No article text was recorded for this version.
discrete spatial tokenization
Version 2 of 2105 papers128 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Geometry Informed Tokenization of Molecules for Language Model Generation
- Blog: LayoutTransformer: Layout Generation and Completion with Self-attention
- Blog: Lane2Seq: Towards Unified Lane Detection via Sequence Generation
- Blog: Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders
- Blog: SeqTrack: Sequence to Sequence Learning for Visual Object Tracking
- Blog: ReCo: Region-Controlled Text-to-Image Generation
- Blog: Global-Local Tree Search in VLMs for 3D Indoor Scene Generation
- Blog: CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs
- Blog: Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models
- Blog: UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
- Blog: Grounding-IQA: Multimodal Language Grounding Model for Image Quality Assessment
- Blog: Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
- Blog: Learning Visual Prior via Generative Pre-Training
- Blog: PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
- Blog: ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning
- Blog: OmniViD: A Generative Framework for Universal Video Understanding
- Blog: Classifier Labels as Language Grounding for Explanations
- Blog: In-Context Learning Enables Robot Action Prediction in LLMs
- Blog: SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data
- Blog: Unifying Vision, Text, and Layout for Universal Document Processing
- Blog: A Unified Sequence Interface for Vision Tasks
- Blog: SeqTR: A Simple Yet Universal Network for Visual Grounding
- Blog: Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks
- Blog: CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction
- Blog: Diagnostic Prediction Using Discomfort Drawings with IBTM
- Blog: PolyGen: An Autoregressive Generative Model of 3D Meshes
- Blog: Pix2seq: A Language Modeling Framework for Object Detection
- Blog: Integrating eye gaze into machine learning using fractal curves
- Blog: AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models
- Blog: Layout Generation and Completion with Self-attention
- Blog: Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs
- Blog: Embodied Understanding of Driving Scenarios
- Blog: Autoregressive Boltzmann Generators
- Blog: Discriminative Dictionary Learning for Autism Spectrum Disorder Identification
- Blog: Crossing the Format Boundary of Text and Boxes: Towards Unified Vision-Language Modeling
- Blog: UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
- Blog: Grounding Multimodal Large Language Models to the World
- Blog: ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model
- Blog: Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment
- Blog: A Unified Sequence Interface for Vision Tasks
- Blog: DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
- Blog: See then Tell: Enhancing Key Information Extraction with Vision Grounding
- Blog: SpatialLM: Training Large Language Models for Structured Indoor Modeling
- Blog: ChartLens: Fine-grained Visual Attribution in Charts
- Blog: Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation
- Blog: Engineering Sketch Generation for Computer-Aided Design
- Blog: Learning to reason over scene graphs: a case study of finetuning GPT-2 into a robot language model for grounded task planning
- Blog: Avi: Action from Volumetric Inference
- Blog: Kosmos-2: Grounding Multimodal Large Language Models to the World
- Blog: PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
- Blog: MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning
- Blog: SceneScript: Reconstructing Scenes with an Autoregressive Structured Language Model
- Blog: VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks
- Blog: LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
- Blog: GiT: Towards Generalist Vision Transformer Through Universal Language Interface
- Blog: Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model
- Blog: Implicit Concept Removal of Diffusion Models
- Blog: SpatialLM: Training Large Language Models for Structured Indoor Modeling
- Blog: Grounding Spatial Relations in Text-Only Language Models
- Blog: Global-Local Tree Search in VLMs for 3D Indoor Scene Generation
Showing 60 of 105 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_discrete_spatial_tokenization_9ad4ecda,
title = {discrete spatial tokenization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/discrete-spatial-tokenization/rdr_9ad4ecdafc5e410387b724571499537f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_discrete_spatial_tokenization_9ad4ecda_v2,
title = {discrete spatial tokenization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/discrete-spatial-tokenization/rdr_9ad4ecdafc5e410387b724571499537f/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}