Related papers: V.I.P. : Iterative Online Preference Distillation …

Recently, Visual Programming (VProg) has emerged as a significant framework for visual reasoning (VR) tasks due to its interpretability and cross-task generality. However, even with invoking powerful pre-trained Vision-Language models…

Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is…

Controllable music generation methods are critical for human-centered AI-based music creation, but are currently limited by speed, quality, and control design trade-offs. Diffusion Inference-Time T-optimization (DITTO), in particular,…

Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model…

Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffers from limited generalization, while the latter, despite its…

Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…

Training large AI models typically requires large-scale datasets in the machine learning process, making training and parameter-tuning process both time-consuming and costly. Some researchers address this problem by carefully synthesizing a…

Large-scale visual learning is increasingly limited by training cost. Existing knowledge distillation methods transfer from a stronger teacher to a weaker student for compression or final-accuracy improvement. We instead investigate…

Recent approaches have shown promises distilling diffusion models into efficient one-step generators. Among them, Distribution Matching Distillation (DMD) produces one-step generators that match their teacher in distribution, without…

Diffusion models have shown great promise for image and video generation, but sampling from state-of-the-art models requires expensive numerical integration of a generative ODE. One approach for tackling this problem is rectified flows,…

To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion. However, these solutions face a large drop in performance for single image queries (e.g., Image-To-Video setting).…

Current approaches for restoration of degraded images face a trade-off: high-performance models are slow for practical use, while fast models produce poor results. Knowledge distillation transfers teacher knowledge to students, but existing…

Recently, open-source video diffusion models (VDMs), such as WanX, Magic141 and HunyuanVideo, have been scaled to over 10 billion parameters. These large-scale VDMs have demonstrated significant improvements over smaller-scale VDMs across…

Direct Preference Optimization (DPO), which aligns models with human preferences through win/lose data pairs, has achieved remarkable success in language and image generation. However, applying DPO to video diffusion models faces critical…

Direct Preference Optimization (DPO) aligns text-to-image (T2I) generation models with human preferences using pairwise preference data. Although substantial resources are expended in collecting and labeling datasets, a critical aspect is…

Diffusion Transformers (DiTs) with billions of model parameters form the backbone of popular image and video generation models like DALL.E, Stable-Diffusion and SORA. Though these models are necessary in many low-latency applications like…

Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length. In this work, we propose a…

Developing lightweight, on-device vision-language GUI agents is essential for efficient cross-platform automated interaction. However, current on-device agents are constrained by limited model capacity, and further performance improvements…

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely…

Existing methods for preference tuning of text-to-image (T2I) diffusion models often rely on computationally expensive generation steps to create positive and negative pairs of images. These approaches frequently yield training pairs that…