BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion

arXiv:2609.35407 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-28

Project page: https://wengwanjiang.github.io/BiMoGen-Page

Terminology

• Alignment — 20× in this paper · explained in 1 episode
• Fine-Tuning — 16× in this paper · explained in 5 episodes
• Diffusion Model — 14× in this paper · explained in 8 episodes
• Transformer — 14× in this paper · explained in 2 episodes
• Ablation — 11× in this paper · explained in 1 episode
• Accuracy — 10× in this paper · explained in 1 episode
• Fidelity — 7× in this paper · explained in 2 episodes
• Generation-Aware Self-Correction — 6× in this paper
• Consistency — 5× in this paper · explained in 3 episodes
• Decoupled Uni- and Cross-Modal Training — 5× in this paper
• Diffusion Models — 5× in this paper · explained in 6 episodes
• Latent Space — 4× in this paper · explained in 7 episodes
• Unified Framework — 4× in this paper · explained in 5 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Quantization — 2× in this paper · explained in 12 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Block Diffusion — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes

Sources

• Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
• Continuous diffusion for categorical data
• Scaling Diffusion Language Models via Adaptation from Autoregressive Models
• Classifier-Free Diffusion Guidance
• LaViDa: A Large Diffusion Language Model for Multimodal Understanding
• ReMoMask: Retrieval-Augmented Masked Motion Generation
• VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension
• Decoupled Weight Decay Regularization
• Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
• Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression
• Absolute Coordinates Make Motion Generation Easy
• Large Language Diffusion Models
• UniMo: Unified Motion Generation and Understanding with Chain of Thought
• FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities
• MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding
• UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation
• FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing
• MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks
• DiMo: Discrete Diffusion Modeling for Motion Generation and Understanding
• BERTScore: Evaluating Text Generation with BERT

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models