相关论文: Exposing and Addressing Cross-Task Inconsistency i…
The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded…
Despite the remarkable success of foundation models, their task-specific fine-tuning paradigm makes them inconsistent with the goal of general perception modeling. The key to eliminating this inconsistency is to use generalist models for…
Object detection is a task that performs position identification and label classification of objects in images or videos. The information obtained through this process plays an essential role in various tasks in the field of computer…
Consistency Identification has obtained remarkable success on open-domain dialogue, which can be used for preventing inconsistent response generation. However, in contrast to the rapid development in open-domain dialogue, few efforts have…
Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…
The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…
Language models have recently achieved strong performance across a wide range of NLP benchmarks. However, unlike benchmarks, real world tasks are often poorly specified, and agents must deduce the user's intended behavior from a combination…
Multi-task problem solving has been shown to improve the accuracy of the individual tasks, which is an important feature for robots, as they have a limited resource. However, when the number of labels for each task is not equal, namely…
Foundational models are trained on extensive datasets to capture the general trends of a domain. However, in medical imaging, the scarcity of data makes pre-training for every domain, modality, or task challenging. Continual learning offers…
Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of…
Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain the factuality of the model knowledge across languages, and preserve the parity of language model performance. We are thus interested in…
With growing applications of Machine Learning (ML) techniques in the real world, it is highly important to ensure that these models work in an equitable manner. One main step in ensuring fairness is to effectively measure fairness, and to…
Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image show emerging abilities to reason over multiple related…
Text-driven image editing has achieved remarkable success in following single instructions. However, real-world scenarios often involve complex, multi-step instructions, particularly ``chain'' instructions where operations are…
Many real-world problems exhibit the coexistence of multiple types of heterogeneity, such as view heterogeneity (i.e., multi-view property) and task heterogeneity (i.e., multi-task property). For example, in an image classification problem…
One of the well-known challenges in computer vision tasks is the visual diversity of images, which could result in an agreement or disagreement between the learned knowledge and the visual content exhibited by the current observation. In…
How to robustly rank the aesthetic quality of given images has been a long-standing ill-posed topic. Such challenge stems mainly from the diverse subjective opinions of different observers about the varied types of content. There is a…
Recently, dense contrastive learning has shown superior performance on dense prediction tasks compared to instance-level contrastive learning. Despite its supremacy, the properties of dense contrastive representations have not yet been…
The comic domain is rapidly advancing with the development of single-page analysis and synthesis models. However, evaluation metrics and datasets lag behind, often limited to small-scale or single-style test sets. We introduce a novel…
This paper investigates the cross-lingual inconsistencies observed in Large Language Models (LLMs), such as ChatGPT, Llama, and Baichuan, which have shown exceptional performance in various Natural Language Processing (NLP) tasks. Despite…