One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception

• URL: http://arxiv.org/abs/2605.17907v1
• Date: Mon, 18 May 2026 06:14:30 GMT
• Title: One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception
• Abstract summary: We propose UniTrans, a universal any-to-any feature modality translation model that instantiates translators on the fly for arbitrary modalities.<n>UniTrans pretrains a bank of expert parameters and learns their combination coefficients as a function of source-to-target modality mapping.<n>Experiments on OPV2V-H and DAIR-V2X demonstrate that UniTrans consistently outperforms state-of-the-art methods in both simulated and real-world settings.
• Score: 14.59409728479271
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: By sharing intermediate features, collaborative perception extends each agent's sensing beyond standalone limits, but real-world feature modality heterogeneity remains a key barrier to effective fusion. Most existing methods, including direct adaption and protocol-based transformation, typically rely on training adapters for newly emerging feature modalities and often require additional retraining or fine-tuning. Such repeated training is costly and is often infeasible across manufacturers due to model and data privacy constraints, limiting real-world scalability. To address this issue, we propose UniTrans, a universal any-to-any feature modality translation model that instantiates translators on the fly for arbitrary modalities. UniTrans pretrains a bank of translator expert parameters and learns their combination coefficients as a function of source-to-target modality mapping. The mapping is measured in a modality-intrinsic latent space, where an intrinsic encoder extracts modality-specific yet scene-invariant codes from single-frame intermediate features, enabling UniTrans to instantiate translators in a zero-shot manner. Experiments on OPV2V-H and DAIR-V2X demonstrate that UniTrans consistently outperforms state-of-the-art methods in both simulated and real-world settings, enabling efficient any-to-any translation through a universal model. The code is available at https://github.com/CheeryLeeyy/UniTrans.

Related papers

• How Far Do Simple Transformations Translate Across Text Embedding Models? [1.7812673697676977]
  We investigate whether simple transformations can translate representations across heterogeneous text embedding models.<n>We test the hypothesis of latent universality in a realistic text setting beyond simplified benchmarks.<n>Overall, the results show that heterogeneous embedding spaces are not universally related by simple mappings as often suggested in some literature.
  arXiv  Detail & Related papers  (2026-08-06T12:57:01Z)
• Any2Any: Unified Arbitrary Modality Translation for Remote Sensing [41.79987718008628]
  Multi-modal remote sensing imagery provides complementary observations of the same geographic scene.<n> Existing cross-modal translation methods treat each modality pair as an independent task.<n>We formulate Any-to-Any translation as inference over a shared latent representation of the scene.
  arXiv  Detail & Related papers  (2026-03-04T14:33:26Z)
• Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs [69.28193153685893]
  Large Language Models (LLMs) frequently exhibit strong translation abilities, even without task-specific fine-tuning.<n>To demystify this process, we leverage Sparse Autoencoders (SAEs) and introduce a novel framework for identifying task-specific features.<n>Our work not only decodes a core component of the translation mechanism in LLMs but also provides a blueprint for using internal model mechanism to create more robust and efficient models.
  arXiv  Detail & Related papers  (2026-01-16T06:29:07Z)
• Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning [5.904095466127043]
  Federated learning (FL) provides a promising paradigm for collaboratively training machine learning models across distributed data sources.<n>We propose an FL framework that provides inherent interpretations using prototypes and lightweight adapter modules.<n>We demonstrate inherent interpretable capabilities and perform a classification task, which shows improvements in accuracy over baseline algorithms.
  arXiv  Detail & Related papers  (2025-07-08T10:30:08Z)
• LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation [102.1527101235251]
  LangTraj is a language-conditioned scene-diffusion model that simulates the joint behavior of all agents in traffic scenarios.<n>By conditioning on natural language inputs, LangTraj provides flexible and intuitive control over interactive behaviors.<n>LangTraj demonstrates strong performance in realism, language controllability, and language-conditioned safety-critical simulation.
  arXiv  Detail & Related papers  (2025-04-15T17:14:06Z)
• One-for-All: Towards Universal Domain Translation with a Single StyleGAN [86.33216867136639]
  We propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains.<n>The proposed UniTranslator is versatile and capable of performing various tasks, including style mixing, stylization, and translations.<n>UniTranslator surpasses the performance of existing general-purpose models and performs well against specialized models in representative tasks.
  arXiv  Detail & Related papers  (2023-10-22T08:02:55Z)
• Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation [50.54059385277964]
  We present a novel data augmentation paradigm termed Continuous Semantic Augmentation (CsaNMT) CsaNMT augments each training instance with an adjacency region that could cover adequate variants of literal expression under the same meaning.
  arXiv  Detail & Related papers  (2022-04-14T08:16:28Z)
• Tight Integrated End-to-End Training for Cascaded Speech Translation [40.76367623739673]
  A cascaded speech translation model relies on discrete and non-differentiable transcription. Direct speech translation is an alternative method to avoid error propagation. This work explores the feasibility of collapsing the entire cascade components into a single end-to-end trainable model.
  arXiv  Detail & Related papers  (2020-11-24T15:43:49Z)
• VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation [77.82373082024934]
  We plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. It can effectively avoid the degeneration of predicting masked words only conditioned on the context in its own language. The proposed cross-lingual model delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark.
  arXiv  Detail & Related papers  (2020-10-30T03:41:38Z)
• Cross-lingual Semantic Role Labeling with Model Transfer [49.85316125365497]
  Cross-lingual semantic role labeling can be achieved by model transfer under the help of universal features. We propose an end-to-end SRL model that incorporates a variety of universal features and transfer methods.
  arXiv  Detail & Related papers  (2020-08-24T09:37:45Z)

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.