) of $\sim$10% relative to priors. Cross-power measurements reduce the PV by 20-30% versus 21cm auto-power alone. With foreground avoidance, spectroscopic redshift precision is essential; photometric redshifts render cross-correlations uninformative. Notably, cross-power spectra constrain ionizing source properties, the escape fraction $f_\mathrm{esc,}$ and the star formation efficiency $f_*$, which remain degenerate in auto-power (PV >60%). Tight constraints require either deep surveys detecting faint galaxies ($M_\mathrm{h,min} \sim 10^{10}\mathrm{M}_\odot$) with moderate foregrounds (PV~11%) or conservative mass limits with optimistic foreground removal (PV~19%). 21cm galaxy cross-correlations enhance morphology constraints beyond auto-power while enabling previously inaccessible source property constraints. Realizing full potential requires precise redshifts and either faint galaxy detection limits or improved 21cm foreground cleaning.
arXiv:2606.03027v1 Announce Type: new
Abstract: Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-art embedding models are not reproducible because they rely on closed or undisclosed training data, and they remain insufficiently robust for Southeast Asian languages. We present SEA-Embedding, a fully open and reproducible text-embedding pipeline for Southeast Asian languages trained only on publicly available data, and use it to study three core factors of robust embedding design: data composition, training objective, and base encoder initialization. SEA-Embedding achieves state-of-the-art results on SEA-BED while enabling systematic and reproducible analysis of robust text embeddings for the region.
arXiv:2606.03028v1 Announce Type: new
Abstract: Audio spotforming is a technique for extracting target speech from noisy mixtures by utilizing multiple microphone arrays. Conventional methods estimate a shared target speech component from linearly separated signals obtained by each array using low-rank approximations and apply post filtering (PF) based on this estimated low-rank representation. However, owing to the mismatch between low-rank models and the complex structure of speech signals, directly relying on low-rank approximations for PF can degrade the speech extraction performance. In this study, we leverage the observation that non-target components located in the target speech direction from the perspective of one array can be spatially separated when viewed from other arrays. This insight motivates a new spotforming method for efficient post-filter estimation using non-target estimates across arrays instead of relying on low-rank approximations. Experiments demonstrate that the proposed method outperforms conventional spotforming methods.
arXiv:2601.04120v2 Announce Type: replace-cross
Abstract: Optimal control of obstacle problems arises in a wide range of applications and is computationally challenging due to its nonsmoothness, nonlinearity, and bilevel structure. Classical numerical approaches rely on mesh-based discretization and typically require solving a sequence of costly subproblems. In this work, we propose a single-loop bilevel deep learning method, which is mesh-free, scalable to high-dimensional and complex domains, and avoids repeated solution of discretized subproblems. The method employs constraint-embedding neural networks to approximate the state and control and preserves the bilevel structure. To train the neural networks efficiently, we propose a Single-Loop Stochastic First-Order Bilevel Algorithm (S2-FOBA), which eliminates nested optimization and does not rely on restrictive lower-level uniqueness assumptions. We analyze the convergence behavior of S2-FOBA under mild assumptions. Numerical experiments on benchmark examples, including distributed and obstacle control problems with regular and irregular obstacles on complex domains, demonstrate that the proposed method achieves satisfactory accuracy while reducing computational cost compared to classical numerical methods.
arXiv:2601.00990v3 Announce Type: replace-cross
Abstract: Fetal ultrasound is the cornerstone of antenatal care, and accurate recognition of a small set of standard anatomical planes underpins biometry, growth surveillance, and detection of structural anomalies. Deep learning classifiers now match or exceed expert accuracy on curated benchmarks, but most remain opaque and miscalibrated, leaving clinicians without the calibrated confidence or faithful explanations needed for safe decision support. We systematically reviewed 78 studies published between January 1, 2015 and April 30, 2026 that paired automated fetal plane classification with explainability or predictive uncertainty quantification, following PRISMA 2020. Pooled balanced accuracy across six standard planes was 0.93 (95% CI 0.91 to 0.95), but only 19 studies (24%) reported calibration and 14 (18%) reported selective prediction. We propose CALIB-XFUS, a 22-item reporting framework that operationalises calibration, explanation faithfulness, and fairness for regulated fetal ultrasound artificial intelligence. The framework spans six domains: clinical task and indication for use; dataset provenance and representativeness; model and training pipeline; calibration and selective prediction; explanation faithfulness and clinician validation; and post-market surveillance. We argue that uncertainty-calibrated, faithfully explained, and fairness-audited fetal ultrasound AI is now both technically feasible and regulatorily expected under the FDA Good Machine Learning Practice principles and the EU AI Act high-risk obligations.
arXiv:2606.03031v1 Announce Type: new
Abstract: Structured financial audit verification is difficult for language-model agents because correctness depends on structured evidence rather than text alone. A model must link reported facts to taxonomy concepts, traverse calculation or dimensional relations, and recompute expected values before applying an audit rule. We propose AuditFlow, a graph-grounded multi-agent framework that separates adaptive search from deterministic verification. AuditFlow builds a symbolic environment from a static US-GAAP taxonomy graph and a dynamic XBRL filing graph, and exposes it through typed tools for fact retrieval, taxonomy traversal, numerical checking, and rule evaluation. Two junior auditors inspect each case from regulatory and evidentiary views, while a senior auditor resolves disagreements and can request further investigation. The final reports are fused through evidential aggregation to produce an audit verdict, expected value, evidence trail, and trustworthiness score. On a FinAuditing-derived FinMR sample, AuditFlow reaches 82.09% joint audit accuracy under GPT-5.5, outperforming the strongest baseline by 14.93 points. Removing deterministic checks drops accuracy to 17.91%, showing that the symbolic environment performs the verification step that the model cannot reliably replace.
arXiv:2606.03032v1 Announce Type: new
Abstract: Multi-agent LLM systems often treat consensus as evidence of successful interaction. For deliberative problems, however, reliability depends on whether agents preserve the facts and viewpoints needed to interpret an issue. We identify the deliberative illusion: discussion produces (1) factual attrition, the progressive loss of issue-critical facts, alongside (2) stance homogenization, the collapse of diverse positions toward consensus. To measure this process, we introduce DelibTrace, a framework that decomposes each issue into atomic facts, labels issue-critical ones, distributes them across agents, and tracks their survival across discussion rounds. Across ethical and news-based deliberation with three representative LLM families, multi-agent discussion erases up to 72% of issue-critical facts. This loss is consequential: retained evidence can reconstruct the issue misleadingly, final stances remain anchored in base-model priors, and a single malicious agent can inject misinformation into the shrinking shared context. These results reveal a sharper risk: agents can agree more while knowing less. We call for evaluations that measure which facts, uncertainties, and legitimate disagreements survive interaction.
arXiv:2512.14508v2 Announce Type: replace-cross
Abstract: Strain engineering enables quantum confinement in pristine graphene without degrading its intrinsic mobility and spin coherence. Here, we extend previously proposed strain-induced charge-qubit architectures by incorporating spin degrees of freedom through Rashba spin-orbit coupling (RSOC) and Zeeman fields, enabling spin-qubit operation in single-layer graphene (SLG). In a graphene p-n junction, a strain-induced nanobubble generates a pseudo-magnetic field that forms double quantum dots with gate-tunable level hybridization. Tight-binding quantum transport simulations and a four-band model reveal two distinct avoided crossings: spin-conserving gaps at zero detuning and spin-flip gaps at finite detuning, the latter increasing with SOC strength while the former decreases. Time-domain simulations confirm detuning-dependent Rabi oscillations corresponding to these two operational regimes. These results demonstrate that strain-induced confinement combined with tunable SOC provides a viable mechanism for coherent spin manipulation in pristine graphene, positioning strained SLG as a promising platform for scalable spin-based quantum technologies.
arXiv:2606.03033v1 Announce Type: new
Abstract: We develop a contraction-based framework for proving mixing-time bounds for Markov chain Monte Carlo algorithms. The framework is built around global and local contraction coefficients of Markov kernels under the $\mathsf E_\gamma$-divergence with $\gamma\ge1$. For projected Langevin Monte Carlo on a compact convex domain, we show that Gaussian smoothing yields an explicit global contraction coefficient for the $\mathsf E_\gamma$-divergence. This gives a direct proof of exponential convergence to the discretized stationary distribution for general smooth, possibly non-convex potentials. The rate is explicit, accommodates arbitrary random-batch sampling schemes, and yields convergence guarantees for several divergences, including KL, $\chi^2$, and R\'enyi divergences. For independent Metropolis--Hastings with target $\pi$, proposal $q$, and unbounded importance weight $w=d\pi/dq$, global contraction coefficients are typically trivial. We therefore introduce a local contraction coefficient on the core $C_R=\{w\le R\}$ and prove that it controls the rejection profile on the core. This yields warm-start convergence bounds governed by the local contraction coefficient and the tail profile $H_R=\pi(w>R)$, recovering sharp existing moment-based convergence rates when $\mathbb E_q[w^p]<\infty$ for some $p>1$, while remaining effective in heavy-tailed regimes where no finite moment of order $p>1$ exists.
arXiv:2606.03046v1 Announce Type: new
Abstract: Zero-knowledge proofs (ZKP) allows a prover to convince a verifier of computational correctness without revealing private data, ensuring both privacy and verifiability. However, proof generation is highly compute-intensive, dominated by polynomial (POLY) and elliptic-curve (EC) operations. These workloads pose two key challenges for hardware acceleration: (1) efficiently supporting diverse large-precision modular multiplications, and (2) maintaining high utilization across workloads that dynamically shift between POLY and EC stages. Existing reconfigurable accelerators address these issues only partially, remaining limited in precision scalability, algorithmic flexibility, and resource efficiency.
To overcome these limitations, we propose ZK-Flex, a flexible and scalable software-hardware co-designed framework for accelerating ZKP proof generation. The software layer incorporates POLY and EC optimizers that reduce computation through hardware- and workload-aware algorithmic choices, while the hardware integrates TCore, a Toom-Cook-based multi-precision core with a flexible NoC and a linked-list memory mechanism that improves parallelism under limited memory capacity. Across representative ZKP benchmarks, ZK-Flex achieves 5 to 11 times speedup and up to 3.8 times higher area efficiency over the state of the art, establishing a new foundation for high-performance, reconfigurable ZKP acceleration.
arXiv:2512.07053v3 Announce Type: replace-cross
Abstract: Integrating contention-based random access procedures into low Earth orbit (LEO) satellite communication (SatCom) systems poses new challenges, including long propagation delays, large Doppler shifts, and a large number of simultaneous access attempts. These factors degrade the efficiency and responsiveness of conventional random access schemes, particularly in scenarios such as satellite-based internet of things and direct-to-device services. In this paper, we propose a deep learning-based random access framework designed for LEO SatCom systems. The framework incorporates an early preamble collision classifier that uses multi-antenna correlation features and a lightweight 1D convolutional neural network to estimate the number of collided users at the earliest stage. Based on this estimate, we introduce an opportunistic transmission scheme that balances access probability and resource efficiency to improve success rates and reduce delay. Simulation results under 3GPP-compliant LEO settings confirm that the proposed framework achieves higher access success probability, lower delay, better physical uplink shared channel utilization, and reduced computational complexity compared to existing schemes.
arXiv:2606.03073v1 Announce Type: new
Abstract: Reinforcement learning (RL) for large language models (LLMs) is highly sensitive to hyperparameter configurations, making hyperparameter optimization (HPO) essential yet computationally expensive. Existing multi-fidelity HPO methods remain inefficient for LLM RL due to the massive model scale and resource-intensive training cycles. In this paper, we propose Joint Fidelity Hyperparameter Optimization (JF-HPO), which simultaneously adapts both model size and training budget as fidelity. JF-HPO is empowered by: (i) it leverages a small proxy model of the target LLM for efficient training and evaluation in each HPO trial; (ii) it integrates carefully designed early-stopping strategies based on training dynamics; (iii) it introduces an efficient checkpointing mechanism to eliminate redundant computations. Compared with existing HPO methods, JF-HPO significantly improves the computational efficiency of each trial (up to 14.9 times), while achieving better or competitive predictive accuracy under the same time budget. Notably, compared with utilizing hyperparameter configurations from the VeRL Recipe, JF-HPO delivers performance improvements ranging from 5.8% to 111.6%.