Active Token Pruning for Efficient Multimodal Reasoning
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2159-2167
Abstract
No abstract availableThis publication has 4 references indexed in Scilit:
- Cascade Speculative Drafting for Even Faster LLM Inference2024
- EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding2023
- NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions2021
- ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question AnsweringProceedings of the AAAI Conference on Artificial Intelligence, 2019