Related papers: Fine-tuning Pocket-Aware Diffusion Models via Deno…
Recent research on robot manipulation based on Behavior Cloning (BC) has made significant progress. By combining diffusion models with BC, diffusion policiy has been proposed, enabling robots to quickly learn manipulation tasks with high…
Optimizing conflicting molecular properties while strictly adhering to complex 3D structural constraints constitutes a challenging Constrained Multi-Objective Optimization Problem (CMOP). Traditional Evolutionary Algorithms (EAs) destroy…
As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full…
Any order generation of discrete data using masked diffusion models (MDMs) offers a compelling alternative to traditional autoregressive models, especially in domains that lack a natural causal ordering of data. However, current popular…
Due to various physical degradation factors and limited counts received, PET image quality needs further improvements. The denoising diffusion probabilistic models (DDPM) are distribution learning-based models, which try to transform a…
State Space Models (SSMs) show significant potential for long-sequence modeling, but their reliance on input order conflicts with the irregular nature of point clouds. Existing approaches often rely on predefined serialization schemes whose…
Recent works in Reinforcement Learning (RL) combine model-free (Mf)-RL algorithms with model-based (Mb)-RL approaches to get the best from both: asymptotic performance of Mf-RL and high sample-efficiency of Mb-RL. Inspired by these works,…
Diffusion models have been widely used in the generative domain due to their convincing performance in modeling complex data distributions. Moreover, they have shown competitive results on discriminative tasks, such as image segmentation.…
Along with recent diffusion models, randomized smoothing has become one of a few tangible approaches that offers adversarial robustness to models at scale, e.g., those of large pre-trained models. Specifically, one can perform randomized…
Discrete diffusion models are often trained through clean-data prediction, but the prediction can be used in different ways to define the reverse dynamics. In Masked Diffusion Models (MDM) these choices largely coincide, whereas in Uniform…
Diffusion models have emerged as powerful tools for 3D medical image generation, yet bridging the gap between standard training objectives and clinical relevance remains a challenge. This paper presents a method to enhance 3D diffusion…
Parameter-efficient fine-tuning methods, such as LoRA, reduces the number of trainable parameters. However, they often suffer from scalability issues and differences between their learning pattern and full fine-tuning. To overcome these…
Structure-based drug design (SBDD), which aims to generate molecules that can bind tightly to the target protein, is an essential problem in drug discovery, and previous approaches have achieved initial success. However, most existing…
Scaling neural network training increasingly depends on synchronous data-parallelism, yet full-precision gradient all-reduce imposes a severe communication bottleneck. We propose Decoupled Momentum Optimization (DeMo), a drop-in replacement…
Diffusion models achieve superior generation quality but suffer from slow generation speed due to the iterative nature of denoising. In contrast, consistency models, a new generative family, achieve competitive performance with…
Multispectral fusion object detection is a critical task for edge-based maritime surveillance and remote sensing, demanding both high inference efficiency and robust feature representation for high-resolution inputs. However, current State…
Model-free and reinforcement learning-based adaptive filtering methods are gaining traction for denoising in dynamic, non-stationary environments such as wireless signal channels. Traditional filters like LMS, RLS, Wiener, and Kalman are…
Memory-efficient personalization is critical for adapting text-to-image diffusion models while preserving user privacy and operating within the limited computational resources of edge devices. To this end, we propose a selective…
Aligning diffusion models to downstream tasks often requires finetuning new models or gradient-based guidance at inference time to enable sampling from the reward-tilted posterior. In this work, we explore a simple inference-time…
Designing compounds with desired properties is a key element of the drug discovery process. However, measuring progress in the field has been challenging due to the lack of realistic retrospective benchmarks, and the large cost of…