Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context · HackerPapers discussions

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context — mentioned by famouswaffles

Wed, 11 Mar 2026 22:18:09 GMT

>With only instructional materials (a 500-page reference grammar, a dictionary, and ≈400 extra parallel sentences) all provided in context, Gemini 1.5 Pro and Gemini 1.5 Flash are capable of learning to translate from English to Kalamang— a Papuan language with fewer than 200 speakers and therefore almost no online presence—with quality similar to a person who learned from the same materials https://arxiv.org/abs/2403.05530

Paper and discussion history. A mention is not an endorsement.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context — mentioned by mi_lk

Sat, 25 Jan 2025 21:23:17 GMT

Same thing happened to Google Gemini paper (1000+ authors) and it was described as big co promo culture (everyone wants credits). Interesting how narratives shift https://arxiv.org/abs/2403.05530

Paper and discussion history. A mention is not an endorsement.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context — mentioned by famouswaffles

Thu, 16 May 2024 06:56:32 GMT

It wasn't a demo. It was a report in the model card https://imgur.com/a/qXcVNOM https://arxiv.org/pdf/2403.05530

Paper and discussion history. A mention is not an endorsement.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context — HN submission

Tue, 14 May 2024 17:21:10 GMT

Gemini 1.5: Multimodal understanding across tokens of context

5 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context — mentioned by barfbagginus

Sat, 13 Apr 2024 06:19:04 GMT

You could do the needle recall test, detailed in the following article, and used in the Gemini technical report: https://vladbogo.substack.com/p/gemini-15-unlocking-multimod... https://arxiv.org/abs/2403.05530 In the needle test, we generate "needle" queries at each point in the context. We then graph the model's recall for each needle. In this case we might 1. Generate needles: Iterate through your conversations one by one, and generate multiple choice questions for each conversation. You might need to break down conversations into chunks. 2. Test the haystack. Given the full context, run…

Paper and discussion history. A mention is not an endorsement.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context — mentioned by simonw

Tue, 09 Apr 2024 16:28:53 GMT

Is that right? I didn't think Gemini was generating images directly, I assumed it was using a separate image generation tool. The paper here https://arxiv.org/pdf/2403.05530.pdf has a model card for Gemini 1.5 Pro that says: Output(s): Generated text in response to the input (e.g., an answer to the question, a summary of multiple documents, comparing documents/videos).

Paper and discussion history. A mention is not an endorsement.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context — HN submission

Fri, 15 Mar 2024 20:57:41 GMT

Gemini 1.5: Unlocking multimodal understanding across tokens of context

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context — HN submission

Wed, 13 Mar 2024 03:14:20 GMT

Google's Gemini 1.5 Pro whitepaper

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.