{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T16:28:58.719Z","data":{"recordId":"wsa_x3dnp7uwwszk","score":1,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://github.com/Tencent/WeVisOne-VL","publisher":"GitHub new repositories","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-29T00:46:41.159Z","detectedPublishedAt":"2026-10-22T08:58:16.000Z","rights":"original"},{"n":2,"url":"https://huggingface.co/tencent/WeVisOne-VL-4B","publisher":"Tencent Hunyuan","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-29T00:46:41.159Z","detectedPublishedAt":"2026-10-22T09:48:14.000Z","rights":"original"}],"claims":[{"id":"ec194365-6935-472a-958c-d2880aed177f","kind":"capability","statement":"The pixel decoder outputs masks and alpha mattes without requiring SAM.","citations":[{"source":1,"supportProbability":0.86,"supports":true,"quote":{"text":"- 🪶 **Lightweight Pixel Decoder**: a 9.6M-parameter decoder outputs masks and alpha mattes, with no SAM required.","rights":"original"}}]},{"id":"1eaa404c-8e36-4d10-8e1b-19932337252a","kind":"availability","statement":"Model weights, an inference package, cookbooks, and an evaluation pipeline are released.","citations":[{"source":1,"supportProbability":0.88,"supports":true,"quote":{"text":"- **[2026-10]** 🎉 We release the technical report, model weights (2B & 4B), inference package, Cookbooks, and evaluation pipeline!","rights":"original"}}]},{"id":"73c70c66-d93e-4ab4-9689-784c6038b1d1","kind":"availability","statement":"A 4B demo is available on Hugging Face Spaces.","citations":[{"source":1,"supportProbability":0.88,"supports":true,"quote":{"text":"- [x] Model weights (2B & 4B) on Hugging Face","rights":"original"}}]},{"id":"f3d3c420-66c8-4f3d-a40d-b13e04fa1562","kind":"recommendation-relevant","statement":"The source reports WeVisOne-VL-4B achieves a 96.4% rejection rate on WeRef-Bench.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":null}]},{"id":"de745826-bd0b-463b-87af-b301a556273d","kind":"capability","statement":"The model supports open-vocabulary object detection, referring localization, object counting, object pointing, and OCR.","citations":[{"source":1,"supportProbability":0.79,"supports":true,"quote":null},{"source":2,"supportProbability":0.88,"supports":true,"quote":{"text":"Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception (referring segmentation and promptable alpha matting) through structured next-token…","rights":"original"}}]},{"id":"f75be082-a434-4309-ab56-23982bd6413a","kind":"capability","statement":"The model supports referring segmentation and promptable alpha matting.","citations":[{"source":1,"supportProbability":0.87,"supports":true,"quote":null},{"source":2,"supportProbability":0.91,"supports":true,"quote":{"text":"Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception (referring segmentation and promptable alpha matting) through structured next-token…","rights":"original"}}]},{"id":"650e3d02-a757-440e-a3ea-e41881979804","kind":"availability","statement":"The release includes the tencent/WeVisOne-VL-4B model and a required mask_decoder.pt component.","citations":[{"source":2,"supportProbability":0.7,"supports":true,"quote":null}]},{"id":"df4c16dd-da87-437f-950b-646015718ab7","kind":"recommendation-relevant","statement":"The model targets single-turn image perception, and video grids are rejected by the pixel decoder.","citations":[{"source":2,"supportProbability":0.94,"supports":true,"quote":{"text":"- For inference efficiency, the model directly generates structured outputs without explicit chain-of-thought (CoT) reasoning, and currently targets single-turn image perception (video grids are rejected by the pixel decoder).","rights":"original"}}]},{"id":"7991d5ea-61f4-4d61-bdee-9c2d33f30316","kind":"recommendation-relevant","statement":"The release is intended for research and is not intended for autonomous high-impact decisions or identifying individuals.","citations":[{"source":2,"supportProbability":0.93,"supports":true,"quote":{"text":"The release is intended for research in visual grounding, referring localization, pointing, counting, OCR localization, referring segmentation, and image matting.","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}