Papers Concept Alignment

Concept Alignment

Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align val…

Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention

Scene Graph Generation (SGG) offers a structured representation critical in many computer vision applications. Traditional SGG approaches, however, are limited by a closed-set assumption, restricting their ability to rec…

Concept Alignment as a Prerequisite for Value Alignment

Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently u…

NEUCORE: Neural Concept Reasoning for Composed Image Retrieval

Composed image retrieval which combines a reference image and a text modifier to identify the desired target image is a challenging task, and requires the model to comprehend both vision and language modalities and their…

AltDiffusion: A Multilingual Text-to-Image Diffusion Model

Large Text-to-Image(T2I) diffusion models have shown a remarkable capability to produce photorealistic and diverse images based on text inputs. However, existing works only support limited language input, e.g., English, …

Language-based Action Concept Spaces Improve Video Self-Supervised Learning

Recent contrastive language image pre-training has led to learning highly transferable and robust image representations. However, adapting these models to video domains with minimal supervision remains an open problem. W…

ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models

The ability to understand visual concepts and replicate and compose these concepts from images is a central goal for computer vision. Recent advances in text-to-image (T2I) models have lead to high definition and realist…

3D Point Cloud Pre-training with Knowledge Distillation from 2D Images

The recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets. However, compared with 2D image datasets, the current pre-training data of 3D point cloud is limited. To ov…

CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge

Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e.g. multimodal retrieval and recommendation. However, existing models suffer from the…

Joint covariate-alignment and concept-alignment: a framework for domain generalization

In this paper, we propose a novel domain generalization (DG) framework based on a new upper bound to the risk on the unseen domain. Particularly, our framework proposes to jointly minimize both the covariate-shift as wel…

Align-smatch: A Novel Evaluation Method for Chinese Abstract Meaning Representation Parsing based on Alignment of Concept and Relation

Abstract Meaning Representation is a sentence-level meaning representation, which abstracts the meaning of sentences into a rooted acyclic directed graph. With the continuous expansion of Chinese AMR corpus, more and mor…

Grammar-Based Concept Alignment for Domain-Specific Machine Translation

Concept Extraction Using Pointer-Generator Networks

Concept extraction is crucial for a number of downstream applications. However, surprisingly enough, straightforward single token/nominal chunk-concept alignment or dictionary lookup techniques such as DBpedia Spotlight …

Discovery of Natural Language Concepts in Individual Units of CNNs

Although deep convolutional networks have achieved improved performance in many natural language tasks, they have been treated as black boxes because they are difficult to interpret. Especially, little is known about how…

Natural Language Detectors Emerge in Individual Neurons

Although deep convolutional networks have achieved improved performance in many natural language tasks, they have been treated as black boxes because they are difficult to interpret. Especially, little is known about how…

Getting the Most out of AMR Parsing

This paper proposes to tackle the AMR parsing bottleneck by improving two components of an AMR parser: concept identification and alignment. We first build a Bidirectional LSTM based concept identifier that is able to in…