arXiv:2605.16164v1 Announce Type: new
Abstract: Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a failure mode in which latent variables are effectively ignored. This failure arises because explicit prior imposition drives optimization toward loss landscape regions corresponding to uninformative latent representations. Here, we introduce Entropic Autoencoders (EAEs), a framework in which reconstruction loss is the only explicit objective, and entropy generates the latent variables' prior implicitly through a free energy-minimizing ensemble of encoders. This ensemble biases learning toward high-volume regions of near-optimal solutions, while decoder updates direct the search trajectories toward informative latent representations. We demonstrate that EAEs mitigate posterior collapse by learning non-Gaussian, multimodal latent distributions that yield diverse, data-consistent generations and preserve different forms of underlying structure in the data. As a proof-of-concept, we show that an EAE captures a superposition of the known low-dimensional dynamics of a reaction-diffusion process. Then, we show that an EAE identifies implicit categorical distinctions in MNIST latent representations, and displays a hierarchical understanding of facial structure on the CelebA dataset, from an "all-human" face to individual-dependent features.
Science Journals
arXiv:2605.15722v1 Announce Type: new
Abstract: Accurate delineation of electrocardiogram (ECG), the segmentation of meaningful waveform features, is crucial for cardiovascular diagnostics. However, the scarcity of annotated data poses a significant challenge for training deep learning models. Conventional semi-supervised semantic segmentation (SemiSeg) methods primarily focus on consistency from unlabeled data, underutilizing the information exchange possible between labeled and unlabeled sets. To address this, we introduce CardioMix, a framework built on a bidirectional CutMix strategy guided by cardiac patterns for ECG segmentation. This approach enriches the labeled set with realistic variations from unlabeled data while simultaneously applying stronger supervisory signals to the unlabeled set, as the cardiac pattern-guided mixing ensures all augmented samples remain physiologically meaningful. Our framework is designed as a plug-and-play module, demonstrating high compatibility with various SemiSeg algorithms. Extensive experiments on SemiSegECG, a public multi-dataset benchmark for ECG delineation, demonstrate that CardioMix consistently outperforms existing CutMix-based fusion strategies across diverse datasets and labeled ratios as a plug-and-play module compatible with various SemiSeg algorithms.
arXiv:2605.16161v1 Announce Type: new
Abstract: This paper presents a novel architecture utilizing a 10T SRAM cell for XNOR-based in-memory computing, aimed at mitigating the extensive routing challenges typically encountered in conventional in-memory computing systems. By integrating a full adder between in-memory multiplication cells, the proposed design achieves a 50% reduction in routing complexity. The architecture performs multiply-accumulate (MAC) operations using XNOR computation optimized for binary neural networks (BNNs). Additionally, a 14T-based full adder is employed to construct an N-bit ripple carry adder in the adder tree, significantly reducing the area compared to traditional 28T-based CMOS designs. The 10T SRAM XNOR computation further enhances the latency for MAC operations. The proposed approach reduces the latency and area overhead, improving the overall hardware's area efficiency by 2.67x compared to the state-of-the-art.
arXiv:2605.15723v1 Announce Type: new
Abstract: Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities largely unused. Multimodal attributed graphs (MAGs), where nodes carry multimodal attributes and edges encode corpus structure, provide a natural setting for refining frozen vision-language embeddings. This refinement is challenging: visual, textual, and cross-modal relations often induce different neighborhood geometries, while unrestricted graph propagation can quickly over-smooth retrieval representations. Effectively leveraging graph context therefore requires simultaneously breaking modality-specific topological barriers, controlling the smoothing regime, and preserving informative smoothing before semantic boundaries collapse. We propose Graph-Optimized Multimodal Alignment (GOMA), a structure-driven post-alignment framework that views frozen multimodal embeddings as graph signals and addresses these requirements through a unified retrieval-oriented design. GOMA decouples three key design choices: where messages should flow, how multimodal evidence should propagate, and which smoothing depth should be retained. Concretely, it learns modality-aware propagation operators, performs finite-step coupled smoothing without diagonal cross-modal shortcuts, and adaptively reads out node-specific smoothing trajectories to preserve useful smoothing before collapse. All experiments follow a transductive MAG retrieval protocol where the graph serves only as unlabeled context and diagonal self-pair edges are removed. On seven MAG benchmarks, GOMA achieves state-of-the-art or tied state-of-the-art retrieval and remains substantially more stable than the strongest graph competitor, demonstrating that MAG structure can serve as an effective post-encoder for frozen multimodal embeddings.
arXiv:2605.16159v1 Announce Type: new
Abstract: Real-time event detection in IoT mesh sensor networks must balance sensitivity against false-positive load on a constrained mesh radio. We present a Monte Carlo comparison of the Temporal Spectral Noise-Floor Adaptation (TSNFA) detector against four classical comparators drawn from the radar Constant False Alarm Rate (CFAR) family and from sequential change detection: the Lipski FFT energy detector, Cell-Averaging CFAR (CA-CFAR), Ordered-Statistic CFAR (OS-CFAR), and state-machine Cumulative Sum (CUSUM). All five detectors are implemented to fit a Cortex-M0+ class envelope, process a 1-D 100 Hz time series in 128-sample frames, and use temporal reference windows in place of the spatial reference cells of conventional radar CFAR. Across a factorial set of four configurations (10 and 50 nodes; 12 dB and 18 dB SNR), each replicated five times over 24 hours, TSNFA achieves 99.97 to 100% event detection rate with 100% event precision and zero false-positive clusters per node. The classical comparators each succeed on one quality dimension and fail on another. Lipski FFT (k = 3), CA-CFAR, and OS-CFAR all maintain near-perfect detection rate but with event precision below 3% and per-node bandwidth between 145 kB/h and 1.2 MB/h. CA-CFAR and OS-CFAR are indistinguishable in false-alarm performance, both saturating the same broadband-statistic failure mode. CUSUM shows an SNR-dependent detection-rate drop from about 70% at 18 dB to 51% at 12 dB. TSNFA is the only algorithm tested that simultaneously achieves high detection rate, high precision, and low per-node bandwidth.
arXiv:2605.16158v1 Announce Type: new
Abstract: Standard Gaussian splatting methods rely on heuristic densification and pruning to adaptively allocate primitives during training, and the resulting Gaussian count strongly influences both reconstruction quality and runtime. This makes comparisons across methods fragile: improvements can stem from higher representational capacity rather than algorithmic design. A common and naive workaround for this is hard-stopping or budgeting densification/pruning once a target count is reached, which biases training because different methods hit the cap at different times, yielding non-uniform densify/prune exposure across views and uneven point distributions. We propose a target point control scheme that preserves the standard densification window and cadence, but adjusts only the existing densification and opacity-culling hyper-parameters to track a quadratic target count trajectory. This quota-governor reaches the desired count by 15k iterations without abrupt cutoffs, ensuring that all methods and views receive equal densification and pruning cycles, enabling fairer, capacity-matched evaluation.
arXiv:2605.03964v2 Announce Type: replace
Abstract: Training machine learning interatomic potentials (MLIPs) for reactive chemistry is often bottlenecked by the high cost of quantum chemical labels and the scarcity of transition state configurations in candidate pools. Active learning (AL) can mitigate these costs, but its effectiveness hinges on the acquisition rule. We investigate whether the latent space of a pretrained MLIP already contains the information necessary for effective acquisition, eliminating the need for auxiliary uncertainty heads, Bayesian training and fine-tuning, or committee ensembles. We introduce two acquisition signals derived directly from a pretrained MACE potential: a finite-width neural tangent kernel (NTK) and an activation kernel built from hidden latent space features. On reactive-chemistry benchmarks, both kernels consistently outperform fixed-descriptor baselines, committee disagreement, and random acquisition, reducing the data required to reach performance targets by an average of 38% for energy error and 28% for force error. We further show that the pretrained model induces similarity spaces that preserve chemically meaningful structure and provide more reliable residual uncertainty estimates than randomly initialised or fixed-descriptor-based kernels. Our results suggest that pretraining aligns latent-space geometry with model error, yielding a practical and sufficient acquisition signal for reactive MLIP fine-tuning.
arXiv:2605.16154v1 Announce Type: new
Abstract: Reinforcement learning (RL) allows vision-language-action (VLA) policies to generalize beyond their training distribution by optimizing directly for task success, but post-training is computationally expensive. A natural response has been to speed rollout collection through faster simulators and world models. In GRPO-based VLA RL, we find that the dominant cost lies elsewhere: gradient computation accounts for approximately 78% of wall-clock time per step in our runs, while rollout collection accounts for only 21%. Gradient cost dominates because much of this computation is spent on phases that contribute little to learning. GRPO's learning signal is driven by advantage variance: only phases where successful and failed rollouts diverge produce learning signal. However, GRPO assigns the same advantage to every chunk in a rollout. As a result, actor-update compute is spent uniformly across the trajectory, including phases the policy already handles after pre-training and supervised fine-tuning. This paper presents Probabilistic Chunk Masking (PCM), a drop-in modification to GRPO that allocates gradient computation to a small, probabilistically selected subset of chunks per trajectory. PCM scores semantic phases using success-failure action variance, a rollout-derived proxy for per-phase gradient variance, and samples a fixed chunk budget with online-updated phase-level keep probabilities. We formalize per-phase gradient variance as the quantity determines where gradient computation is useful and show that success-failure action variance provides a measurable proxy for it. PCM requires no reward model or learned critic. On three LIBERO benchmarks, PCM matches the final success rate of standard GRPO while achieving 2.38 times wall-clock speedup, 4.8 times faster gradient updates, and 60% lower peak activation memory, while backpropagating through fewer than 20% of trajectory chunks.
arXiv:2605.15774v1 Announce Type: new
Abstract: Traditional Fully Homomorphic Encryption (FHE) schemes often suffer from prohibitive computational overhead and complex noise management. In this paper, we propose a novel symmetric FHE through a mechanism of plaintext fragmentation and dynamic interposition. Our approach is built upon a modular encryption foundation, c = mk + rp, which is naturally additive but typically limited by exponential noise growth during multiplication. To resolve this, we introduce an interposition framework where the plaintext is partitioned into multiple fragments across distinct logical positions. We introduce a dual-regulator system to govern the multiplication process; exponent regulators (t_i) redirect the product of fragments to a new target position, preventing the accumulation of secret key exponents, while coefficient regulators (d_i) normalize the resulting scalars. Security is established through a binding mechanism where exponents and coefficients are mutually dependent, shielding the secret key k from algebraic manipulation and substitution attacks.
arXiv:2511.03606v2 Announce Type: replace-cross
Abstract: The study of self-normalized processes plays a crucial role in a wide range of applications, from sequential decision-making to econometrics. While the behavior of self-normalized concentration has been widely investigated for scalar-valued processes, vector-valued processes remain comparatively underexplored, especially outside of the sub-Gaussian framework. In this contribution, we provide concentration bounds for self-normalized processes with light tails beyond sub-Gaussianity (such as Bennett or Bernstein bounds). We illustrate the relevance of our results in the context of online linear regression, with applications in (kernelized) linear bandits.
arXiv:2605.16149v1 Announce Type: new
Abstract: Space plasmas are generally characterized by non-Maxwellian distributions with suprathermal populations, as routinely revealed by in situ observations. Such departures from standard Maxwellian distributions can be understood as signatures of quasiequilibrium states, in which the distribution of the medium can be expressed as a continuous superposition of Maxwellian distributions, namely through superstatistics. Here, we construct macroscopic relations linking fluxes to their associated driving forces in such plasmas, where superstatistical effects enter the picture through the transport coefficients. After comparing the resulting superstatistical distributions with observed electron distributions in the solar wind, we turn to the kinetic response of quasiequilibrium plasmas and derive the corresponding transport coefficients, including the electric and thermal conductivities, the mobility, and the diffusion coefficient. We further extend the analysis to viscous plasmas and compute the shear and bulk viscosity coefficients. Overall, quasiequilibrium effects are found to systematically enhance the transport coefficients relative to their Maxwellian values. We quantify this enhancement for the three main universality classes of superstatistics, which are the most commonly encountered in experimental and observational situations, and interpret it as a consequence of the increased population of energetic particles in the non-Maxwellian tails.
arXiv:2605.16143v1 Announce Type: new
Abstract: Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acquiring sufficient environment-specific information. We identify autonomous exploration as a critical yet underexplored capability for building adaptive agents. To formalize and quantify this capability, we introduce Exploration Checkpoint Coverage, a verifiable metric that measures how broadly an agent discovers key states, objects, and affordances. Our systematic evaluation reveals that agents trained with standard task-oriented reinforcement learning consistently exhibit narrow and repetitive behaviors that impede downstream performance. To address this limitation, we develop a training strategy that interleaves task-execution rollouts and exploration rollouts, with each type of rollout optimized by its corresponding verifiable reward. Building on this training strategy, we propose the Explore-then-Act paradigm, which decouples information-gathering from task execution: agents first utilize an interaction budget to acquire grounded environmental knowledge, then leverage it for task resolution. Our results demonstrate that learning to systematically explore is imperative for building generalizable and real-world-ready agents.
arXiv:2601.15818v3 Announce Type: replace-cross
Abstract: Advances in accelerator technology have led to significant improvements in the quality of muon beams over the past decades. Investigations of the muon and muonium enable precise measurements of fundamental constants, as well as searches for new physics beyond the Standard Model. Furthermore, by utilizing muon beams with high intensity and polarization, studies of the dynamics of the muon and muonium within atomic level can offer valuable insights into materials science. This review presents recent progress and prospects at the frontiers of muon beams and high-precision muonium physics. It also provides an overview of novel methods and detection techniques to achieve high sensitivities in different areas, including particle physics, nuclear physics, materials science and beyond.
arXiv:2604.12750v2 Announce Type: replace-cross
Abstract: We study how exact Solvability Complexity Index (SCI) statements should be formulated for families of computational problems rather than for single problems. While the equality \(\mathrm{SCI}_G (\mathcal P)=k\) is unambiguous for an individual computational problem \(\mathcal P\), the family setting requires one to distinguish family-pointwise exactness, witness-space sharpness, and worst-case exactness. We formalize this trichotomy, prove that witness-space sharpness coincides with worst-case exactness but is, in general, strictly weaker than family-pointwise exactness, and give a canonical source-family example witnessing the strictness. We then establish two positive upgrade theorems: an abstract pullback principle and a concrete finite-query criterion guaranteeing that witness-space sharpness upgrades to family-pointwise exactness. Next, we introduce a decoder-regular finite-query transport preorder on SCI computational problems, prove that it is a preorder, derive a transport-saturation sufficient criterion extending the principal-source package, and show that the associated transport degrees need not form a lattice in full generality. We analyze the natural decoder classes \(\mathscr R_{\mathrm{cont}}\) and \(\mathscr R_{\mathrm{Bor}}\): on the full class the corresponding quotients are not upper semilattices, while on the nondegenerate subclass the preorder is upward and downward directed. Finally, we exhibit two natural positive families realizing the principal transport mechanism: exact integration on compact intervals and a fixed-window spectral decision family obtained by block-diagonal stabilization.
arXiv:2605.15725v1 Announce Type: new
Abstract: Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trade-off between action abstraction and generation fidelity. Existing methods typically circumvent this issue by using two-stage training with pre-trained world models or by limiting predictions to optical flow. In this paper, we introduce DiLA, a novel Disentangled Latent Action world model that aims to resolve this trade-off via content-structure disentanglement. Our key insight is that disentanglement and latent action learning are co-evolving: the predictive bottleneck inherent in latent action learning serves as a driving force for disentanglement, compelling the model to distill spatial layouts into the structure pathway while offloading visual details to a separate content pathway for generation. This synergy yields a continuous, semantically structured latent action space without compromising generative quality. DiLA achieves superior results in video generation quality, action transfer, visual planning, and manifold interpretability. These findings establish DiLA as a unified framework that simultaneously achieves high-level action abstraction and high-fidelity generation, advancing the frontier of self-supervised world model learning.
arXiv:2605.15990v1 Announce Type: new
Abstract: Tremendous efforts have been put into evaluating the inclusivity and effectiveness of AI systems across cultures. However, the cultural capabilities considered in much of the literature remain vaguely defined, are referred to using interchangeable terminology, and are typically limited to recalling accurate information about various demographics, regions, and nationalities. To address this construct ambiguity, we draw from Intercultural Communication scholarship and propose a three-level taxonomy of AI-relevant cultural capabilities: Cultural Awareness answers "Does the model know?", Cultural Sensitivity answers "How does it frame its knowledge?", and Cultural Competence answers "Can it adapt as the interaction evolves?". Beyond conceptual clarification, we position this taxonomy as a practical tool for improving the validity and interpretability of AI evaluation in real-world, multicultural settings. Without such construct clarity, evaluation results risk overstating model capabilities and may lead to inappropriate deployment decisions in culturally sensitive contexts.
arXiv:2605.15952v1 Announce Type: new
Abstract: Teleoperation promises to extend the operational envelope of automated vehicles, yet it critically depends on network latency and video quality. We report a fixed-base driving-simulator study (N=25) with a 2x2 manipulation of added latency (100/300 ms) and bitrate (500/2000 kbit/s), plus a best-case baseline (0 ms added, 9000 kbit/s). We measured effective glass-to-glass (G2G) latency per condition (baseline approx. 413 ms; effective totals approx. 500-700 ms) and verified stable framerate and encoder settings. Multimodal measures covered performance (speed, steering reversals, crashes), oculomotor behavior (blink rate, fixation duration), physiology (RR interval, heart rate, skin conductance), and subjective workload. Latency and bitrate each increased operator load and modestly affected performance. Physiological measures (heart rate, RR interval) exhibited sub-additive interactions, whereas performance and oculomotor interactions were small or non-significant. Equivalence tests showed that 300 ms with 2000 kbit/s was velocity-equivalent to best-case (SESOI +/- 2 km/h), while 300 ms with 500 kbit/s was not. We argue that latency and video quality should be treated as largely independent design levers, and that physiology-aware adaptation can anticipate overload before safety is compromised.
arXiv:2605.15372v1 Announce Type: cross
Abstract: We derive an explicit formula for the intrinsic MacWilliams transform for permutation-invariant qudit codes. Such codes naturally live in symmetric power representations, where the relevant error sectors are determined by the irreducible decomposition of the conjugation action on the associated operator space. Using the multiplicity-free structure of this decomposition and the corresponding intertwiner algebra, we identify the intrinsic MacWilliams matrix with a finite Racah transform. The entries are given by a terminating hypergeometric series, and the rows of the matrix are Racah orthogonal polynomials with parameters determined explicitly by the block length and local dimension. Computing the spectrum of the degree-one twirl reveals that this spectrum lies on an affine quadratic lattice. Then we derive a tridiagonal multiplication rule from the representation theory of the adjoint sector. As consequences, we obtain closed-form orthogonality, detailed-balance, and involutivity identities for the transform. The resulting formula supplies an explicit MacWilliams matrix for computing linear programming bounds on permutation-invariant qudit codes.
arXiv:2605.16114v1 Announce Type: new
Abstract: We propose a scalable neuromorphic architecture based on spiking dynamics emerging from the autonomous time-continuous evolution of clockless (asynchronous) digital circuits. Implemented on commercially available field-programmable gate arrays (FPGAs), our system implements networks of interacting Boolean spiking neurons with configurable excitatory and inhibitory synaptic weights. A complete processing pipeline enables efficient handling of spike-encoded data for solving machine-learning tasks. We demonstrate competitive performance for an audio classification task with spike-based encoding and high-speed processing. Power consumption is significantly lower than traditional digital implementations; this makes our approach an efficient alternative that bridges the gap to dedicated analog neuromorphic systems without the need for specialized hardware design. More generally, our approach establishes clockless digital hardware as a viable platform for neuromorphic computing. It paves the way for reconfigurable chips to be turned into energy-efficient quasi-analog neuromorphic processors.
arXiv:2605.16067v1 Announce Type: new
Abstract: We propose a variational quantum classifier operating on high dimensional deep representations via amplitude encoding, stabilized by a learnable classical pre encoding layer.By combining normalized amplitude embeddings with bounded quantum observables, the resulting model induces a structured and smooth hypothesis class with controlled sensitivity to input variations. Model reliability is assessed using SAFE-AI metrics derived from the Cramer von Mises divergence, enabling consistent evaluation across accuracy, robustness, and explainability dimensions. Empirical results show that the proposed quantum model provides competitive predictive performance compared with strong classical baselines while exhibiting a more balanced SAFE reliability profile, with improved robustness to noise and stability under structured feature removal. These findings suggest that variational quantum circuits offer a principled mechanism for stability oriented SAFE learning in safety critical settings.
arXiv:2605.16065v1 Announce Type: new
Abstract: 3D Gaussian Splatting (3D-GS) enables real-time 3D scene reconstruction but lacks robust segmentation for editing tasks such as object removal, extraction, and recoloring. Existing approaches that lift 2D segmentations to the 3D domain suffer from view inconsistencies and coarse masks. In this paper, we propose a novel framework that leverages the Segment Anything Model High Quality (SAM-HQ) to generate accurate 2D masks, addressing the limitations of the standard SAM in boundary fidelity and fine-structure preservation. To achieve robust 3D segmentation of any target object in a given scene, we introduce a prior-guided label reassignment method that assigns labels to 3D Gaussians by enforcing multiview consistency with learned priors. Our approach achieves state-of-the-art segmentation accuracy and enables interactive, real-time object editing while maintaining high visual fidelity. Qualitative results demonstrate superior boundary preservation and practical utility in Virtual Reality (VR) and robotics, advancing 3D scene editing.
arXiv:2603.01675v2 Announce Type: replace
Abstract: We extend the study of the 2-Solo Chess problem which was first introduced by Aravind, Misra, and Mittal in 2022. 2-Solo Chess is a single-player variant of chess in which the player must clear the board via captures such that only one piece remains, with each piece capturing at most twice. It is known that the problem is solvable in polynomial time for instances containing only pawns, while it becomes NP-complete for instances restricted to rooks, bishops, or queens. In this work, we complete the complexity classification by proving that 2-Solo Chess is NP-complete if the instance contains only knights or only kings.
arXiv:2509.21663v2 Announce Type: replace
Abstract: Neurosymbolic integration (NeSy) blends neural-network learning with symbolic reasoning. The field can be split between methods injecting hand-crafted rules into neural models, and methods inducing symbolic rules from data. We introduce Logic of Hypotheses (LoH), a novel language that unifies these strands, enabling the flexible integration of data-driven rule learning with symbolic priors and expert knowledge. LoH extends propositional logic syntax with a choice operator, which has learnable parameters and selects a subformula from a pool of options. Using fuzzy logic, formulas in LoH can be directly compiled into a differentiable computational graph, so the optimal choices can be learned via backpropagation. This framework subsumes some existing NeSy models, while adding the possibility of arbitrary degrees of knowledge specification. Moreover, the use of G\"odel fuzzy logic and the recently developed G\"odel trick yields models that can be discretized to hard Boolean-valued functions without any loss in performance. We provide experimental analysis on such models, showing strong results on tabular data and on two NeSy tasks with a perceptual component.
arXiv:2605.16052v1 Announce Type: new
Abstract: Recent advances in large language models (LLMs) have significantly enhanced automated legal reasoning. Yet, it remains unclear whether their performance reflects genuine legal reasoning ability or artifacts of data contamination. We present a comprehensive empirical study of tax law reasoning approaches and implement a contamination detection protocol to rigorously assess LLM reliability. We show that performance can be inflated by contamination. Building on this analysis, we conduct a systematic evaluation, comparing monolithic LLMs with hybrid systems that translate statutory text into formal representations and delegate inference to symbolic solvers. We build a novel test suite designed to probe generalization to unseen documents via case and rule variations. Our findings indicate that legal reasoning is inherently compositional and that neuro-symbolic frameworks offer a more reliable and robust foundation for legal AI, as well as improved generalization to unobserved situations.
arXiv:2605.16048v1 Announce Type: new
Abstract: State Space Models (SSMs) are inherently recurrent along the sequence dimension, yet depth-recurrence - reusing the same block repeatedly across layers, as recently applied in looped transformers - has not been explored in this model family. We show that a looped SSM with $k$ parameters iterated $L$ times consistently closely matches or outperforms a standard SSM with $k \cdot L$ independent parameters across four architectures (LRU, S5, LinOSS, LrcSSM) and six time series classification benchmarks, despite operating within a strictly smaller hypothesis space, as we formally establish. Since the larger model contains the looped model as a special case, this dominance cannot be explained by expressivity and instead points to parameter sharing across depth as a beneficial inductive bias that simplifies optimization. These results demonstrate that depth-recurrence is orthogonal to sequence-recurrence and independently beneficial. We further show that input reshaping is an equally neglected design axis: concatenating timesteps for low-dimensional inputs, or flattening and rechunking the joint feature-time dimension for high-dimensional ones, yields accuracy gains of 1-6% across all models, confirmed over 5 random seeds. Both techniques provide standalone improvements that compound when combined, suggesting that depth and input reshaping are two independent and underexplored design axes for SSMs on time series.