提出关联递归记忆方法，让大模型上下文窗口突破长度限制，高效处理超长序列
arXiv:2607.11614v1 Announce Type: cross Abstract: Extending the context length of large language models (LLMs) is critical for many real-world applica…
面向长推理场景，提出信息感知的KV缓存压缩方法，显著提升大模型推理效率与速度。
arXiv:2606.26875v1 Announce Type: cross Abstract: Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing …
提出一种新型稀疏块注意力机制Proxy Block-CAGE，有望提升长序列建模效率并降低计算开销。
Hi, I'm a PhD student in Bioinformatics/Computational Biology with a software engineering background, I'm trying to pivot toward AI/ML research. I'm f…
长文本生成中的KV缓存压缩新方法，利用动量策略在解码时高效压缩，大幅降低内存占用。
arXiv:2605.29873v1 Announce Type: new Abstract: Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-gen…
提出Periodic RoPE方法，让大模型突破上下文长度瓶颈，实现无限长序列理解，是长文本处理的重要进步。
arXiv:2605.27980v1 Announce Type: cross Abstract: The ability to process ultra-long contexts is crucial for large language models (LLMs) to perform lo…
利用解码步骤的置信度信号，提出混合精度存储的KV缓存逐出策略，有效缓解长序列推理中的GPU内存瓶颈。
arXiv:2605.24786v1 Announce Type: cross Abstract: Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and…
提出UxSID模型，用语义感知对超长用户行为序列建模，显著提升推荐系统兴趣捕捉精度。
arXiv:2605.09040v3 Announce Type: replace-cross Abstract: Modeling ultra-long user sequences involves a difficult trade-off between efficiency and eff…
提出无需重训练的稀疏注意力机制STS，通过推测性token稀疏性突破大模型长序列推理的算力和内存瓶颈。
arXiv:2605.15508v1 Announce Type: new Abstract: The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Lan…