Arcee: Differentiable Recurrent State Chain for Generative Vision Modeling with Mamba SSMs

• URL: http://arxiv.org/abs/2511.11243v2
• Date: Mon, 17 Nov 2025 18:00:42 GMT
• Title: Arcee: Differentiable Recurrent State Chain for Generative Vision Modeling with Mamba SSMs
• Abstract summary: State-space models (SSMs) are increasingly adopted for long-context sequence modeling.<n>Recent "Mamba-for-vision" variants largely explore multiple scan orders to relax strict causality for non-sequential signals.<n>Arcee is a cross-block recurrent state chain that reuses each block's terminal state-space representation.
• Score: 3.5590835022089813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-space models (SSMs), Mamba in particular, are increasingly adopted for long-context sequence modeling, providing linear-time aggregation via an input-dependent, causal selective-scan operation. Along this line, recent "Mamba-for-vision" variants largely explore multiple scan orders to relax strict causality for non-sequential signals (e.g., images). Rather than preserving cross-block memory, the conventional formulation of the selective-scan operation in Mamba reinitializes each block's state-space dynamics from zero, discarding the terminal state-space representation (SSR) from the previous block. Arcee, a cross-block recurrent state chain, reuses each block's terminal state-space representation as the initial condition for the next block. Handoff across blocks is constructed as a differentiable boundary map whose Jacobian enables end-to-end gradient flow across terminal boundaries. Key to practicality, Arcee is compatible with all prior "vision-mamba" variants, parameter-free, and incurs constant, negligible cost. As a modeling perspective, we view terminal SSR as a mild directional prior induced by a causal pass over the input, rather than an estimator of the non-sequential signal itself. To quantify the impact, for unconditional generation on CelebA-HQ (256$\times$256) with Flow Matching, Arcee reduces FID$\downarrow$ from $82.81$ to $15.33$ ($5.4\times$ lower) on a single scan-order Zigzag Mamba baseline. Efficient CUDA kernels and training code will be released to support rigorous and reproducible research.

Related papers

• SketchMamba: A Lightweight State-Space Model for Joint Progressive Sketch Classification and Stroke Auto-Completion [0.0]
  Existing vector-sketch models treat recognition and generation as separate tasks.<n>We present SketchMamba, a single causal sequence model that continuously classifies a sketch from any partial prefix while simultaneously generating its continuation.
  arXiv  Detail & Related papers  (2026-07-26T10:05:23Z)
• $γ$-Bridge: A Look-Parametric Diffusion Bridge [1.6583003147024213]
  Multiplicative Gamma noise is a signal-dependent degradation in coherent imaging.<n>We introduce $$-Bridge, a look-parametric bridge whose schedule $L(t)$ connects the noisy observation at $L_obs$ to the clean limit through exact multiplicative Gamma marginals.
  arXiv  Detail & Related papers  (2026-07-21T18:45:58Z)
• AdaSurvMamba: Dynamic Fusion and Semantic Scanning for Multimodal Survival Analysis [57.942670844512016]
  We introduce AdaSurvMamba as a novel adaptive framework for multimodal survival analysis.<n>The framework features a Dual-Scale Importance-Aware Reconstruction (DSIR) module to dynamically modulate cross-modal interaction strength.<n>Experiments across five TCGA cohorts demonstrate consistent gains over existing methods.
  arXiv  Detail & Related papers  (2026-06-28T11:36:31Z)
• MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection [108.36437360254605]
  This paper proposes MambaADv2, a framework tailored for multi-class unsupervised anomaly detection.<n>MambaADv2 comprises a pre-trained encoder and a Mamba-inspired decoder, equipped with Duality-enhanced State Space (DSS) modules across multiple scales.<n>The structure of the Hybrid State Space (HSS) block is tailored by following the SSD-based Mamba lineage and incorporating Mamba3-style position-aware state-space modeling.
  arXiv  Detail & Related papers  (2026-06-22T10:14:06Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• Prefix-Adaptive Block Diffusion for Efficient Document Recognition [52.15352911463151]
  Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsing.<n>We propose the Prefix- Block Diffusion Model (PA-BDM) which replaces intra-block bidirectional denoising with causal denoising from prefix to suffix.<n> Experiments show that the 3B PA-BDM achieves higher recognition scores on several benchmarks and improves inference throughput by 71.6% over the 2.5B MinerU-Diffusion.
  arXiv  Detail & Related papers  (2026-05-16T07:50:13Z)
• Hierarchical Transformer Preconditioning for Interactive Physics Simulation [28.137076331332413]
  Hierarchical Transformer Preconditioner, a neural preconditioner anchored to a weak-admissibility H-matrix partition.<n>Network models the inverse through low-rank far-field factors.<n>Uses highway connections to propagate context across depth sparse.
  arXiv  Detail & Related papers  (2026-05-13T11:02:27Z)
• CAWN: Continuous Acoustic Wave Networks for Autoregressive Language Modeling [46.16066322190728]
  We introduce the Continuous Acoustic Wave Network (CAWN), a fully continuous sequence-mixing architecture.<n>Instead of discrete matrix-based attention, CAWN projects hidden states into multi-headed complex-domain phasors.<n>To prevent signal degradation over ultra-long contexts, we introduce a dual-gated Selective Phase Resonance mechanism.
  arXiv  Detail & Related papers  (2026-04-05T20:13:22Z)
• SfMamba: Efficient Source-Free Domain Adaptation via Selective Scan Modeling [60.860172819390954]
  Source-free domain adaptation (SFDA) tackles the challenge of adapting source-pretrained models to unlabeled target domains.<n>We propose a framework called SfMamba to fully explore the stable dependency in source-free model transfer.
  arXiv  Detail & Related papers  (2026-01-13T14:53:47Z)
• Quantifying Memory Use in Reinforcement Learning with Temporal Range [51.98491034847041]
  Temporal Range is a model-agnostic metric that treats first-order sensitivities of multiple vector outputs across a temporal window to the input sequence as a temporal influence profile.<n>We also report Temporal Range for a compact Long Expressive Memory (LEM) policy trained on the task, using it as a proxy readout of task-level memory.
  arXiv  Detail & Related papers  (2025-12-05T22:58:09Z)
• Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling [27.146380722473932]
  Inverse problems, where the goal is to recover an unknown signal from noisy or incomplete measurements, are central to medical imaging, remote sensing, and computational biology.<n>We propose a novel framework called emphcoupled data and space diffusion posterior sampling (C-DPS), which eliminates the need for constraint tuning or likelihood measurement.<n>C-DPS consistently outperforms existing baselines, both qualitatively and quantitatively, across multiple inverse problem benchmarks.
  arXiv  Detail & Related papers  (2025-10-08T18:59:16Z)
• Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model [15.551773379039675]
  State Space Models (SSMs) have historically played a central role in sequential modeling.<n>Recent advances in selective SSMs like Mamba offer a compelling alternative.<n>We propose a hybrid architecture that combines shifted window self-attention for spatial context aggregation with Mamba-based selective scanning for efficient temporal propagation.
  arXiv  Detail & Related papers  (2025-10-01T13:11:13Z)
• Mamba Modulation: On the Length Generalization of Mamba [34.91142589654215]
  Mamba is a leading architecture for state-space language models.<n>We show that Mamba's performance significantly deteriorates when applied to contexts longer than those seen during pre-training.<n>We propose an approach that applies spectrum scaling to pre-trained Mamba models to enable robust long-context generalization.
  arXiv  Detail & Related papers  (2025-09-23T22:46:19Z)
• Trajectory-aware Shifted State Space Models for Online Video Super-Resolution [57.87099307245989]
  This paper presents a novel online VSR method based on Trajectory-aware Shifted SSMs (TS-Mamba)<n>TS-Mamba first constructs the trajectories within a video to select the most similar tokens from the previous frames.<n>Our TS-Mamba achieves state-of-the-art performance in most cases and over 22.7% reduction complexity (in MACs)
  arXiv  Detail & Related papers  (2025-08-14T08:42:15Z)
• Polar Hierarchical Mamba: Towards Streaming LiDAR Object Detection with Point Clouds as Egocentric Sequences [12.420075828114326]
  Real-time object detection is essential for autonomous vehicles, where real-time perception requires low latency and high throughput.<n>Recent Mamba-based state space models (SSMs) have shown promise for LiDAR perception, but only in the full-scan setting.<n>We propose Polar Hierarchical Mamba, a novel SSM architecture designed for polar-coordinate streaming LiDAR.
  arXiv  Detail & Related papers  (2025-06-07T22:53:50Z)
• Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling [50.994194925685434]
  LrcSSM is a $textitnon-linear$ recurrent model that processes long sequences as fast as today's linear state-space layers.<n>By forcing its Jacobian matrix to be diagonal, the full sequence can be solved in parallel.<n>LrcSSM offers a formal gradient-stability guarantee that other input-varying systems such as Liquid-S4 do not provide.
  arXiv  Detail & Related papers  (2025-05-27T20:02:59Z)
• Vector Copula Variational Inference and Dependent Block Posterior Approximations [5.442153262282512]
  Key to VI is the selection of a tractable density to approximate the Bayesian posterior.<n>This paper proposes using vector copulas to capture dependence between the blocks parsimoniously.
  arXiv  Detail & Related papers  (2025-03-03T00:24:54Z)
• Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion [46.82975707531064]
  Selective state space models (SSMs) excel at capturing long-range dependencies in 1D sequential data.<n>We propose Spatial-Mamba, a novel approach that establishes neighborhood connectivity directly in the state space.<n>We show that Spatial-Mamba, even with a single scan, attains or surpasses the state-of-the-art SSM-based models in image classification, detection and segmentation.
  arXiv  Detail & Related papers  (2024-10-19T12:56:58Z)
• SIGMA: Selective Gated Mamba for Sequential Recommendation [56.85338055215429]
  Mamba, a recent advancement, has exhibited exceptional performance in time series prediction.<n>We introduce a new framework named Selective Gated Mamba ( SIGMA) for Sequential Recommendation.<n>Our results indicate that SIGMA outperforms current models on five real-world datasets.
  arXiv  Detail & Related papers  (2024-08-21T09:12:59Z)
• Multistep Inverse Is Not All You Need [87.62730694973696]
  In real-world control settings, the observation space is often unnecessarily high-dimensional and subject to time-correlated noise. It is therefore desirable to learn an encoder to map the observation space to a simpler space of control-relevant variables. We propose a new algorithm, ACDF, which combines multistep-inverse prediction with a latent forward model.
  arXiv  Detail & Related papers  (2024-03-18T16:36:01Z)
• FOVEA: Foveated Image Magnification for Autonomous Navigation [53.69803081925454]
  We propose an attentional approach that elastically magnifies certain regions while maintaining a small input canvas. Our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning. On the autonomous driving datasets Argoverse-HD and BDD100K, we show our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning.
  arXiv  Detail & Related papers  (2021-08-27T03:07:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.