Related papers: Localize, Understand, Collaborate: Semantic-Aware …

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful…

Retrieval-augmented generation (RAG) is key to enhancing large language models (LLMs) to systematically access richer factual knowledge. Yet, using RAG brings intrinsic challenges, as LLMs must deal with potentially conflicting knowledge,…

Legibility of robot motion is critical in human-robot interaction, as it allows humans to quickly infer a robot's intended goal. Although traditional trajectory generation methods typically prioritize efficiency, they often fail to make the…

Text-guided 3D editing aims to modify existing 3D assets using natural-language instructions. Current methods struggle to jointly understand complex prompts, automatically localize edits in 3D, and preserve unedited content. We introduce…

Recent research on automotive driving developed an efficient end-to-end learning mode that directly maps visual input to control commands. However, it models distinct driving variations in a single network, which increases learning…

Intent-based recommender systems have garnered significant attention for uncovering latent fine-grained preferences. Intents, as underlying factors of interactions, are crucial for improving recommendation interpretability. Most methods…

Recent advancements in diffusion models have driven the growth of text-guided image editing tools, enabling precise and iterative modifications of synthesized content. However, as these tools become increasingly accessible, they also…

Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natural images and shallow commonsense reasoning, offering limited assessment of this capability…

Semantic editing of images is the fundamental goal of computer vision. Although deep learning methods, such as generative adversarial networks (GANs), are capable of producing high-quality images, they often do not have an inherent way of…

Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while…

We propose an interactive editing method that allows humans to help deep neural networks (DNNs) learn a latent space more consistent with human knowledge, thereby improving classification accuracy on indistinguishable ambiguous data.…

Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness frequently manifests as…

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…

In this paper, we focus on the task of instruction-based image editing. Previous works like InstructPix2Pix, InstructDiffusion, and SmartEdit have explored end-to-end editing. However, two limitations still remain: First, existing datasets…

With the rapid advancement of commercial multi-modal models, image editing has garnered significant attention due to its widespread applicability in daily life. Despite impressive progress, existing image editing systems, particularly…

Visual understanding is inherently intention-driven - humans selectively focus on different regions of a scene based on their goals. Recent advances in large multimodal models (LMMs) enable flexible expression of such intentions through…

Existing image editing methods can handle simple editing instructions very well. To deal with complex editing instructions, they often need to jointly fine-tune the large language models (LLMs) and diffusion models (DMs), which involves…

When faced with accomplishing a task, human experts exhibit intentional behavior. Their unique intents shape their plans and decisions, resulting in experts demonstrating diverse behaviors to accomplish the same task. Due to the…

Conditional image generation is an active research topic including text2image and image translation. Recently image manipulation with linguistic instruction brings new challenges of multimodal conditional generation. However, traditional…

Visual-prompt-guided edit transfer aims to learn image transformations directly from example pairs, offering more precise and controllable editing than purely text-driven approaches. However, existing diffusion transformer-based methods…