{"work":{"id":"895dc295-4d82-4fd4-97d0-bb87df86a585","openalex_id":null,"doi":null,"arxiv_id":"2311.17043","raw_key":null,"title":"Llama-vid: An image is worth 2 tokens in large language models","authors":null,"authors_text":"Yanwei Li, Chengyao Wang, and Jiaya Jia","year":2023,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2311.17043","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-23T22:53:33.153243+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T23:20:32.972343+00:00","updated_at":"2026-05-23T22:53:33.153243+00:00","title_quality_ok":true,"display_title":"Llama-vid: An image is worth 2 tokens in large language models","render_title":"Llama-vid: An image is worth 2 tokens in large language models"},"hub":{"state":{"work_id":"895dc295-4d82-4fd4-97d0-bb87df86a585","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":16,"external_cited_by_count":null,"distinct_field_count":2,"first_pith_cited_at":"2024-02-24T16:39:16+00:00","last_pith_cited_at":"2026-05-19T15:05:00+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-03T16:16:15.517712+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"method","n":3},{"context_role":"background","n":2}],"polarity_counts":[{"context_polarity":"use_method","n":3},{"context_polarity":"background","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}