MemFlow routes queries by intent to tiered memory operations, nearly doubling accuracy of a 1.7B SLM on long-horizon benchmarks compared to full-context baselines.
Fu, Stefano Ermon, Atri Rudra, and Christopher Ré
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
RPA kernel for TPUs achieves 86% MBU in decode and 73% MFU in prefill on Llama 3 8B via tiling for ragged memory, fused pipelines, and specialized compilation for prefill/decode workloads.
Joint few-step distillation and step-specific structural pruning turns a video diffusion model into a compact Mixture-of-Models that cuts 24% extra FLOPs per step and reaches 30× speedup on Wan-14B.
Key-axis-only content-aware erase plus a scalar write gate restores WY-form chunk training for delta-rule models and improves 1.3B language-model quality over GDN-2.
CONF-KV dynamically allocates KV cache budget via model confidence, matching full-KV perplexity within 1.5-2.1 points at sliding-window memory cost and improving retrieval accuracy.
citing papers explorer
-
MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
MemFlow routes queries by intent to tiered memory operations, nearly doubling accuracy of a 1.7B SLM on long-horizon benchmarks compared to full-context baselines.
-
Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU
RPA kernel for TPUs achieves 86% MBU in decode and 73% MFU in prefill on Llama 3 8B via tiling for ragged memory, fused pipelines, and specialized compilation for prefill/decode workloads.
-
Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation
Joint few-step distillation and step-specific structural pruning turns a video diffusion model into a compact Mixture-of-Models that cuts 24% extra FLOPs per step and reaches 30× speedup on Wan-14B.
-
CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention
Key-axis-only content-aware erase plus a scalar write gate restores WY-form chunk training for delta-rule models and improves 1.3B language-model quality over GDN-2.
-
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM
CONF-KV dynamically allocates KV cache budget via model confidence, matching full-KV perplexity within 1.5-2.1 points at sliding-window memory cost and improving retrieval accuracy.