…This shift creates safety risks that are difficult to detect from isolated prompts or final responses, because harm often emerges only through multi-step execution traces whose individual actions appear locally benign…
…Existing methods typically address only part of this challenge, either localizing task-relevant regions without specifying executable motion, or predicting motion but with limited scalability. In this paper, we present ourmodel, a…
…Query-only compression , as in nested query resampling , replaces explicit grid-aligned tokens with non-local summaries and substantially degrades spatial grounding. To resolve this representational conflict, we introduce PARCEL (Pool-Anchored…
…View arXiv page View PDF Project page Add to collection Community ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations This is an automated message from the Librarian Bot . I…
…Based on this design, we build a diverse model zoo spanning structural control, brightness adjustment, color adjustment, image editing, super-resolution, sharpness enhancement, aesthetic alignment, content reference, local inpainting, and age control…
…However, current publicly available datasets predominantly focus on local editing or style transfer, which largely preserve the original scene structure and are easier to scale. In contrast, Background Replacement , a task central…
…https://ruixu.me/html/SuperGaussians/index.html View arXiv page View PDF Project page GitHub 67 Add to collection Community Today we're releasing SVGS , a new approach for Gaussian Splatting that…
…HakushoBench contains 2,053 images spanning over 10 image types, with manually annotated QA pairs, designed to assess deep and holistic understanding of charts and tables, rather than local visual cues alone…
…Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions, leaving us unable to localize failures to writing, maintenance, retrieval…
…View arXiv page View PDF Project page GitHub 5 Add to collection Community A controlled framework for evaluating whether VLMs know when not to answer spatial questions. This is an automated message…