Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SpikeMLLM: Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales and Temporal Compression

About

Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment in resource-constrained environments. Spiking Neural Networks (SNNs), with their sparse event-driven computation, offer inherent energy efficiency advantages on neuromorphic hardware, yet extending them to MLLMs faces two key challenges: heterogeneous modalities make uniform spike encoding insufficient, and high-resolution image inputs amplify timestep unfolding overhead. We propose SpikeMLLM, the first spike-based framework for MLLMs, which unifies existing ANN quantization methods in the spiking representation space and incorporates Modality-Specific Temporal Scales (MSTS) guided by Modality Evolution Discrepancy (MED) and Temporally Compressed LIF (TC-LIF) for timestep compression from T=L-1 to T=log2(L)-1. Experiments on four representative MLLMs across diverse multimodal benchmarks show that SpikeMLLM maintains near-lossless performance under aggressive timestep compression (Tv/Tt=3/4), with average gaps of only 0.72% and 1.19% relative to the FP16 baseline on InternVL2-8B and Qwen2VL-72B. We further develop a dedicated RTL accelerator tailored to the spike-driven datapath, observing 9.06x higher throughput and 25.8x better power efficiency relative to an FP16 GPU baseline under a deployment-oriented co-design setting, suggesting the promise of algorithm-hardware co-design for efficient multimodal intelligence.

Han Xu, Zhiyong Qin, Di Shang, Jiahong Zhang, Xuerui Qiu, Bo Lei, Tiejun Huang, Bo Xu, Guoqi Li• 2026

Related benchmarks

TaskDatasetResultRank
Visual Question AnsweringTextVQA
Accuracy83.46
1453
Science Question AnsweringScienceQA
Accuracy89.84
791
Optical Character RecognitionOCRBench
Score829
433
Multimodal Perception and CognitionMME
Overall Score2.24e+3
270
Document Visual Question AnsweringDocVQA
Accuracy95.54
203
Optical Character Recognition EvaluationOCRBench
Score817
91
Multimodal Model EvaluationMME
MME Score2.45e+3
77
Multimodal Scientific ReasoningScienceQA
Accuracy96.83
28
Multimodal Large Language Model InferenceQwen2VL-7B FP16 (inference)
Power Consumption (W)7.13
2
Showing 9 of 9 rows

Other info

Follow for update