Hybrid Mamba-Transformer Architectures

Follow this topic Ask about this topic

Latest papers

19 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Oct 14, 2026

TurboMamba: Faster Inference, Faster Training, and Better Prediction with Lexical Memory

We introduce TurboMamba, a language-model architecture for faster inference, faster training, and better token prediction. A global Mamba-3 model runs once per completed token block. A small Transformer uses this global context and earlier tokens within the block to predict the next token. Three lightweight additions improve local predictions: direct access to the previous block's last token, a small correction to next-token scores, and a learned mixture with recent-token frequencies. We compare twelve small-scale implementations on public FineWeb-Edu, with comparable parameter counts and shared training-budget caps. The baselines include Transformer, Mamba-3, Jamba, and Zamba. The Jamba and Zamba versions use Mamba-3 in place of their original Mamba modules. TurboMamba achieves the lowest mean test prediction loss (negative log-likelihood, NLL) among all twelve models. Its mean NLL is 9.4% lower than that of Mamba-3, 7.3% lower than that of the Jamba version, and 18.3% lower than that of the Zamba version. End-to-end training throughput is 2.60x that of Mamba-3, 2.81x that of the Jamba version, and 4.82x that of the Zamba version. We measure end-to-end batch latency for a batch of 32 sequences, each with a 256-token prompt and 128 generated tokens. On this workload, TurboMamba achieves a 3.12x speedup over Mamba-3, a 3.53x speedup over the Jamba version, and a 6.21x speedup over the Zamba version.

Hanxin Zhang

Department of Neurology, University of Pittsburgh

Hybrid Transformer-State Space Model Architectures Autoregressive Language Modeling Efficient Language Model Training LLM Inference Acceleration Hybrid Mamba-Transformer Architectures

Oct 1, 2026

Learning Rate Transfer for Hybrid Transformer-SSM Architectures

We study learning rate (LR) scaling for hybrid architectures combining Transformer and State-Space Model (SSM) blocks, a class adopted by several recent production language models. In particular, we focus on the gap between the theoretical scaling rules derived for SSMs under zero-order-hold (ZOH) discretization at infinite width with growing state size, and the field-standard practical implementations using simplified-ZOH Mamba at fixed state size. Surprisingly, in this practical regime hybrid architectures achieve a near-zero LR transfer gap across widths 256-2048 and depths 4-32 up to billion-parameter scale using only the original

μ

P prescription, even though SSM operations fall outside its Tensor Programs representability conditions and every parameterization we test fails the standard coordinate-check diagnostic of

μ

P correctness. We attribute this to a two-condition decomposition of LR transfer in hybrid architectures: a global update-to-weight invariance, enforced by

μ

P's initialization and LR scaling; and a local per-component balance, provided by AdamW's per-parameter normalization. Our observations show that the optimal LR is invariant to width up to 8

\times

, that this width invariance holds across depth, sequence length, batch size, and Transformer-to-SSM ratio, and that it transfers to Nemotron-H, a production hybrid outside our custom architecture set. We hope these findings fill the gap between theoretical scaling rules and practical hybrid implementations, and stimulate further research toward bridging it.

Jimin Seo, Gyubok Lee, Yeonsik Jo +11

Seoul National University · SB Intuitions · LG AI Research +1

Hyperparameter Transfer Hybrid Transformer-State Space Model Architectures Hybrid Mamba-Transformer Architectures Hybrid Transformer Architectures

Sep 22, 2026

MambaVoice: Lightweight Audiovisual Singing Voice Separation Via A Hybrid Mamba-Transformer Model

Isolating a target singing voice from a music video remains challenging, particularly in the presence of multiple vocalists and dense instrumental accompaniment. We propose MambaVoice, a lightweight audiovisual framework that leverages a hybrid Mamba--Transformer architecture for targeted singing voice separation. The model jointly encodes audio and visual streams using an attention-based band-split audio encoder and a spatio-temporal graph convolutional network (ST-GCN) for facial motion features. These modalities are fused through a multiplicative gating mechanism, enabling visual cues to selectively modulate audio representations. The fused features are processed by a hybrid backbone that combines Transformer self-attention with Selective State Space Models (SSMs), achieving efficient long-range temporal modeling with linear complexity. We evaluated MambaVoice on the Acappella and URSing datasets under challenging conditions, including mixtures with interfering singers. At 16.2 million parameters, the model demonstrates comparable performance, achieving 14.18 dB SDR on Acappella and strong cross-dataset performance on URSing, comparable to larger models at a fraction of the parameter count. These findings highlight the effectiveness of hybrid SSM--attention architectures for scalable, efficient audiovisual source separation, suggesting they are well-suited as lightweight components within larger pipelines. We conduct a perceptual study that further supports our improvements in objective metrics. We provide our implementation online.

Adithi Shankar, Gopika Krishnan, Gloria Haro +2

Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain · Intelligent Multimodal Vision Analysis Group, Universitat Pompeu Fabra, Barcelona, Spain · Serra Húnter Fellow Programme, Universitat Pompeu Fabra, Barcelona, Spain

Hybrid Mamba-Transformer Architectures Audio Source Separation

Aug 19, 2026

HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads

Hybrid Transformer-Mamba large language models (LLMs) enhance long-context efficiency, but their heterogeneous computation and communication patterns complicate efficient hardware acceleration. Chiplet-based architectures offer a scalable solution by integrating specialized compute and memory units. However, the design space spanning static architectural configurations and dynamic runtime policies is prohibitively large to explore exhaustively. To address this challenge, we present HYDRA, a comprehensive design space exploration framework for hybrid LLM serving on heterogeneous chiplet systems. HYDRA jointly explores chiplet composition, placement, inter-chiplet bandwidth provisioning, dynamic batching, and runtime scheduling. It integrates communication-aware placement, dynamic batching, elastic task scheduling, and a fast Markov-based performance estimator that captures multi-tenant runtime dynamics for efficient and accurate exploration. Across all workloads, HYDRA delivers 1.55x the throughput and 43.7 percent lower time-to-first-token on average, with throughput gains reaching up to 2.3x compared to state-of-the-art baselines. These results highlight that co-designing architecture and runtime policies is critical for efficient large-scale LLM serving on heterogeneous chiplet systems.

Jiahao Lin, Alish Kanani, Sangwan Lee +2

University of Wisconsin–Madison · University of Ulsan

Hybrid Mamba-Transformer Architectures LLM Serving Heterogeneous Computing LLM Inference Scheduling

Jul 10, 2026

A Sovereign, Open-Source Foundation Model for German and English

We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B of 30B parameters per token and keeps the inference cache near-constant as context grows, giving it a decisive throughput advantage over dense models for long-context, high-concurrency deployment. Pretrained on roughly 27 trillion tokens with deliberately up-weighted German, Soofi S matches dense 14 to 27B models on aggregate English and German benchmarks while achieving the best code aggregates in both languages among 17 open base models, and outperforms every European sovereign baseline in our comparison, including ones far larger in active parameters. Among fully open models, Soofi S obtains the highest English and German evaluation scores, ahead of Olmo 3 32B and Apertus 70B. Soofi S was built end-to-end on the German Industrial AI Cloud, a sovereign HPC scale AI infrastructure operated by Deutsche Telekom in Munich. Soofi S will be released under highly permissive, open-access terms: weights, selected intermediate checkpoints, full per-source data accounting, hyperparameters, and training and evaluation code. Where source licenses permit, data-construction artifacts are released under permissive licenses; commercially licensed sources are documented with aggregate statistics and exact mixture accounting.

The Soofi-Team, :, Benedikt Droste +29

ellamind · Fraunhofer IAIS · Lamarr +8

Language Model Pretraining Multilingual Language Models Mixture-of-Experts Language Models Hybrid Mamba-Transformer Architectures Language Modeling Efficient Language Model Inference

Jul 2, 2026

Training Hybrid Block Diffusion Language Models with Partial Bidirectionality

High-throughput long-context generation is one of the central challenges for large language models. Generation is typically memory-bandwidth-bound rather than compute-bound: each decoding step must stream the accumulated key/value (KV) cache from memory, so bandwidth demand grows with context length while only one token is emitted. Two parallel approaches have therefore emerged: reducing memory access with efficient attention variants and linear-time mixers such as Mamba, or increasing parallel computation by generating blocks of tokens at once. However, technical challenges arise when combining these two ideas. Earlier hybrid diffusion models such as DiffuMamba use bidirectional Mamba mixing, including a reverse-direction scan relative to causal generation. This reverse scan needs to scan the entire sequence, so its states are not prefix-only and cannot be precisely reused as a cache even when diffusion is performed block by block. We propose a BDLM Mamba--attention hybrid that addresses this challenge by restricting the reverse Mamba scan to the active denoising block, which enables exact caching across blocks. In an 87M-parameter DCLM sweep, BDLM Mamba-H achieves the best C4-en validation perplexity compared to BDLM attention and full-sequence baselines. At 350M parameters, it remains competitive with BDLM attention. For long-context inference, BDLM Mamba-H reaches 19.7x the throughput of full-sequence DiffuMamba-H at 65K tokens and 3.7x the throughput of BDLM attention at 262K, showing that Mamba hybrids are a potential long-context diffusion architecture.

Pranshu Chaturvedi, Parth Shroff, Tarun Suresh +2

Stanford University

Blockwise Diffusion Language Models Diffusion Language Models Long-Context Language Model Inference Mamba Diffusion Language Model Inference Diffusion Model Caching+1

Jun 12, 2026

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

NVIDIA, :, Aaron Blakeman +571

Allan

Mixture-of-Experts Language Models Long-Context Language Model Inference LLM Inference Acceleration Agentic Reasoning Hybrid Mamba-Transformer Architectures

Jun 1, 2026

Forget Attention: Importance-Aware Attention Is All You Need

Combining attention's global retrieval with the sequential importance signal of state space models (SSMs) is the open challenge of hybrid language modeling. Transformers see everywhere but cannot prioritize; SSMs know what matters but cannot revisit. Existing hybrids -- Jamba (block level) and Hymba (head level) -- place the two in separate compartments, so neither informs the other during the attention computation itself. We propose SISA (SSM-Informed Softmax Attention), which adds an SSM-derived importance term directly inside the attention score and realizes the full operation as a single SDPA call on augmented query/key vectors -- no recurrent state, no custom kernel. At 152M / 5B tokens, SISA reaches LAMBADA-greedy 17.3% (vs. Transformer 13.9 and Mamba-3 15.5) and attains NIAH 100% from step 1K, 7x faster than Transformer's retrieval convergence; at 369M, Mamba-3 leads LAMBADA while SISA preserves perfect NIAH and stock-SDPA execution. SISA thus defines a third design axis for SSM-attention hybrids -- score-level fusion -- beyond the block-level and head-level paradigms that have dominated the field.

Suhyeong Shin, Yeongwook Yang

Department of Computer Engineering Kangwon National University

Softmax Attention Long-Context Language Modeling Hybrid Transformer-State Space Model Architectures Hybrid Attention State Space Models Hybrid Mamba-Transformer Architectures

May 29, 2026

Zamba2-VL Technical Report

We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with a small number of shared transformer blocks. Across a broad range of image understanding, reasoning, OCR, grounding, and counting benchmarks, Zamba2-VL is competitive with leading Transformer-based open-weight VLMs of comparable scale, including the Molmo2, Qwen3-VL, and InternVL3.5 families, and substantially outperforms prior SSM-based and hybrid VLMs such as VL-Mamba, Cobra, and mmMamba. Inheriting the near-linear prefill compute and small, near-constant recurrent state of its Zamba2 backbone, Zamba2-VL delivers roughly an order of magnitude lower time-to-first-token (TTFT) than these Transformer baselines at matched parameter scale, with the efficiency gap most pronounced at the smaller 1.2B and 2.7B scales most relevant to on-device and edge deployment. We release three models -- 1.2B, 2.7B, and 7B -- together with inference code at https://huggingface.co/collections/Zyphra/zamba2-vl.

Hassan Shapourian, Kasra Hejazi, Olabode M. Sule +1

Zyphra, San Francisco, CA

Vision-Language Models Efficient VLM Inference Hybrid Transformer-State Space Model Architectures Multimodal Foundation Models Hybrid Mamba-Transformer Architectures

May 8, 2026

Priming: Hybrid State Space Models From Pre-trained Transformers

Hybrid State-Space models combine Attention with recurrent State-Space Model (SSM) layers, balancing eidetic memory from Attention with compressed fading memory from SSMs. This yields smaller Key-Value caches and faster decoding than Transformers, along with a richer architectural design space. Exploring that design space at scale has so far required training from scratch, a barrier that has kept most large-model Hybrid research within a narrow range of architectures. We introduce Priming, a method that turns Hybrid architecture design from a pre-training problem into a knowledge transfer one. Priming initializes a Hybrid model from a pre-trained Transformer and, through short alignment and post-training phases, recovers downstream quality using less than 0.5% of the source model's pre-training token budget. Priming is agnostic to the source Transformer family (e.g., Qwen, Llama, Mistral), model class (dense or Mixture-of-Experts), and model scale. Priming enables us to run the first controlled comparison of SSM layer types at scale under identical conditions. We evaluate, Gated KalmaNet (GKA), Gated DeltaNet (GDN), and Mamba-2, and show that their expressiveness hierarchy, GKA>GDN>Mamba-2, directly predicts downstream performance on long-context reasoning tasks. We scale Priming to 8B/32B reasoning models with native 128K contexts. Our Hybrid GKA 32B improves over its source Qwen3-32B by +3.8 average reasoning points, while staying within 1% of a Transformer post-trained on the same data and enabling up to 2.3x higher decode throughput. To foster research on Hybrid architectures, we release a model zoo of primed Hybrid models for long-context reasoning and instruction following, together with the Priming training and inference code (Sequence Parallelism algorithms for long-context training, optimized GKA kernels, and vLLM serving plugin), all under Apache~2.0 License.

Aditya Chattopadhyay, Elvis Nunez, Prannay Kaul +6

AWS Agentic AI

State Space Models Long-Context Language Model Inference LLM Inference Acceleration Transfer Learning Long-Context Inference Hybrid Transformer-State Space Model Architectures+2

May 3, 2026

QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL

Offline goal-conditioned RL (GCRL) learns goal-reaching policies from static datasets, but real-world datasets are often partially observable and history-dependent, exhibiting a mix of Markovian and non-Markovian that violate standard RL assumptions. History-aware sequence models such as Decision Transformer (DT) are a natural fit for long-term dependency modeling, yet pure attention is inefficient and brittle when handling local Markovian structure and long-range context simultaneously. Although recent hybrid architectures (e.g., LSDT) introduce local extractors to improve local dependencies modeling, the fixed-window extraction cannot adapt its effective memory to varying dependency lengths in temporally heterogeneous settings, often truncating long-range context rather than compressing its content adaptively. Moreover, sequential offline GCRL faces a key bottleneck: under sparse rewards, return-to-go (RTG) becomes non-discriminative across sub-trajectories, providing little guidance signal for stitching goal-reaching behaviors from diverse demonstrations. To address these, we propose QHyer, which replaces RTG with a flow-parameterized, state-conditioned goal-reaching Q-estimator to support stitching across demonstrations, and introduces a gated Hybrid Attention-Mamba backbone that performs content-adaptive history compression while preserving local dynamics. Extensive experiments demonstrate that QHyer achieves state-of-the-art performance on both non-Markovian and Markovian datasets, validating its effectiveness for diverse scenarios.

Xing Lei, Jincheng Wang, Xuetao Zhang +1

National Key Laboratory of Human-Machine Hybrid Augmented Intelligence and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University · Computer Science, University College London · School of Engineering, Westlake University

Hybrid Mamba-Transformer Architectures Offline RL Sparse-Reward RL Goal-Conditioned RL

Apr 14, 2026

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemotron 3 Super is the first model in the Nemotron 3 family to 1) be pre-trained in NVFP4, 2) leverage LatentMoE, a new Mixture-of-Experts architecture that optimizes for both accuracy per FLOP and accuracy per parameter, and 3) include MTP layers for inference acceleration through native speculative decoding. We pre-trained Nemotron 3 Super on 25 trillion tokens followed by post-training using supervised fine tuning (SFT) and reinforcement learning (RL). The final model supports up to 1M context length and achieves comparable accuracy on common benchmarks, while also achieving up to 2.2x and 7.5x higher inference throughput compared to GPT-OSS-120B and Qwen3.5-122B, respectively. Nemotron 3 Super datasets, along with the base, post-trained, and quantized checkpoints, are open-sourced on HuggingFace.

NVIDIA, :, Aakshita Chandiramani +544

Hybrid Transformer-State Space Model Architectures Mixture-of-Experts Language Models Language Model Pretraining Hybrid Mamba-Transformer Architectures LLM Inference Acceleration

Mar 22, 2026

HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit

Audio representation learning typically evaluates design choices such as input frontend, sequence backbone, and sequence length in isolation. We show that these axes are coupled, and conclusions from one setting often do not transfer to others. We introduce HELIX, a controlled framework comparing pure Mamba, pure attention, and a minimal hybrid with a single attention bottleneck. All models are parameter-matched at about 8.3M parameters to isolate architectural effects. Across six datasets, we find that the preferred input representation depends on the backbone, and that attention hurts performance on short, stationary audio but becomes important at longer sequence lengths. On a 5-minute speaker identification task with 30,000 tokens, pure attention fails with out-of-memory errors, while HELIX closes an 11.5-point gap over pure Mamba.

Khushiyant, Param Thakkar

Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany · Department of Computer Engineering and Information Technology, Veermata Jijabai Technological Institute, Mumbai, India

Audio Representation Learning Hybrid Mamba-Transformer Architectures Hybrid Attention Mamba

Mar 8, 2026

InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model

Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic complexity, whereas Mamba-style selective state-space models (SSMs) scale linearly but often struggle to capture high-rank and synchronous global interactions. We present a consistency boundary analysis that characterizes when diagonal short-memory SSMs can approximate causal attention and identifies structural gaps that remain. Motivated by this analysis, we propose InfoMamba, an attention-free hybrid architecture. InfoMamba replaces token-level self-attention with a concept bottleneck linear filtering layer that serves as a minimal-bandwidth global interface and integrates it with a selective recurrent stream through information-maximizing fusion (IMF). IMF dynamically injects global context into the SSM dynamics and encourages complementary information usage through a mutual-information-inspired objective. Extensive experiments on classification, dense prediction, and non-vision tasks show that InfoMamba consistently outperforms strong Transformer and SSM baselines, achieving competitive accuracy-efficiency trade-offs while maintaining near-linear scaling.

Youjin Wang, Jiaqiao Zhao, Rong Fu +5

Renmin University of China, Beijing, China · University of Macau, Macau SAR, China · Central South University, Changsha, China +1

Hybrid Mamba-Transformer Architectures Hybrid Transformer-State Space Model Architectures Sequence Modeling Selective SSMs Self-Attention

Mar 3, 2026

MaBERT:A Padding Safe Interleaved Transformer Mamba Hybrid Encoder for Efficient Extended Context Masked Language Modeling

Self attention encoders such as Bidirectional Encoder Representations from Transformers(BERT) scale quadratically with sequence length, making long context modeling expensive. Linear time state space models, such as Mamba, are efficient; however, they show limitations in modeling global interactions and can suffer from padding induced state contamination. We propose MaBERT, a hybrid encoder that interleaves Transformer layers for global dependency modeling with Mamba layers for linear time state updates. This design alternates global contextual integration with fast state accumulation, enabling efficient training and inference on long inputs. To stabilize variable length batching, we introduce paddingsafe masking, which blocks state propagation through padded positions, and mask aware attention pooling, which aggregates information only from valid tokens. On GLUE, MaBERT achieves the best mean score on five of the eight tasks, with strong performance on the CoLA and sentence pair inference tasks. When extending the context from 512 to 4,096 tokens, MaBERT reduces training time and inference latency by 2.36x and 2.43x, respectively, relative to the average of encoder baselines, demonstrating a practical long context efficient encoder.

Jinwoong Kim, Sangjin Park

Graduate School of Industrial Data Engineering, Hanyang University, Seoul, Republic of Korea

Hybrid Transformer-State Space Model Architectures Long-Context Language Modeling Hybrid Mamba-Transformer Architectures Sequence Modeling Long-Context Language Model Inference Masked Language Modeling+1

Mar 1, 2026

Efficient Extractive Summarization with MAMBA-Transformer Hybrids for Low-Resource Scenarios

Extractive summarization of long documents is bottlenecked by quadratic complexity, often forcing truncation and limiting deployment in resource-constrained settings. We introduce the first Mamba-Transformer hybrid for extractive summarization, combining the semantic strength of pre-trained transformers with the linear-time processing of state space models. Leveraging Mamba's ability to process full documents without truncation, our approach preserves context while maintaining strong summarization quality. The architecture includes: (1) a transformer encoder for sentence-level semantics, (2) a Mamba state space model to capture inter-sentence dependencies efficiently, and (3) a linear classifier for sentence relevance prediction. Across news, argumentative, and scientific domains under low-resource conditions, our method achieves: (1) large gains over BERTSUM and MATCHSUM, including +0.23 ROUGE-1 on ArXiv and statistically significant improvements on all datasets (p < 0.001); (2) consistent advantages across domains, strongest on the longest documents; (3) robust performance with limited training data; and (4) 24-27% faster inference on news summarization (CNN/DailyMail). We introduce the first hybrid Transformer-state space architecture for summarization, showing significant ROUGE improvements in low-resource scenarios.

Nisrine Ait Khayi

Independent Researcher · University of Memphis

Hybrid Transformer-State Space Model Architectures Text Summarization Hybrid Mamba-Transformer Architectures Long-Context Modeling Sequence Modeling State Space Models

Mar 1, 2026

VP-Hype: A Hybrid Mamba-Transformer Framework with Visual-Textual Prompting for Hyperspectral Image Classification

Accurate classification of hyperspectral imagery (HSI) is often frustrated by the tension between high-dimensional spectral data and the extreme scarcity of labeled training samples. While hierarchical models like LoLA-SpecViT have demonstrated the power of local windowed attention and parameter-efficient fine-tuning, the quadratic complexity of standard Transformers remains a barrier to scaling. We introduce VP-Hype, a framework that rethinks HSI classification by unifying the linear-time efficiency of State-Space Models (SSMs) with the relational modeling of Transformers in a novel hybrid architecture. Building on a robust 3D-CNN spectral front-end, VP-Hype replaces conventional attention blocks with a Hybrid Mamba-Transformer backbone to capture long-range dependencies with significantly reduced computational overhead. Furthermore, we address the label-scarcity problem by integrating dual-modal Visual and Textual Prompts that provide context-aware guidance for the feature extraction process. Our experimental evaluation demonstrates that VP-Hype establishes a new state of the art in low-data regimes. Specifically, with a training sample distribution of only 2%, the model achieves Overall Accuracy (OA) of 99.69% on the Salinas dataset and 99.45% on the Longkou dataset. These results suggest that the convergence of hybrid sequence modeling and multi-modal prompting provides a robust path forward for high-performance, sample-efficient remote sensing.

Abdellah Zakaria Sellam, Fadi Abdeladhim Zidi, Salah Eddine Bekhouche +4

Institute of Applied Sciences and Intelligent Systems (ISASI), CNR, 73100 Lecce, Italy · Dept. of Engineering for Innovation, University of Salento, 73100 Lecce, Italy · VSC Laboratory, Department of Electronics and Automation, University of Biskra, Biskra, Algeria +4

Hybrid Mamba-Transformer Architectures Hyperspectral Image Classification Hyperspectral Imaging

Feb 27, 2026

Stateful Token Reduction for Long-Video Hybrid VLMs

Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as token pruning. We study token reduction in hybrid Mamba--Transformer VLMs and find that it is stateful: Mamba layers maintain a recurrent state that accumulates information from earlier tokens, allowing discarded tokens to persist, so reduction behaves more like compression than dropping.We support this view with a representation-based probing method measuring how much information from discarded tokens is retained, and analyze layer-wise sparsity and cross-layer importance stability. Our findings show importance is sparse within layers but unstable across layers, making aggressive early pruning unreliable while hybrids remain robust to later reduction.Motivated by this, we propose a hybrid-aware token reduction framework with a low-to-high progressive schedule and a unified query-conditioned importance score for attention and Mamba layers. For Mamba, excluding the position-dependent decay from the recurrence produces a stronger selection signal. Across long-video benchmarks, our method achieves

3.8{\times}

--

4.2{\times}

prefilling speedups at a 25% token budget while maintaining near-baseline accuracy and improving with light finetuning. Hybrid models benefit from aggressive reduction, improving both efficiency and accuracy, whereas Transformers exhibit the standard trade-off. Our method also outperforms prior baselines on the same hybrid backbone and combines effectively with visual redundancy reduction methods.

Jindong Jiang, Amala Sanjay Deshmukh, Kateryna Chumachenko +7

NVIDIA

Hybrid Mamba-Transformer Architectures Efficient VLM Inference Video-Language Models Multimodal Token Compression Visual Token Compression

Sep 28, 2025

HyMaTE: A Hybrid Mamba and Transformer Model for EHR Representation Learning

Electronic health Records (EHRs) have become a cornerstone in modern-day healthcare. They are a crucial part for analyzing the progression of patient health; however, their complexity, characterized by long, multivariate sequences, sparsity, and missing values poses significant challenges in traditional deep learning modeling. While Transformer-based models have demonstrated success in modeling EHR data and predicting clinical outcomes, their quadratic computational complexity and limited context length hinder their efficiency and practical applications. On the other hand, State Space Models (SSMs) like Mamba present a promising alternative offering linear-time sequence modeling and improved efficiency for handling long sequences, but focus mostly on mixing sequence-level information rather than channel-level data. To overcome these challenges, we propose HyMaTE (A Hybrid Mamba and Transformer Model for EHR Representation Learning), a novel hybrid model tailored for representing longitudinal data, combining the strengths of SSMs with advanced attention mechanisms. By testing the model on predictive tasks on multiple clinical datasets, we demonstrate HyMaTE's ability to capture an effective, richer, and more nuanced unified representation of EHR data. Additionally, the interpretability of the outcomes achieved by self-attention illustrates the effectiveness of our model as a scalable and generalizable solution for real-world healthcare applications. Codes are available at: https://github.com/healthylaife/HyMaTE.

Md Mozaharul Mottalib, Thao-Ly T. Phan, Rahmatollah Beheshti

University of Delaware Newark, Delaware, USA · Thomas Jefferson University & Nemours Children’s Health Wilmington, Delaware, USA

Representation Learning Hybrid Mamba-Transformer Architectures Longitudinal EHR Modeling Time Series Transformers