tracked author

Jie Tang (唐杰)

IndexCache, SAO, and CompactionRL coauthor and Tsinghua computer science professor in the Knowledge Engineering Group. His official homepage identifies his work in artificial intelligence, machine learning, data mining, knowledge graphs, and the GLM project ecosystem.

3 archived notes X: not-found Homepage

Related Notes

按论文归档时间排序，展示该作者在本站已经出现的材料。

归档 Jul 14, 2026

IndexCache: Accelerating Sparse Attention via Cross Layer Index Reuse

用 loss guided layer search 或 multi layer distillation 划分 Full / Shared 层，跨层复用 top k positions 并跳过最多 75% 的 DSA indexer 计算。

待审阅 2603.12201-indexcache-cross-layer-index-reuse Sparse Attention Long Context Serving Runtime

归档 Jul 13, 2026

CompactionRL: Reinforcement Learning with Context Compaction for Long Horizon Agents

CompactionRL 用独立 critic 和按后续 token 数折扣的跨段优势训练上下文压缩轨迹；两个模型在启用压缩的 coding 评测中提高 Pass@1，但 SUPO 已覆盖摘要—执行联合训练与全 token 归一化，且论文未报告直接对照或总计算。

待审阅 2607.05378-compactionrl-context-compaction-agent-rl Agent Memory Agent RL Credit Assignment

归档 Jul 11, 2026

Single Rollout Asynchronous Optimization for Agentic Reinforcement Learning

用每 prompt 单 rollout、强化 critic 与双侧 token mask 替代异步 GRPO 的组内等待和 group baseline。

待审阅 2607.07508-sao-single-rollout-asynchronous-agentic-rl RL Algorithm Agent RL Credit Assignment