Related papers: Macro-from-Micro Planning for High-Quality and Par…
Modeling disease progression is crucial for improving the quality and efficacy of clinical diagnosis and prognosis, but it is often hindered by a lack of longitudinal medical image monitoring for individual patients. To address this…
Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is…
Generating minute-long videos is a critical step toward developing world models, providing a foundation for realistic extended scenes and advanced AI simulators. The emerging semi-autoregressive (block diffusion) paradigm integrates the…
Diffusion models excel at short-horizon robot planning, yet scaling them to long-horizon tasks remains challenging due to computational constraints and limited training data. Existing compositional approaches stitch together short segments…
Video generation, while capable of generating realistic videos, is computationally expensive and slow, prohibiting real-time applications. In this paper, we observe that video latents encoded via an autoencoder under the Latent Diffusion…
Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…
Motion prediction has been studied in different contexts with models trained on narrow distributions and applied to downstream tasks in human motion prediction and robotics. Simultaneously, recent efforts in scaling video prediction have…
Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion models with bidirectional generation, which limits temporal…
World model-based searching and planning are widely recognized as a promising path toward human-level physical intelligence. However, current driving world models primarily rely on video diffusion models, which specialize in visual…
Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion language models can generate multiple tokens in parallel, but sampling from them requires a denoising order: a strategy for deciding which…
Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore,…
We propose a novel AutoRegressive Generation-based paradigm for image Segmentation (ARGenSeg), achieving multimodal understanding and pixel-level perception within a unified framework. Prior works integrating image segmentation into…
We propose UniMo, an innovative autoregressive model for joint modeling of 2D human videos and 3D human motions within a unified framework, enabling simultaneous generation and understanding of these two modalities for the first time.…
Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video…
Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency.…
Next-Token Prediction (NTP) is a de facto approach for autoregressive (AR) video generation, but it suffers from suboptimal unidirectional dependencies and slow inference speed. In this work, we propose a semi-autoregressive (semi-AR)…
The massive adoption of large language models (LLMs) demands efficient deployment strategies. However, the auto-regressive decoding process, which is fundamental to how most LLMs generate text, poses challenges to achieve efficient serving.…
Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks…
Multimodal Large Language Models (MLLMs) have achieved strong performance across many tasks, yet most systems remain limited to offline inference, requiring complete inputs before generating outputs. Recent streaming methods reduce latency…
Extracting human motion from large-scale web videos offers a scalable solution to the data scarcity issue in character animation. However, some human parts in many video frames cannot be seen due to off-screen captures or occlusions. It…