LongLive-RAG formulates long video generation as retrieval-augmented generation by treating self-generated latents as a dynamic searchable history and adding a Window Temporal Delta Loss for better retrieval.
Dialogue without limits: Constant-sized kv caches for extended responses in llms
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
HybridGen achieves 1.41x-3.2x average speedups over six prior KV cache methods for LLM inference by using attention logit parallelism, a feedback-driven scheduler, and semantic-aware KV cache mapping.
WorldKV enables persistent world memory in autoregressive video diffusion models by selectively retrieving and compressing KV-cache chunks, matching full-cache fidelity at roughly twice the throughput without training.
A unified learnable KV eviction policy with cross-layer calibration reduces memory and matches or exceeds full-cache performance on long-context tasks by retaining useful tokens and limiting attention dilution.
citing papers explorer
-
LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation
LongLive-RAG formulates long video generation as retrieval-augmented generation by treating self-generated latents as a dynamic searchable history and adding a Window Temporal Delta Loss for better retrieval.
-
HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
HybridGen achieves 1.41x-3.2x average speedups over six prior KV cache methods for LLM inference by using attention logit parallelism, a feedback-driven scheduler, and semantic-aware KV cache mapping.
-
WorldKV: Efficient World Memory with World Retrieval and Compression
WorldKV enables persistent world memory in autoregressive video diffusion models by selectively retrieving and compressing KV-cache chunks, matching full-cache fidelity at roughly twice the throughput without training.
-
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
A unified learnable KV eviction policy with cross-layer calibration reduces memory and matches or exceeds full-cache performance on long-context tasks by retaining useful tokens and limiting attention dilution.