awesome-multimodal-token-compression
github.com/cokeshao/awesome-multimodal-token-compression β[TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198
388
GitHub Stars
65
Curated Resources
3
Categories
27 min ago
Last Refreshed
π₯ NewsRecent Papers (Last 6 Months)Published in Recent Conference/Journal
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me published in recent conference/journal resources from awesome-multimodal-token-compression"
Installation instructions βWhat's inside
Published in Recent Conference/Journal
- Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
- AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
- AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
- ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling
- AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding
- AutoPrune: Each Complexity Deserves a Pruning Policy
Recent Papers (Last 6 Months)
- EchoingPixels: Cross-Modal Adaptive Token Reduction for Efficient Audio-Visual LLMs
- LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
- LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs
- OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
- Stage-adaptive Token Selection for Efficient Omni-modal LLMs
π₯ News
Showing a sample of 65 resources. View the full list on GitHub β