10 papers
Vela: User Behavior as Supervision Sparks LLM Intelligence
Yang Xiao, Yusong Sun, Haoyi Wu +17
Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommendation and advertising systems.…
PACT: From Credit Assignment to Critic Alignment
Jiayan Fu, Hang Xu, Yong Zhang +4
Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted mathematical definition, leavin…
RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
Yang Liu, Zhaokai Luo, Huayi Jin +10
Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it removes the physical per-hea…
AtomRec: Evolving Atomic Memory for Agentic Recommendation
Peiyu Hu, Weihai Lu, Siying Gu +5
Agentic recommender systems use large language models to maintain semantic memory and support evidence-aware recommendation. However, existing memory mechanisms often compress user…
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
Yang Xiao, Yusong Sun, Haoyi Wu +7
Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends,…
OneModel: A Unified Foundation for Platform-Scale Multi-Scenario Ranking
Yinqi Zhang, Peiyu Hu, Yuntian Tang +16
Platform-scale recommender systems often span multiple business streams such as organic recommendation, advertising, and merchant services, where user behaviors form a continuous c…
Hierarchical Latent Reasoning for LLM-based Recommendation
Peiyu Hu, Siying Gu, Weihai Lu +8
Large Language Models (LLMs) have shown strong potential for recommendation by leveraging their semantic understanding and contextual modeling capabilities. Recent studies further…
RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
Yang Liu, Zhaokai Luo, Huayi Jin +7
As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure. It limits GPU memory capacity, serv…
FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models
Bing Tian, Haikun Liu, Xiaocheng Zhong +5
Block-wise diffusion large language models (dLLMs) decode sequentially at the block level, enabling effective KV-cache reuse across blocks but making inter-block decoding strictly…
Akashic: A Low-Overhead LLM Inference Service with MemAttention
Yang Liu, Zhaokai Luo, Huayi Jin +7
Recent LLM-based agent systems continuously accumulate context across multi-turn interactions, tool invocations, and cross-session workflows. Replaying the full history for every r…