Pith. sign in

REVIEW 8 cited by

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.15451 v3 pith:24KBJ373 submitted 2025-03-19 cs.CV

MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

Lixing Xiao , Shunlin Lu , Huaijin Pi , Ke Fan , Liang Pan , Yueer Zhou , Ziyong Feng , Xiaowei Zhou
show 2 more authors
Sida Peng Jingbo Wang
This is my paper
classification cs.CV
keywords motiongenerationautoregressivecausalmodelmotionstreamerstreamingaccumulation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motions and incoming texts. Existing methods struggle to achieve streaming motion generation, e.g., diffusion models are constrained by pre-defined motion lengths, while GPT-based methods suffer from delayed response and error accumulation problem due to discretized non-causal tokenization. To solve these problems, we propose MotionStreamer, a novel framework that incorporates a continuous causal latent space into a probabilistic autoregressive model. The continuous latents mitigate information loss caused by discretization and effectively reduce error accumulation during long-term autoregressive generation. In addition, by establishing temporal causal dependencies between current and historical motion latents, our model fully utilizes the available information to achieve accurate online motion decoding. Experiments show that our method outperforms existing approaches while offering more applications, including multi-round generation, long-term generation, and dynamic motion composition. Project Page: https://zju3dv.github.io/MotionStreamer/

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

    cs.GR 2026-07 accept novelty 7.0

    An autoregressive diffusion model with a hybrid explicit-root/latent-body representation generates real-time, controllable 3D human motion from text and spatial constraints.

  2. LottieGPT: Tokenizing Vector Animation for Autoregressive Generation

    cs.CV 2026-04 unverdicted novelty 7.0

    LottieGPT tokenizes Lottie animations into compact sequences and fine-tunes Qwen-VL to autoregressively generate coherent vector animations from natural language or visual prompts, outperforming prior SVG models.

  3. ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control

    cs.RO 2026-06 unverdicted novelty 6.0

    ReactiveBFM introduces a real-time closed-loop planning-control system for humanoids using curriculum-based error recovery and asynchronous replanning, achieving 93.1% success under severe perturbations in sim-to-sim tests.

  4. Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control

    cs.CV 2026-05 unverdicted novelty 6.0

    MSCoT uses multi-scale hierarchical token prediction, multi-scale guidance, and a token refiner to deliver SOTA text-to-motion control with 48% FID gain, 61% lower error, and 10x faster inference on HumanML3D.

  5. Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs

    cs.CV 2026-04 unverdicted novelty 6.0

    IMU-to-4D uses wearable IMU data and repurposed LLMs to predict coherent 4D human motion plus coarse scene structure, outperforming cascaded state-of-the-art pipelines in temporal stability.

  6. LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens

    cs.CV 2026-02 unverdicted novelty 6.0

    LLaMo scales pretrained LLMs for unified motion-language tasks by encoding motion into continuous causal latents and adding a flow-matching head for real-time autoregressive generation and captioning.

  7. Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control

    cs.RO 2026-05 unverdicted novelty 5.0

    DAJI is a hierarchical framework using distillation and autoregressive generation to learn future-aware joint intents for language-conditioned humanoid robot control.

  8. Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control

    cs.RO 2026-05 unverdicted novelty 5.0

    DAJI learns future-aware joint intents from language to enable proactive humanoid control, reporting 94.42% rollout success on HumanML3D-style tasks and 0.152 subsequence FID on BABEL.