Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Explore this paper's citation graph
Summary
Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks.
- Type
- preprint
- Published
- 2024-03-08
- Cited by
- 3,933
- References
- 0
- Access
- Open access
- OpenAlex
- https://openalex.org/W4392679398
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:268297180
Keywords
Context (archaeology), Business, Computer science, Internet privacy, Geography
References
No references recorded for this paper.
Cited by
- Creativity and Machine Learning: A Survey
- Multimodal Chain-of-Thought Reasoning in Language Models
- When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions
- Can Large Language Models Write Good Property-Based Tests?
- A Survey on Decentralized Federated Learning
- Are Large Language Models Really Robust to Word-Level Perturbations?
- MatFormer: Nested Transformer for Elastic Inference
- Unlock Reliable Skill Inference for Quadruped Adaptive Behavior by Skill Graph
- IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers
- LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering
- Data-Centric Foundation Models in Computational Healthcare: A Survey
- In-context Learning with Retrieved Demonstrations for Language Models: A Survey
- Conditional and Modal Reasoning in Large Language Models
- KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
- Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks
- Learning a Decision Tree Algorithm with Transformers
- History, development, and principles of large language models: an introductory survey
- UFO: A UI-Focused Agent for Windows OS Interaction
- World Model on Million-Length Video And Language With Blockwise RingAttention
Related papers
- Using DataGrid Control to Realize DataBase of Querying in VB6.0
- Study and Two Types of Typical Usage of DataGrid Web Server Control
- PACWON: A parallelizing compiler for workstations on a network
- Bidirectional Sort and Choosing a Row to Update or Delete by Click Any Cell in DataGrid
- OpenCL-accelerated object classification in video streams using Spatial Pooler of Hierarchical Temporal Memory
- ESKVS: efficient and secure approach for keyframes-based video summarization framework
- Flexible Application of VSFlexGrid