arXiv:2603.29773v1 Announce Type: new
Abstract: Real-world image restoration aims to restore high-quality (HQ) images from degraded low-quality (LQ) inputs captured under uncontrolled conditions. Existing methods typically depend on ground-truth (GT) …
arXiv:2512.17320v2 Announce Type: replace
Abstract: The widespread adoption of text-to-image (T2I) generation has raised concerns about privacy, bias, and copyright violations. Concept erasure techniques offer a promising solution by selectively remov…
arXiv:2603.29759v1 Announce Type: new
Abstract: Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment. However, existing benchmarks suffer from three fundamental limitations: (1) heavy …
arXiv:2512.15713v3 Announce Type: replace
Abstract: Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce latency. However, …
arXiv:2603.29742v1 Announce Type: new
Abstract: Diffusion-based watermarking methods embed verifiable marks by manipulating the initial noise or the reverse diffusion trajectory. However, these methods share a critical assumption: verification can suc…
arXiv:2512.11423v3 Announce Type: replace
Abstract: Existing DiT-based audio-driven avatar generation methods have achieved considerable progress, yet their broader application is constrained by limitations such as high computational overhead and the …
arXiv:2603.29734v1 Announce Type: new
Abstract: Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in hig…
arXiv:2512.08829v2 Announce Type: replace
Abstract: Vision-Language Models (VLMs) are increasingly tasked with ultra-long multimodal understanding. While linear architectures offer constant computation and memory footprints, they often struggle with h…
arXiv:2603.29733v1 Announce Type: new
Abstract: In this work, we explore the role of synthetic data in improving the detection of Hand-Object Interactions from egocentric images. Through extensive experimentation and comparative analysis on VISOR, Ego…
arXiv:2512.05513v3 Announce Type: replace
Abstract: Large Video-Language Models (Video-LMs) have achieved impressive progress in multimodal understanding, yet their reasoning remains weakly grounded in space and time. We present Know-Show, a new bench…