{"total":72,"rows":[{"id":"2604.03208","title":"Hierarchical Planning with Latent World Models","created":"2026-04-03","cited_by_count":43,"area":"wm"},{"id":"2512.24617","title":"Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space","created":"2025-12-31","cited_by_count":17,"area":"lr"},{"id":"2602.11698","title":"SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion","created":"2026-02-12","cited_by_count":12,"area":null},{"id":"2509.18750","title":"False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models","created":"2025-09-23","cited_by_count":11,"area":null},{"id":"2602.08984","title":"Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models","created":"2026-02-09","cited_by_count":11,"area":null},{"id":"2510.10159","title":"BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data","created":"2025-10-11","cited_by_count":10,"area":null},{"id":"2512.15586","title":"Bolmo: Byteifying the Next Generation of Language Models","created":"2025-12-17","cited_by_count":9,"area":null},{"id":"2507.12720","title":"FLEXITOKENS: Flexible Tokenization for Evolving Language Models","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2510.21795","title":"Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attention","created":"2025-10-20","cited_by_count":8,"area":null},{"id":"2604.07466","title":"Cross-Tokenizer LLM Distillation through a Byte-Level Interface","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2605.05971","title":"Training Transformers for KV Cache Compressibility","created":"2026-05-07","cited_by_count":7,"area":"inference"},{"id":"2510.20280","title":"Context-level Language Modeling by Learning Predictive Context Embeddings","created":"2025-10-23","cited_by_count":6,"area":null},{"id":"2510.21954","title":"Model-Aware Tokenizer Transfer","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2601.13260","title":"Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2603.05815","title":"Hierarchical Latent Action Model","created":"2026-03-06","cited_by_count":6,"area":"wm"},{"id":"2603.15685","title":"DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression","created":"2026-03-15","cited_by_count":6,"area":"inference"},{"id":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2603.02023","title":"PonderLM-3: Adaptive Token-Wise Pondering with Differentiable Masking","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2605.01188","title":"Compute Optimal Tokenization","created":"2026-05-02","cited_by_count":4,"area":null},{"id":"2601.21420","title":"ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation","created":"2026-01-29","cited_by_count":3,"area":"moe"},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2602.10603","title":"dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2603.06351","title":"DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking","created":"2026-03-06","cited_by_count":3,"area":"diffusion"},{"id":"2603.11352","title":"TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2605.08044","title":"Fast Byte Latent Transformer","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2508.02247","title":"ByteGen: A Tokenizer-Free Generative Model for Orderbook Events in Byte Space","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2601.07141","title":"MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models","created":"2026-01-12","cited_by_count":2,"area":"safety"},{"id":"2602.20981","title":"Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2604.27263","title":"Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2605.06546","title":"Efficient Pre-Training with Token Superposition","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2508.05628","title":"H-Net++: Hierarchical Dynamic Chunking for Tokenizer-Free Language Modelling in Morphologically-Rich Languages","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2510.23043","title":"HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling","created":"2025-10-27","cited_by_count":1,"area":"ssm"},{"id":"2602.13194","title":"Semantic Chunking and the Entropy of Natural Language","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2603.03583","title":"ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.22325","title":"Hybrid Associative Memories","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2603.26097","title":"Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer","created":"2026-03-27","cited_by_count":1,"area":"deeprl"},{"id":"2605.09630","title":"Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models","created":"2026-05-10","cited_by_count":1,"area":"inference"},{"id":"2605.28769","title":"Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.08204","title":"Neural Field Tokenizations with Hierarchy and Spatial Locality Priors","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.28057","title":"MultiHashFormer: Hash-based Generative Language Models","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2607.02087","title":"SUNTA: Hierarchical Video Prediction with Surprise-based Chunking","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.05806","title":"Hierarchical Latent Prediction for Language Models","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2510.16987","title":"Back to Bytes: Revisiting Tokenization Through UTF-8","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2511.19963","title":"MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2601.03019","title":"DNACHUNKER: Learnable Tokenization for DNA Language Models","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2602.01007","title":"Distilling Token-Trained Models into Byte-Level Models","created":"2026-02-01","cited_by_count":0,"area":"distill"},{"id":"2602.13940","title":"You Can Learn Tokenization End-to-End with Reinforcement Learning","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2602.17739","title":"GeneZip: Region-Aware Compression for Long Context DNA Modeling","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.27859","title":"KazByte: Adapting Qwen models to Kazakh via Byte-level Adapter","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2605.12928","title":"The Efficiency Gap in Byte Modeling","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.30080","title":"Adaptive Targeted Dynamic Chunking for Tokenization-Free Hierarchical Model","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.04552","title":"LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.09019","title":"TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech","created":"2026-06-08","cited_by_count":0,"area":"inference"},{"id":"2606.13862","title":"SuperThoughts: Reasoning Tokens in Superposition","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.27320","title":"Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.05691","title":"Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.03599","title":"Disentangling Language Modeling and Boundaries","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.12756","title":"ReconSpan: Reconstruction-Guided Adaptive Latent Tokenization","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.15454","title":"Dynamic Multi-Byte Prediction With Hierarchical Language Models","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.17325","title":"What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.27658","title":"When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.10715","title":"NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.19291","title":"Why Pretraining Fails to Share Cross-Lingual Knowledge","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.05978","title":"Byte Language Models: Scaling, Emergent Abstractions, and Information Allocation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06805","title":"H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning","created":"2026-10-05","cited_by_count":0,"area":"wm"},{"id":"2610.11743","title":"TraceRelay: Attention-Aligned Recurrence over Rolling Traces","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.11790","title":"Easy to anticipate, hard to compute: boundary dependence finds the computed outputs that entropy patching misses","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13605","title":"zip2zip++: Towards Inference-Time Token Compression with Minimal Quality Loss","created":"2026-10-09","cited_by_count":0,"area":"inference"},{"id":"2610.14162","title":"Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.19210","title":"Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.19975","title":"LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation","created":"2026-10-14","cited_by_count":0,"area":"moe"}],"next_cursor":null}