Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement

• URL: http://arxiv.org/abs/2604.06155v1
• Date: Tue, 07 Apr 2026 17:54:22 GMT
• Title: Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement
• Abstract summary: Multi-Token Prediction (MTP) has shown promise in learning more structured representations.<n>We propose a novel method LSE-MTP, which anchors predictions to ground-truth hidden state trajectories.<n> Experiments on synthetic graphs and real-world Manhattan Taxi Ride show that LSE-MTP effectively bridges the gap between discrete tokens and continuous state representations.
• Score: 12.77109338375446
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Whether Large Language Models (LLMs) develop coherent internal world models remains a core debate. While conventional Next-Token Prediction (NTP) focuses on one-step-ahead supervision, Multi-Token Prediction (MTP) has shown promise in learning more structured representations. In this work, we provide a theoretical perspective analyzing the gradient inductive bias of MTP, supported by empirical evidence, showing that MTP promotes the convergence toward internal belief states by inducing representational contractivity via gradient coupling. However, we reveal that standard MTP often suffers from structural hallucinations, where discrete token supervision encourages illegal shortcuts in latent space that violate environmental constraints. To address this, we propose a novel method Latent Semantic Enhancement MTP (LSE-MTP), which anchors predictions to ground-truth hidden state trajectories. Experiments on synthetic graphs and real-world Manhattan Taxi Ride show that LSE-MTP effectively bridges the gap between discrete tokens and continuous state representations, enhancing representation alignment, reducing structural hallucinations, and improving robustness to perturbations.

Related papers

• AdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction [32.62594861280837]
  Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads.<n>We propose AdaMTP, an adaptive training paradigm that aligns the prediction horizon with the intrinsic predictability of the sequence.<n>Across mathematical reasoning, code generation, and general benchmarks on three backbones, AdaMTP consistently outperforms standard MTP in both task performance and inference speedup.
  arXiv  Detail & Related papers  (2026-08-01T04:18:49Z)
• Learning When to Listen: Gated Affect Fusion for Human Motion Prediction [0.0]
  We present a systematic study investigating the utility and temporal limitations of affect-conditioned forecasting in-the-wild.<n>We introduce the Gated Affect Transformer (GAT) to dynamically regulate cross-modal information flow.<n>Our findings provide empirical evidence that facial affect should be regarded as a complementary behavioral cue.
  arXiv  Detail & Related papers  (2026-07-01T00:47:02Z)
• Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs [54.16324124242172]
  Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models.<n>We identify a previously overlooked optimization pathology in existing latent visual reasoning methods.<n>We show that inference-time latent optimization, without any parameter updates, effectively unleashes the suppressed reasoning capacity of visual latents.
  arXiv  Detail & Related papers  (2026-05-04T15:36:12Z)
• OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation [61.18260993245354]
  Chain-of-Thought (CoT) reasoning is a powerful driver of trajectory prediction in VLA-based autonomous driving.<n>We present OneVL, a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders.<n>OneVL becomes the first latent CoT method to surpass explicit CoT, delivering state-of-the-art accuracy at answer-only latency.
  arXiv  Detail & Related papers  (2026-04-20T16:37:22Z)
• How Transformers Learn to Plan via Multi-Token Prediction [33.974020982252206]
  Multi-token prediction (MTP) has emerged as a promising alternative to next-token prediction (NTP)<n>We show that MTP consistently outperforms NTP on both synthetic graph path-finding tasks and more realistic reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-04-13T18:04:09Z)
• OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning [51.33849811496781]
  Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous dynamics by Partial Differential Equations (PDEs)<n>We propose OMNIFLOW, a multimodal-symbolic architecture designed to ground frozen LLMs in fundamental physical laws without requiring domain-specific parameter updates.<n>We evaluate it on a benchmark spanning microscopic turbulence, theoretical Navier-Stokes, and macroscopic global weather forecasting.
  arXiv  Detail & Related papers  (2026-03-16T18:29:01Z)
• Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding [38.5840117402958]
  We argue that adequate contextual reasoning information can be directly extracted from the token probability distribution.<n>We present Latent Entropy-Aware Decoding, an efficient plug-and-play decoding strategy.<n>The model employs probability-weighted continuous embeddings under high-entropy states and transitions back to discrete token embeddings as entropy decreases.
  arXiv  Detail & Related papers  (2026-03-09T12:47:54Z)
• No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs [65.783709850324]
  This work stems from prior complementary observations on the dynamics of Chain-of-Thought (CoT): Large Language Models (LLMs)<n>LLMs are shown latent planning of subsequent reasoning prior to CoT emergence, thereby diminishing the significance of explicit CoT.<n>We investigate the latent planning strength of LLMs, through our probing method, Tele-Lens, applying to hidden states across diverse task domains.
  arXiv  Detail & Related papers  (2026-02-02T13:46:56Z)
• Idea-Gated Transformers: Enforcing Semantic Coherence via Differentiable Vocabulary Pruning [0.40611352512781856]
  We introduce the Idea-Gated Transformer, a novel architecture that separates semantic planning from syntactic generation.<n>We propose a differentiable gating mechanism that suppresses semantically irrelevant tokens, effectively pruning the search space in real-time.
  arXiv  Detail & Related papers  (2025-12-03T01:17:07Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• A Survey on Latent Reasoning [100.54120559169735]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities.<n>CoT reasoning that verbalizes intermediate steps limits the model's expressive bandwidth.<n>Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state.
  arXiv  Detail & Related papers  (2025-07-08T17:29:07Z)
• On multi-token prediction for efficient LLM inference [0.36681882674260474]
  We first show that such models inherently possess MTP capabilities via numerical marginalization over intermediate token probabilities.<n>We then explore the challenges of integrating MTP heads into frozen LLMs and find that their hidden layers are strongly specialized for NTP.
  arXiv  Detail & Related papers  (2025-02-13T15:42:44Z)

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.