Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding

• URL: http://arxiv.org/abs/2608.03471v1
• Date: Tue, 04 Aug 2026 11:07:19 GMT
• Title: Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding
• Abstract summary: Generative Vision-Language Models (VLMs) commonly treat bounding-box coordinates as independent output symbols.<n>Hi-Token encodes each coordinate with axis-specific tokens for the hundreds, tens, and ones digits.<n>Hi-GAR complements this representation with a geometry-based reward for Group Relative Policy Optimization.
• Score: 22.205716720462647
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Vision-Language Models (VLMs) commonly treat bounding-box coordinates as independent output symbols, leaving numerical order and axis semantics implicit. We identify this representation as an important source of error in visual grounding. Hi-Token encodes each coordinate with axis-specific tokens for the hundreds, tens, and ones digits, which adds coarse-to-fine structure and increases token reuse while retaining the existing VLM architecture. Hi-GAR complements this representation with a geometry-based reward for Group Relative Policy Optimization (GRPO), using box overlap and coordinate accuracy at multiple scales. Controlled comparisons under matched training conditions show that Hi-Token improves localization throughout the evaluated IoU range. Hi-GAR further reduces low-overlap predictions and is used only during training. Experiments on three VLM backbones and the RefCOCO family show consistent gains across models and benchmarks. Hi-R1 achieves higher values than strong specialist baselines on most reported metrics. Analyses of token frequency, digit boundaries, object scale, and IoU distributions explain the effects of coordinate representation and reward training. The results show that structured coordinate generation provides an effective approach to generative visual grounding.

Related papers

• Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning [13.385292682258147]
  We present a representation-guided and geometry-enhanced tokenizer that learns discrete tokens under joint supervision.<n> Experiments on NAVSIM show improved reconstruction fidelity and representation consistency, competitive planning performance under a fixed decoder, and better generative quality under matched settings.
  arXiv  Detail & Related papers  (2026-06-01T09:02:32Z)
• HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution [2.4519602914420475]
  We present HiTokSR, a hierarchical token prediction framework.<n>We show that HiTokSR achieves state-of-the-art performance in both quality and reconstruction fidelity.
  arXiv  Detail & Related papers  (2026-05-31T11:02:58Z)
• LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding [80.49137401046201]
  We introduce a unified generative grounding and detection framework based on Parallel Box Decoding (PBD)<n>We show that PBD improves both decoding throughput and localization accuracy.<n>We further develop a scalable data engine and curate LocateAnything-Data, a large-scale dataset with more than 138 million training samples.
  arXiv  Detail & Related papers  (2026-05-26T17:59:12Z)
• What matters for Representation Alignment: Global Information or Spatial Structure? [64.67092609921816]
  Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features.<n>We investigate a fundamental question: what aspect of the target representation matters for generation, its textitglobal revisionsemantic information.<n>We replace the standard projection layer in REPA with a simple convolution layer and introduce a spatial normalization layer for the external representation.
  arXiv  Detail & Related papers  (2025-12-11T16:39:53Z)
• Detect Anything via Next Point Prediction [51.55967987350882]
  Rex- Omni is a 3B-scale MLLM that achieves state-of-the-art object perception performance.<n>On benchmarks like COCO and LVIS, Rex- Omni attains performance comparable to or exceeding regression-based models.
  arXiv  Detail & Related papers  (2025-10-14T17:59:54Z)
• Beyond BEV: Optimizing Point-Level Tokens for Collaborative Perception [17.654858416126093]
  Collaborative perception allows agents to enhance their perceptual capabilities by exchanging intermediate features.<n>Existing methods typically organize these intermediate features as 2D bird's-eye-view (BEV) representations.<n>We present CoPLOT, a novel Collaborative perception framework that utilizes Point-Level Optimized Tokens.
  arXiv  Detail & Related papers  (2025-08-27T07:27:42Z)
• Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections [15.488985833084408]
  We introduce Federated learning with Auxiliary projections (FedAux)<n>FedAux is a personalized subgraph FL framework that learns to align, compare, and aggregate heterogeneously distributed local models without sharing raw data or node embeddings.<n> Empirical evaluations across diverse graph benchmarks demonstrate that FedAux substantially outperforms existing baselines in both accuracy and personalization performance.
  arXiv  Detail & Related papers  (2025-05-29T09:17:49Z)
• Self-Supervised and Generalizable Tokenization for CLIP-Based 3D Understanding [87.68271178167373]
  We present a universal 3D tokenizer designed for scale-invariant representation learning with a frozen CLIP backbone.<n>S4Token is a tokenization pipeline that produces semantically-informed tokens regardless of scene scale.
  arXiv  Detail & Related papers  (2025-05-24T18:26:30Z)
• Compile Scene Graphs with Reinforcement Learning [69.36723767339001]
  Next-token prediction is the fundamental principle for training large language models (LLMs)<n>We introduce R1-SGG, a multimodal LLM (M-LLM) initially trained via supervised fine-tuning (SFT) on the scene graph dataset.<n>We design a set of graph-centric rewards, including three recall-based variants -- Hard Recall, Hard Recall+Relax, and Soft Recall.
  arXiv  Detail & Related papers  (2025-04-18T10:46:22Z)
• Spatial-spectral Hyperspectral Image Classification via Multiple Random Anchor Graphs Ensemble Learning [88.60285937702304]
  This paper proposes a novel spatial-spectral HSI classification method via multiple random anchor graphs ensemble learning (RAGE) Firstly, the local binary pattern is adopted to extract the more descriptive features on each selected band, which preserves local structures and subtle changes of a region. Secondly, the adaptive neighbors assignment is introduced in the construction of anchor graph, to reduce the computational complexity.
  arXiv  Detail & Related papers  (2021-03-25T09:31:41Z)

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.