Labels who speaks when in an audio recording, with improved speaker assignment and counting. It runs locally, supports offline use, and offers an exclusive diarization output that is easier to align with transcription timestamps.
Pan-cancer CT segmentation dataset for training and benchmarking medical-image segmentation models — packaged as a Hugging Face dataset with an estimated 10k–100k samples and linked arXiv references. Designed for model development and reproducible benchmarking; non-commercial license applies.
Performs open-vocabulary promptable segmentation and tracking on images and videos, returning instance masks and unique IDs from short noun-phrase or exemplar prompts. Trained on a 4M-concept, 52M-mask dataset; uses a presence head and a decoupled detector–tracker design, with near real-time inference for multi-object video.
Turns a single anime illustration into up to 23 semantically organized, inpainted layers with inferred drawing order, exported as a layered PSD. It provides a 2.5D animation starting point, but does not handle Live2D rigging or motion.
De-identified longitudinal multimodal CT dataset for multicancer screening that pairs ~24k CT volumes with radiology reports and voxel-wise tumor annotations across 13 cancer types. Designed for longitudinal disease modeling, detection/segmentation and vision–language research; CC BY‑NC‑ND 4.0 for non-commercial use.
Provides ~50M multimodal annotations organized for unified training across structured visual understanding, segmentation, dense geometric prediction, and multi-view reconstruction — released as task-specific JSONL files that reference original image assets rather than redistributing raw images.
Recovers editable design files from raster images by growing an editable layer hierarchy via an agentic pipeline that selects and composes modality-specific tools. Introduces graceful verification (accept/prune/retry) to prevent error accumulation and presents the Figma Edit Replay Benchmark (909 files, 14,796 edits) to measure editability across layout, color, and text edits.
Treats human annotations as oracle rollouts and separates them from on-policy baselines to improve reinforcement learning for video multimodal LLMs. Key features include a decoupled advantage estimator, sign-balanced pruning, and scalable gains across model sizes and data budgets.
Integrates a pretrained vision–language model with a BEV perception head and a Planning Expert to provide 3D perception, driving VQA and motion planning for autonomous driving while keeping the base VLM architecture unchanged.
Develops a vision-language foundation model for autonomous driving that unifies 3D BEV perception, visual question answering, and motion planning without changing the pretrained VLM architecture. Key elements include an external BEV perception head for 3D detection and occupancy, a Planning Expert using flow-matching for trajectory prediction, and a staged training recipe combining driving and general VLM data.
Provides official pretrained VisionHOPE visual-backbone checkpoints for ImageNet classification, COCO object detection & instance segmentation, and ADE20K semantic segmentation. Includes hierarchical Tiny/Small/Base models with PyTorch-compatible downloadable weights.
Jointly selects timesteps, network blocks, and channels from a frozen diffusion model under a channel budget for downstream discriminative tasks. It improves compact features across segmentation, classification, and semantic correspondence.