{"total":82,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440,"area":null},{"id":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121,"area":"wm"},{"id":"2311.01017","title":"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","created":"2023-11-02","cited_by_count":106,"area":"wm"},{"id":"2411.06070","title":"GFT: Graph Foundation Model with Transferable Tree Vocabulary","created":"2024-11-09","cited_by_count":85,"area":null},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80,"area":null},{"id":"2411.02038","title":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","created":"2024-11-04","cited_by_count":80,"area":null},{"id":"2406.11837","title":"Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%","created":"2024-06-17","cited_by_count":68,"area":null},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"id":"2410.06424","title":"Restructuring Vector Quantization with the Rotation Trick","created":"2024-10-08","cited_by_count":51,"area":null},{"id":"2401.13537","title":"Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models","created":"2024-01-24","cited_by_count":46,"area":null},{"id":"2403.05618","title":"OmniJet-$\\alpha$: The first cross-task foundation model for particle physics","created":"2024-03-08","cited_by_count":43,"area":null},{"id":"2411.02393","title":"Adaptive Length Image Tokenization via Recurrent Allocation","created":"2024-11-04","cited_by_count":43,"area":null},{"id":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34,"area":"diffusion"},{"id":"2401.14732","title":"Residual Quantization with Implicit Neural Codebooks","created":"2024-01-26","cited_by_count":25,"area":null},{"id":"2310.05718","title":"EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders","created":"2023-10-09","cited_by_count":16,"area":null},{"id":"2405.10812","title":"VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling","created":"2024-05-13","cited_by_count":15,"area":null},{"id":"2412.16326","title":"When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2503.15475","title":"Cube: A Roblox View of 3D Intelligence","created":"2025-03-19","cited_by_count":15,"area":null},{"id":"2412.10504","title":"Aspen Open Jets: Unlocking LHC Data for Foundation Models in Particle Physics","created":"2024-12-13","cited_by_count":14,"area":null},{"id":"2501.05534","title":"OmniJet-${\\alpha}_C$: Learning point cloud calorimeter simulations using generative transformers","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2503.17074","title":"Zero-Shot Styled Text Image Generation, but Make It Autoregressive","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2504.02817","title":"Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization","created":"2025-04-03","cited_by_count":13,"area":null},{"id":"2310.03004","title":"Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization","created":"2023-10-04","cited_by_count":10,"area":null},{"id":"2405.15840","title":"Learning the Language of Protein Structure","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2509.10140","title":"Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2509.21434","title":"Foundation models for high-energy physics","created":"2025-09-25","cited_by_count":10,"area":null},{"id":"2503.17760","title":"CODA: Repurposing Continuous VAEs for Discrete Tokenization","created":"2025-03-22","cited_by_count":8,"area":null},{"id":"2507.22920","title":"Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey","created":"2025-07-21","cited_by_count":8,"area":"mllm"},{"id":"2512.20308","title":"SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision","created":"2025-12-23","cited_by_count":8,"area":null},{"id":"2507.10547","title":"Quantize-then-Rectify: Efficient VQ-VAE Training","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2510.04961","title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2411.01801","title":"Bootstrapping Top-down Information for Self-modulating Slot Attention","created":"2024-11-04","cited_by_count":6,"area":"lr"},{"id":"2510.08757","title":"LOTION: Smoothing the Optimization Landscape for Quantized Training","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2503.14259","title":"Quantization-Free Autoregressive Action Transformer","created":"2025-03-18","cited_by_count":5,"area":"offlinerl"},{"id":"2506.21022","title":"Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2509.26469","title":"DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2604.18907","title":"Gradient-Based Program Synthesis with Neurally Interpreted Languages","created":"2026-04-20","cited_by_count":5,"area":null},{"id":"2407.04939","title":"Balance of Number of Embedding and their Dimensions in Vector Quantization","created":"2024-07-06","cited_by_count":4,"area":null},{"id":"2503.01261","title":"Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2603.26380","title":"Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2505.19014","title":"Tokenizing Electron Cloud in Protein-Ligand Interaction Learning","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2510.23240","title":"Autoregressive Styled Text Image Generation, but Make it Reliable","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2512.04149","title":"Enhancing next token prediction based pre-training for jet foundation models","created":"2025-12-03","cited_by_count":3,"area":null},{"id":"2602.02334","title":"VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2410.10180","title":"Gaussian Mixture Vector Quantization with Aggregated Categorical Posterior","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2506.20040","title":"Cross-Layer Discrete Concept Discovery for Interpreting Language Models","created":"2025-06-24","cited_by_count":2,"area":"mechinterp"},{"id":"2508.06588","title":"Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2508.10719","title":"Exploiting Discriminative Codebook Prior for Autoregressive Image Generation","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2406.09676","title":"Optimizing Byte-level Representation for End-to-end ASR","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2409.01591","title":"Dynamic Motion Synthesis: Masked Audio-Text Conditioned Spatio-Temporal Transformers","created":"2024-09-03","cited_by_count":1,"area":null},{"id":"2411.16468","title":"Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2412.07264","title":"QuantFormer: Learning to Quantize for Neural Activity Forecasting in Mouse Visual Cortex","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2503.22145","title":"Tokenization of Gaze Data","created":"2025-03-28","cited_by_count":1,"area":"mllm"},{"id":"2506.20297","title":"OLALa: Online Learned Adaptive Lattice Codes for Heterogeneous Federated Learning","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2512.06609","title":"Training-Free Vector Quantization via Gaussian VAEs","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2602.17133","title":"VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2602.18896","title":"Beyond Stationarity: Rethinking Codebook Collapse in Vector Quantization","created":"2026-02-21","cited_by_count":1,"area":"diffusion"},{"id":"2605.21195","title":"RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2607.15933","title":"Distributional Matching for Vector Quantization: A Unified Theoretical and Empirical Framework","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2607.19575","title":"VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2608.29179","title":"History-Conditioned Joint-Prefix Alignment for Generative Recommendation","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2503.08125","title":"Quantization Design for Deep Learning-Based CSI Feedback","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2506.09896","title":"A look at adversarial attacks on radio waveforms from discrete latent space","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2507.15386","title":"Learning to Gridize: Segment Physical World by Wireless Communication Channel","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2509.01400","title":"Distillation of a tractable model from the VQ-VAE","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2510.04220","title":"MASC: Boosting Autoregressive Image Generation with a Manifold-Aligned Semantic Clustering","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.09696","title":"Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.13331","title":"Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2512.01537","title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.22244","title":"Is Hierarchical Quantization Essential for Optimal Reconstruction?","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.01140","title":"Generalized Radius and Integrated Codebook Transforms for Differentiable Vector Quantization","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.15045","title":"VQ-DSC-R: Robust Vector Quantized-Enabled Digital Semantic Communication With OFDM Transmission","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.22304","title":"Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"id":"2605.08657","title":"Fitting Multilinear Polynomials for Logic Gate Networks","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.29859","title":"MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.11363","title":"NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.23626","title":"A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.02107","title":"A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.26774","title":"StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.15427","title":"Riemannian Graph Tokenizer for Structural Knowledge Transfer","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}