1 citations · 2 across the 7 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.AI2026
Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression
Wei Luo, Yi Huang, Songchen Ma +3
The KV cache used in large language models has linearly growing time complexity, so LLMs face memory blow-up and reduced decoding efficiency when they process long contexts. Curren…
cs.AR2026★ 1 cited
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding
Pingcheng Dong, Yonghao Tan, Xuejiao Liu +13
This work presents a 55nm speculative decoding-based LLM accelerator with bumping-based face-to-face ReRAM-on-logic stacking technology. It features a local rotation unit for outli…
cs.AR2026
Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling
Songchen Ma, Hongyi Li, Weihao Zhang +8
Mixture-of-Experts is a promising approach for edge AI with low-batch inference. Yet, on-device deployments often face limited on-chip memory and severe workload imbalance; the pre…