HAWK: Rethinking Multimodal Drafting for Speculative Decoding
cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
- Accelerating Large Language Model Decoding with Speculative Sampling
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- The Unreasonable Ineffectiveness of the Deeper Layers
- SpecVLM: Fast Speculative Decoding in Vision-Language Models
- Draft-OPD: On-Policy Distillation for Speculative Draft Models
- SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
- Speculative Decoding Reimagined for Multimodal Large Language Models
- Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
- SmolVLM: Redefining small and efficient multimodal models
- ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models