{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-10-30-sensetime-sensenova-loop-9b-preview/","md":"https://postcutoff.com/e/2026-10-30-sensetime-sensenova-loop-9b-preview/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-30-sensetime-sensenova-loop-9b-preview","date":"2026-10-30","date_precision":"day","short_title":"SenseTime open-sources SenseNova-Loop-9B-Preview, a looped multimodal model that runs a shared 24-layer block twice (Apache 2.0)","deck":null,"takeaway":"SenseTime released SenseNova-Loop-9B-Preview on Oct 30, 2026: an Apache-2.0, ~9B-parameter text-and-image model whose middle block of 24 decoder layers is run twice, adding depth of computation without extra weights.","category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"GitHub: OpenSenseNova/SenseNova-Loop","url":"https://github.com/OpenSenseNova/SenseNova-Loop","type":"code","group":"primary","domain":"github.com"},{"n":2,"title":"TechNode: SenseTime releases open-weight Loop-9B","url":"https://technode.com/2026/11/18/sensetime-releases-open-weight-loop-9b-model-that-reuses-layers-for-deeper-computation/","type":"press","group":"press","domain":"technode.com"},{"n":3,"title":"TechNode (Nov 2)","url":"https://technode.com/2026/11/02/sensetime-open-sources-9-billion-parameter-ai-model-that-reuses-layers-for-deeper-processing/","type":"press","group":"press","domain":"technode.com"},{"n":4,"title":"Pandaily (Nov 1)","url":"https://pandaily.com/sensetime-sensenova-loop-9b-preview-looped-transformer-mhc-open-source-apache-2","type":"press","group":"press","domain":"pandaily.com"}],"official":1,"filed":"2026-11-02","updated":"2026-11-19","orgs":["SenseTime"],"title":"SenseTime open-sources SenseNova-Loop-9B-Preview, a looped multimodal model that runs a shared 24-layer block twice (Apache 2.0)","summary":"SenseTime released SenseNova-Loop-9B-Preview on Oct 30, 2026: an Apache-2.0, ~9B-parameter text-and-image model whose middle block of 24 decoder layers is run twice, adding depth of computation without extra weights. Training supports sequences up to 262,144 tokens.","key_facts":["~9B parameters; shared 24-layer block executed twice","Input text and images, output text; aimed at document understanding, coding and tool use","Weights, inference instructions and training guidance released; licence Apache 2.0","Nov 18 (TechNode): SenseTime released Loop-9B as an open-weight model; it reuses layers in a loop for deeper computation"],"key_numbers":[],"tags":["open-weights","china","looped-transformer","multimodal","architecture"],"science":null,"body_md":"","disputed":[],"related":[],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-11-19","type":"edit","text":"Open-weight release"},{"date":"2026-11-02","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-11-02","run":null,"sources_read":null,"updated":"2026-11-19","human_review":null,"version":{"date":"2026-11-19"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":152,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":122,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":213,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":152,"in_training_data":false}],"short_url":null}