arXiv:2603.02210v3 Announce Type: replace
Abstract: Human-product images, which showcase the integration of humans and products, play a vital role in advertising, e-commerce, and digital marketing. The essential challenge of generating such images lie…
arXiv:2604.11804v2 Announce Type: replace
Abstract: In this work, we study Human-Object Interaction Video Generation (HOIVG), which aims to synthesize high-quality human-object interaction videos conditioned on text, reference images, audio, and pose….
arXiv:2604.16004v1 Announce Type: cross
Abstract: Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning …
arXiv:2604.15237v2 Announce Type: replace
Abstract: Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing $O(1)$ frameworks primarily rely on a “pure eviction” paradigm, whi…
arXiv:2604.10096v2 Announce Type: replace
Abstract: Current embodied intelligent systems still face a substantial gap between high-level reasoning and low-level physical execution in open-world environments. Although Vision-Language-Action (VLA) model…
arXiv:2408.15549v4 Announce Type: replace
Abstract: As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated…
arXiv:2604.15857v1 Announce Type: new
Abstract: Recent digital media advancements have created increasing demands for sophisticated portrait manipulation techniques, particularly head swapping, where one’s head is seamlessly integrated with another’s …
arXiv:2604.15862v1 Announce Type: new
Abstract: 3D Gaussian Splatting (3DGS) has recently redefined the paradigm of 3D reconstruction, striking an unprecedented balance between visual fidelity and computational efficiency. As its adoption proliferates…
arXiv:2505.21072v4 Announce Type: replace
Abstract: Large Language Models (LLMs) enhanced with retrieval, an approach known as Retrieval-Augmented Generation (RAG), have achieved strong performance in open-domain question answering. However, RAG remai…
arXiv:2604.14605v2 Announce Type: replace
Abstract: Graphic design creation involves harmoniously assembling multimodal components such as images, text, logos, and other visual assets collected from diverse sources, into a visually-appealing and cohes…