Related papers: SteeringDiffusion: A Bottlenecked Activation Contr…

Diffusion Denoising models demonstrated impressive results across generative Computer Vision tasks, but they still fail to outperform standard autoregressive solutions in the discrete domain, and only match them at best. In this work, we…

Text-driven motion diffusion models are capable of generating realistic human motions, but text alone often struggles to express fine-level nuances of motion, commonly referred to as style. Recent approaches have tackled this challenge by…

Diffusion models (DMs) have become the dominant paradigm of generative modeling in a variety of domains by learning stochastic processes from noise to data. Recently, diffusion denoising bridge models (DDBMs), a new formulation of…

Audio-driven emotional 3D facial animation encounters two significant challenges: (1) reliance on single-modal control signals (videos, text, or emotion labels) without leveraging their complementary strengths for comprehensive emotion…

Discrete diffusion language models (DDLMs) generate text by iteratively denoising categorical token sequences, while recent drifting methods for continuous generators suggest that part of this sampling-time correction can instead be…

Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate system identification as an in-context meta-learning problem…

The Stable Diffusion Model (SDM) is a prevalent and effective model for text-to-image (T2I) and image-to-image (I2I) generation. Despite various attempts at sampler optimization, model distillation, and network quantification, these…

A central challenge in mobile manipulation is preserving multiple plausible action models while remaining reactive during execution. A bottle in a cluttered scene can often be approached and grasped in multiple valid ways. Robust behavior…

This paper presents a novel approach for denoising Electron Backscatter Diffraction (EBSD) patterns using diffusion models. We propose a two-stage training process with a UNet-based architecture, incorporating an auxiliary regression head…

Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning approaches leverage diffusion model priors with geometry…

In recent years, diffusion based methods have emerged as a powerful paradigm for generative modeling. Although discrete diffusion for natural language processing has been explored to a lesser extent, it shows promise for tasks requiring…

Inference-time steering offers a promising way to control language models (LMs) without retraining. However, standard approaches typically rely on activation addition, which inevitably alters the hidden-state magnitudes raising concerns…

Vision Transformers and U-Net architectures have been widely adopted in the implementation of Diffusion Models. However, each architecture presents specific challenges while realizing them on-device. Vision Transformers require positional…

The conditional text-to-image diffusion models have garnered significant attention in recent years. However, the precision of these models is often compromised mainly for two reasons, ambiguous condition input and inadequate condition…

Proteins underpin most biological function, and the ability to design them with tailored structures and properties is central to advances in biotechnology. Diffusion-based generative models have emerged as powerful tools for protein design,…

Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iterations} and \textit{complex backbone networks} lead to…

Reward models (RMs) are critical components of alignment pipelines, yet they exhibit biases toward superficial stylistic cues, preferring better-presented responses over semantically superior ones. Existing debiasing methods typically…

Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing de-biasing techniques rely heavily on additional training, which imposes high computational costs and risks of compromising…

Diffusion models have made significant strides in recent years, exhibiting strong generalization capabilities in planning and control tasks. However, most diffusion-based policies remain focused on reward maximization or cost minimization,…

Human-centric generative models designed for AI-driven storytelling must bring together two core capabilities: identity consistency and precise control over human performance. While recent diffusion-based approaches have made significant…