相关论文: Language Control Diffusion: Efficiently Scaling th…

We propose CLAD -- a Constrained Latent Action Diffusion model for vision-language procedure planning in instructional videos. Procedure planning is the challenging task of predicting intermediate actions given a visual observation of a…

Recent diffusion-based generators can produce high-quality images from textual prompts. However, they often disregard textual instructions that specify the spatial layout of the composition. We propose a simple approach that achieves robust…

Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model…

We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve…

Recently, Diffusion Large Language Models (DLLMs) have offered high throughput and effective sequential reasoning, making them a competitive alternative to autoregressive LLMs (ALLMs). However, parallel decoding, which enables simultaneous…

Diffusion Language Models (DLMs) have emerged as a promising new paradigm for text generative modeling, potentially addressing limitations of autoregressive (AR) models. However, current DLMs have been studied at a smaller scale compared to…

Addressing decision-making problems using sequence modeling to predict future trajectories shows promising results in recent years. In this paper, we take a step further to leverage the sequence predictive method in wider areas such as…

Designing realistic multi-object scenes requires not only generating images, but also planning spatial layouts that respect semantic relations and physical plausibility. On one hand, while recent advances in diffusion models have enabled…

Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively manage their working context. An agent can procedurally…

Classifier-Free Guidance (CFG) is a widely used mechanism for controlling diffusion-based generative models, yet its guidance scale is typically treated as a fixed hyperparameter throughout generation. This static design yields a suboptimal…

Diffusion models that are based on iterative denoising have been recently proposed and leveraged in various generation tasks like image generation. Whereas, as a way inherently built for continuous data, existing diffusion models still have…

Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by strong perplexity on…

In this work, we present an in-context policy adaptation (ICPAD) framework designed for long-horizon multi-task environments, exploring diffusion-based skill learning techniques in cross-domain settings. The framework enables rapid…

In this paper, we argue that iterative computation with diffusion models offers a powerful paradigm for not only generation but also visual perception tasks. We unify tasks such as depth estimation, optical flow, and amodal segmentation…

Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they continue to struggle with long-horizon planning and reasoning. To address this, we propose an…

Diffusion models emerged as a leading approach in text-to-image generation, producing high-quality images from textual descriptions. However, attempting to achieve detailed control to get a desired image solely through text remains a…

Modern LLM pre-training consumes vast amounts of compute and training data, making the scaling behavior, or scaling laws, of different models a key distinguishing factor. Discrete diffusion language models (DLMs) have been proposed as an…

Parallel applications with irregular and time-varying workloads often suffer from load imbalance. Dynamic load balancing techniques address this challenge by redistributing work during execution. We present a new type of distributed…

The Object Navigation (ObjectNav) task aims to guide an agent to locate target objects in unseen environments using partial observations. Prior approaches have employed location prediction paradigms to achieve long-term goal reasoning, yet…

Manufacturing environments are becoming more complex and unpredictable due to factors such as demand variations and shorter product lifespans. This complexity requires real-time decision-making and adaptation to disruptions. Traditional…