Видео ютуба по тегу Token Compression

Data-Centric LLM Token Compression
Data-Centric LLM Token Compression
LLaVA-Scissor: Semantic Video Compression
LLaVA-Scissor: Semantic Video Compression
UniPruneBench: Visual Token Compression Benchmark
UniPruneBench: Visual Token Compression Benchmark
Token-Efficient Long Video Understanding for Multimodal LLMs | Paper explained
Token-Efficient Long Video Understanding for Multimodal LLMs | Paper explained
CompressX - Solana Token Compression Service (Demo)
CompressX - Solana Token Compression Service (Demo)
Сжатие токенов с помощью DeepSeek OCR и TOON
Сжатие токенов с помощью DeepSeek OCR и TOON
4.3.2. Prompt Compression Explained
4.3.2. Prompt Compression Explained
LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
DeepSeek-OCR: Contexts Optical Compression
DeepSeek-OCR: Contexts Optical Compression
Снижение стоимости токенов за счет мгновенного сжатия LLMLingua
Снижение стоимости токенов за счет мгновенного сжатия LLMLingua
Sequential Text Compression Strategy for LLMs | 65% Token Reduction with NLP + Data Cleaning
Sequential Text Compression Strategy for LLMs | 65% Token Reduction with NLP + Data Cleaning
[QA] LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
[QA] LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
2510.18234 - DeepSeek OCR: Contexts Optical Compression
2510.18234 - DeepSeek OCR: Contexts Optical Compression
Style compression: Make LLMs sound less generic (with fewer tokens)
Style compression: Make LLMs sound less generic (with fewer tokens)
DeepSeek-OCR Explained: How Visual Tokens Compress Text for Efficient LLMs
DeepSeek-OCR Explained: How Visual Tokens Compress Text for Efficient LLMs
Let's build the GPT Tokenizer
Let's build the GPT Tokenizer
Контекстное каскадное сжатие: исследование верхних пределов сжатия текста
Контекстное каскадное сжатие: исследование верхних пределов сжатия текста
Bridging the Gap: Encoding Long Text with Highly Compressed Yet Learnable Tokens
Bridging the Gap: Encoding Long Text with Highly Compressed Yet Learnable Tokens
[2025 Team 3] Hierarchical Token Compression for Video Summarization with MLLMs
[2025 Team 3] Hierarchical Token Compression for Video Summarization with MLLMs
Why LLMs get dumb (Context Windows Explained)
Why LLMs get dumb (Context Windows Explained)
Compressing LLM Context by 10X Using Vision #airesearch #llm #ocr
Compressing LLM Context by 10X Using Vision #airesearch #llm #ocr
DeepSeek OCR — больше, чем просто OCR
DeepSeek OCR — больше, чем просто OCR
[2023 Best AI Paper] Learning to Compress Prompts with Gist Tokens
[2023 Best AI Paper] Learning to Compress Prompts with Gist Tokens
Объяснение DeepSeek-OCR
Объяснение DeepSeek-OCR
#279 FastGen: Адаптивное сжатие кэша KV для LLM
#279 FastGen: Адаптивное сжатие кэша KV для LLM