Related papers: MAMBO-G: Magnitude-Aware Mitigation for Boosted Gu…
Classifier-free guidance (CFG) has become a widely adopted and practical approach for enhancing generation quality and improving condition alignment. Recent studies have explored guidance mechanisms for unconditional generation, yet these…
Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs)…
In zero-shot text-to-speech, achieving a balance between fidelity to the target speaker and adherence to text content remains a challenge. While classifier-free guidance (CFG) strategies have shown promising results in image generation,…
Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a training-free…
A key challenge in synthesizing audios from silent videos is the inherent trade-off between synthesis quality and inference efficiency in existing methods. For instance, flow matching based models rely on modeling instantaneous velocity,…
Distributed optimization is essential for training large models on large datasets. Multiple approaches have been proposed to reduce the communication overhead in distributed training, such as synchronizing only after performing multiple…
Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…
While Model Predictive Control (MPC) delivers strong performance across robotics applications, solving the underlying (batches of) nonlinear trajectory optimization (TO) problems online remains computationally demanding. Existing…
Diffusion models have achieved impressive results in generative tasks for text-to-video (T2V) synthesis. However, achieving accurate text alignment in T2V generation remains challenging due to the complex temporal dependencies across…
The recent introduction of the large-scale, long-form MAD and Ego4D datasets has enabled researchers to investigate the performance of current state-of-the-art methods for video grounding in the long-form setup, with interesting findings:…
Recent breakthroughs in radiance fields have significantly advanced 3D scene reconstruction and novel view synthesis (NVS) in autonomous driving. Nevertheless, critical limitations persist: reconstruction-based methods exhibit substantial…
Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we…
Multimodal learning has gained much success in recent years. However, current multimodal fusion methods adopt the attention mechanism of Transformers to implicitly learn the underlying correlation of multimodal features. As a result, the…
Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking…
This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…
Instruction tuning improves the reasoning abilities of large language models (LLMs), with data quality and scalability being the crucial factors. Most instruction tuning data come from human crowd-sourcing or GPT-4 distillation. We propose…
Recent years have seen substantial progress in diffusion-based controllable video generation. However, achieving precise control in complex scenarios, including fine-grained object parts, sophisticated motion trajectories, and coherent…
Precise spatial fidelity in Image-to-3D multi-instance generation is critical for downstream real-world applications. Recent work attempts to address this by fine-tuning pre-trained Image-to-3D (I23D) models on multi-instance datasets,…
This paper proposes a mode multigrid (MMG) method, and applies it to accelerate the convergence of the steady state flow on unstructured grids. The dynamic mode decomposition (DMD) technique is used to analyze the convergence process of…
While thinking-aware generation aims to improve performance on complex tasks, we identify a critical failure mode where existing sequential, autoregressive approaches can paradoxically degrade performance due to error propagation. To…