Related papers: TRACE: Structure-Aware Character Encoding for Robu…
In the evolving landscape of text-to-image (T2I) diffusion models, the remarkable capability to generate high-quality images from textual descriptions faces challenges with the potential misuse of reproducing sensitive content. To address…
Semantically consistent cross-domain image translation facilitates the generation of training data by transferring labels across different domains, making it particularly useful for plant trait identification in agriculture. However,…
Graph diffusion models have emerged as state-of-the-art techniques in graph generation; yet, integrating domain knowledge into these models remains challenging. Domain knowledge is particularly important in real-world scenarios, where…
Introductory Computer Science classes are important for laying the foundation for advanced programming courses. However, students without prior programming experience may find these courses challenging, leading to difficulties in…
Scene text recognition (STR) suffers from challenges of either less realistic synthetic training data or the difficulty of collecting sufficient high-quality real-world data, limiting the effectiveness of trained models. Meanwhile, despite…
We introduce a new approach to systematically map features discovered by sparse autoencoder across consecutive layers of large language models, extending earlier work that examined inter-layer feature links. By using a data-free cosine…
In recent years, visual representation learning has gained widespread attention in robotic imitation learning. However, in complex Out-of-Distribution(OOD) settings characterized by clutter and occlusion, the attention of global visual…
Data contamination is a known threat to the reliability of model evaluation. However, it remains underexplored in code large language models (LLMs), where contamination often goes beyond exact duplication. We present TRACER, a…
We present TALE, a novel training-free framework harnessing the generative capabilities of text-to-image diffusion models to address the cross-domain image composition task that focuses on flawlessly incorporating user-specified objects…
The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited…
This paper presents a scene text detection technique that exploits bootstrapping and text border semantics for accurate localization of texts in scenes. A novel bootstrapping technique is designed which samples multiple 'subsections' of a…
In robotics, diffusion models can capture multi-modal trajectories from demonstrations, making them a transformative approach in imitation learning. However, achieving optimal performance following this regiment requires a large-scale…
Watermarking methods have always been effective means of protecting intellectual property, yet they face significant challenges. Although existing deep learning-based watermarking systems can hide watermarks in images with minimal impact on…
The detection and tracking of human landmarks in video streams has gained in reliability partly due to the availability of affordable RGB-D sensors. The analysis of such time-varying geometric data is playing an important role in the…
Knowledge graphs (KGs) are ubiquitous in numerous real-world applications, and watermarking facilitates protecting intellectual property and preventing potential harm from AI-generated content. Existing watermarking methods mainly focus on…
Reusing pre-collected data from different domains is an appealing solution for decision-making tasks, especially when data in the target domain are limited. Existing cross-domain policy transfer methods mostly aim at learning domain…
This paper introduces STRASS: Summarization by TRAnsformation Selection and Scoring. It is an extractive text summarization method which leverages the semantic information in existing sentence embedding spaces. Our method creates an…
Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts. However, current personalization approaches struggle…
Driven by deep neural networks and large scale datasets, scene text detection methods have progressed substantially over the past years, continuously refreshing the performance records on various standard benchmarks. However, limited by the…
Sparse encoders offer high-precision retrieval by representing term importance within a vocabulary space, yet their English-centric structures pose a critical impediment to language transfer for non-English languages. To overcome this…