works on
adaptive pruning 1audio-video processing 1batch processing 1budget allocation 1inference acceleration 1inference efficiency 1large language models 1multimodal large language models 1speculative decoding 1token compression 1

From the 2 of 12 linked papers with an AI index.

most citedSpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism

1 citations · 1 across the 12 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs

Haoyang Huang, Wenjie Huang, Tianqi Xu +14

OmniDelta is a training-free framework that dynamically allocates token budgets for audio and video inputs in omni-modal large language models, using skill pools and local complexi…