Related papers: CurEvo: Curriculum-Guided Self-Evolution for Video…
It is common knowledge that the quantity and quality of the training data play a significant role in the creation of a good machine learning model. In this paper, we take it one step further and demonstrate that the way the training…
Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human…
In humans and animals, curriculum learning -- presenting data in a curated order - is critical to rapid learning and effective pedagogy. Yet in machine learning, curricula are not widely used and empirically often yield only moderate…
We propose a general framework for self-supervised learning of transferable visual representations based on Video-Induced Visual Invariances (VIVI). We consider the implicit hierarchy present in the videos and make use of (i) frame-level…
Recent advances in Source-Free Unsupervised Video Domain Adaptation (SFUVDA) leverage vision-language models to enhance pseudo-label generation. However, challenges such as noisy pseudo-labels and over-confident predictions limit their…
Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…
Pre-trained language models have achieved remarkable success across diverse applications but remain susceptible to spurious, concept-driven correlations that impair robustness and fairness. In this work, we introduce CURE, a novel and…
Code evolution is inevitable in modern software development. Changes to third-party APIs frequently break existing code and complicate maintenance, posing practical challenges for developers. While large language models (LLMs) have shown…
Curriculum Learning (CL), drawing inspiration from natural learning patterns observed in humans and animals, employs a systematic approach of gradually introducing increasingly complex training data during model development. Our work…
Online courses have significantly lowered the barrier to accessing education, yet the varying content quality of these videos poses challenges. In this work, we focus on the task of automatically evaluating the quality of video course…
This paper addresses the task of video question answering (videoQA) via a decomposed multi-stage, modular reasoning framework. Previous modular methods have shown promise with a single planning stage ungrounded in visual content. However,…
The natural association between visual observations and their corresponding sound provides powerful self-supervisory signals for learning video representations, which makes the ever-growing amount of online videos an attractive source of…
While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce \emph{EasyV2V}, a…
Video-to-text summarization remains underexplored in terms of comprehensive evaluation methods. Traditional n-gram overlap-based metrics and recent large language model (LLM)-based approaches depend heavily on human-written reference…
This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods encounter limitations…
Self-evolution of multimodal large language models (MLLMs) remains a critical challenge: pseudo-label-based methods suffer from progressive quality degradation as model predictions drift, while template-based methods are confined to a…
Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…
Curriculum Learning for Reinforcement Learning is an increasingly popular technique that involves training an agent on a sequence of intermediate tasks, called a Curriculum, to increase the agent's performance and learning speed. This paper…
The need for interpretable models has fostered the development of self-explainable classifiers. Prior approaches are either based on multi-stage optimization schemes, impacting the predictive performance of the model, or produce…
Modern video summarization methods are based on deep neural networks that require a large amount of annotated data for training. However, existing datasets for video summarization are small-scale, easily leading to over-fitting of the deep…