HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

• URL: http://arxiv.org/abs/2606.13289v1
• Date: Thu, 11 Jun 2026 12:46:07 GMT
• Title: HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
• Abstract summary: We present HYDRA-X, the first UMM that unifies image and video tokenization within a single Vision Transformer (ViT)<n>Our design is driven by two challenges: injecting image and video semantic awareness into the latent space and decompressing it.<n>Instantiated at the 7B model, HYDRA-X achieves strong performance across image and video understanding and generation tasks.
• Score: 48.01715215603613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDRA-X, the first UMM that unifies image and video tokenization within a single Vision Transformer (ViT). Our design is driven by two core challenges: efficiently injecting spatiotemporal reconstruction capability into a native ViT, and embedding image- and video-level semantic awareness into the latent space. To address the first, comprehensive ablations reveal two key findings: (1) frame-level causal temporal attention suffices for visual reconstruction, whereas full spatiotemporal attention degrades it; and (2) hierarchical temporal compression substantially outperforms single-step alternatives. To tackle the second, we propose a lightweight decompressor that upsamples temporally compressed features under joint image-video teacher supervision, thereby enforcing complementary semantic structures within the compact latent space. Building on this holistic tokenizer, we further propose a principled improvement of the editing pipeline: source-target interaction should occur at the latent level inside the tokenizer rather than at the semantic level inside the LLM, substantially improving editing consistency and accelerating convergence. Instantiated at the 7B dense model, HYDRA-X achieves strong performance across image and video understanding and generation tasks, paving the way for future unified-tokenizer UMMs.

Related papers

• Beyond Text Conditioning: A Systematic Study of MLLM-DiT Fusion for Video Generation [50.92925099642139]
  Diffusion Transformers (DiTs) have become the dominant paradigm for high-fidelity video generation, yet their ability to perform high-level semantic planning remains limited.<n>We propose BiVidGen, a hybrid framework where an MLLM first generates semantic visual tokens and a DiT renders videos conditioned on both text and these tokens via multi-layer cross-attention.
  arXiv  Detail & Related papers  (2026-08-14T07:40:41Z)
• SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models [31.77829987533264]
  We propose a novel unified multimodal framework featuring textbfSemantic-textbfPixel self-alignment and textbfRouting (textbfSPAR)<n>To reconcile semantic perception with pixel-level reconstruction, we introduce an asymmetric dual-stream unified tokenizer. A lightweight semantic stream anchors discriminative features, while a Transformer-augmented pixel stream recovers fine-grained visual details into a unified compact latent space.
  arXiv  Detail & Related papers  (2026-06-22T08:48:19Z)
• Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification [80.62512020268626]
  UniAR is a unified autoregressive framework where a single visual tokenizer serves as the key bridge between understanding and generation.<n>UniAR adapts a pretrained vision encoder with multi-level feature fusion and a lookup-free bitwise quantization scheme.<n>A diffusion-based visual decoder operates on discrete visual tokens to decode high-fidelity images.
  arXiv  Detail & Related papers  (2026-06-16T17:59:22Z)
• DAMS:Dual-Branch Adaptive Multiscale Spatiotemporal Framework for Video Anomaly Detection [7.117824587276951]
  This study offers a dual-path architecture called the Dual-Branch Adaptive Multiscale Stemporal Framework (DAMS), which is based on multilevel feature and decoupling fusion.<n>The main processing path integrates the Adaptive Multiscale Time Pyramid Network (AMTPN) with the Convolutional Block Attention Mechanism (CBAM)
  arXiv  Detail & Related papers  (2025-07-28T08:42:00Z)
• Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations [131.33758144860988]
  Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity.<n>Current end-to-end frameworks suffer a critical spatial-temporal trade-off.<n>We propose a simple yet effective spatial-temporal decoupled framework that decomposes representations into spatial features for layouts and temporal features for motion dynamics.
  arXiv  Detail & Related papers  (2025-07-07T06:54:44Z)
• Cross Paradigm Representation and Alignment Transformer for Image Deraining [40.66823807648992]
  We propose a novel Cross Paradigm Representation and Alignment Transformer (CPRAformer)<n>Its core idea is the hierarchical representation and alignment, leveraging the strengths of both paradigms to aid image reconstruction.<n>We use two types of self-attention in the Transformer blocks: sparse prompt channel self-attention (SPC-SA) and spatial pixel refinement self-attention (SPR-SA)
  arXiv  Detail & Related papers  (2025-04-23T06:44:46Z)
• Making LLaMA SEE and Draw with SEED Tokenizer [69.1083058794092]
  We introduce SEED, an elaborate image tokenizer that empowers Large Language Models with the ability to SEE and Draw. With SEED tokens, LLM is able to perform scalable multimodal autoregression under its original training recipe. SEED-LLaMA has exhibited compositional emergent abilities such as multi-turn in-context multimodal generation.
  arXiv  Detail & Related papers  (2023-10-02T14:03:02Z)
• Planting a SEED of Vision in Large Language Model [73.17530130368053]
  We present SEED, an elaborate image tokenizer that empowers Large Language Models (LLMs) with the ability to SEE and Draw at the same time. This version of SEED was trained in 5.7 days using only 64 V100 GPUs and 5M publicly available image-text pairs.
  arXiv  Detail & Related papers  (2023-07-16T13:41:39Z)

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.