ZetaGPT: A Reference Implementation of Positional--Encoding--Free State--Space--Attention Language Models

• URL: http://arxiv.org/abs/2608.09432v1
• Date: Mon, 10 Aug 2026 11:05:16 GMT
• Title: ZetaGPT: A Reference Implementation of Positional--Encoding--Free State--Space--Attention Language Models
• Abstract summary: This work explores a language model architecture that implicitly encodes positional information before attention computation.<n>We present textscZetaGPT, a compact hybrid language model designed for research, rapid prototyping, algorithm verification, and educational applications.
• Score: 0.304585143845864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based language models rely on self-attention, whose computation is permutation-equivariant and therefore lacks an intrinsic mechanism for representing token order. Existing architectures address this limitation by explicitly incorporating positional information through learned positional embeddings or hand-crafted positional encodings, such as rotary positional encoding (RoPE), treating positional information as an architecturally acquired capability rather than an inherent property of the model. Motivated by the pursuit of positional-encoding-free architectures, this work explores a language model architecture that integrates causal state-space equations to implicitly encode positional information before attention computation. Specifically, each model block applies a causal state-space equation before self-attention, allowing recurrent state dynamics to encode sequential information into token representations. Consequently, subsequent attention layers operate on position-aware representations without requiring explicit positional encodings while retaining the expressive modeling capacity of self-attention. We present \textsc{ZetaGPT}, a compact hybrid language model designed for research, rapid prototyping, algorithm verification, and educational applications. In addition to the proposed architecture, \textsc{ZetaGPT} provides a fully open-source, end-to-end training pipeline encompassing dataset construction, tokenizer training, pretraining, supervised fine-tuning, reinforcement learning from human feedback (RLHF), and chain-of-thought (CoT) reasoning via pure reinforcement learning. To the best of our knowledge, \textsc{ZetaGPT} is the first open-source small language model without explicit positional encoding and establishes a compact, reproducible reference implementation for the development and empirical study of positional-encoding-free language models.

Related papers

• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• The Model Is Not the Product: A Dual-Pillar Architecture for Local-First Psychological Coaching [51.56484100374058]
  This report introduces Psych LM, an iOS application that validates the thesis that, for such applications, the surrounding architecture is paramount.<n>Psych LM runs a local, on-device language model within a purpose-built, local-first runtime designed for behavioral and life-coaching applications.
  arXiv  Detail & Related papers  (2026-05-23T05:49:11Z)
• Structure from Rank: Rank-Order Coding as a Bridge from Sequence to Structure [42.559054240539915]
  We propose a rank-order based neural network inspired by the STG-LIFG-PMC pathway.<n>We first demonstrate that this model efficiently compresses input while retaining the capacity to reconstruct full utterances from partial cues.<n>We then show that the network exhibits global-level novelty detection similar to the P3B novelty wave.
  arXiv  Detail & Related papers  (2026-03-09T13:41:45Z)
• RePo: Language Models with Context Re-Positioning [10.269249887819988]
  In-context learning is fundamental to modern Large Language Models (LLMs)<n> prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices.<n>We propose RePo, a novel mechanism that reduces extraneous load via context re-positioning.
  arXiv  Detail & Related papers  (2025-12-16T13:30:30Z)
• Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning [29.745218855471787]
  Tokenization is a necessary component within the current architecture of many language mod-els.<n>We argue that tokenization is necessary for reasonably human-like language performance.<n>We discuss implications for architectural choices, meaning construction, the primacy of language for thought.
  arXiv  Detail & Related papers  (2024-12-14T18:18:52Z)
• CLSP: High-Fidelity Contrastive Language-State Pre-training for Agent State Representation [49.19402798479942]
  multimodal learning has become an important research area for artificial intelligence. For intelligent agents, the state is a crucial modality to convey precise information alongside common modalities like images, videos, and language. We propose a High-Fidelity Contrastive Language-State Pre-training method, which can accurately encode state information into general representations.
  arXiv  Detail & Related papers  (2024-09-24T07:08:00Z)
• Physics of Language Models: Part 1, Learning Hierarchical Language Structures [51.68385617116854]
  Transformer-based language models are effective but complex, and understanding their inner workings and reasoning mechanisms is a significant challenge.<n>We introduce a family of synthetic CFGs that produce hierarchical rules, capable of generating lengthy sentences.<n>We demonstrate that generative models like GPT can accurately learn and reason over CFG-defined hierarchies and generate sentences based on it.
  arXiv  Detail & Related papers  (2023-05-23T04:28:16Z)
• Word Order Matters when you Increase Masking [70.29624135819884]
  We study the effect of removing position encodings on the pre-training objective itself, to test whether models can reconstruct position information from co-occurrences alone. We find that the necessity of position information increases with the amount of masking, and that masked language models without position encodings are not able to reconstruct this information on the task.
  arXiv  Detail & Related papers  (2022-11-08T18:14:04Z)
• Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
  We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
  arXiv  Detail & Related papers  (2020-10-24T11:55:28Z)
• Rethinking Positional Encoding in Language Pre-training [111.2320727291926]
  We show that in absolute positional encoding, the addition operation applied on positional embeddings and word embeddings brings mixed correlations. We propose a new positional encoding method called textbfTransformer with textbfUntied textPositional textbfEncoding (T)
  arXiv  Detail & Related papers  (2020-06-28T13:11:02Z)
• Sequence Model Design for Code Completion in the Modern IDE [3.4824234779710452]
  We propose a novel design for predicting top-k next tokens that combines static analysis' ability to enumerate all valid keywords and in-scope identifiers with the ability of a language model to place a probability distribution over them. Our model mixes character-level input representation with token output to represent out-of-vocabulary (OOV) tokens meaningfully and minimize prediction latency.
  arXiv  Detail & Related papers  (2020-04-10T22:40:49Z)

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.