10 papers
From Blind Search to Memory-Aware Evolution: Efficient DBMS Tuning via Collaborative Diagnosis and Utility-Aware Retrieval
Zhaoyan Hong, Yishen Sun, Xinyi Zhang +7
Modern DBMSs expose multiple configurable components (e.g., knobs, query hints, and indexes) that jointly determine query performance. Multi-component tuning is challenging due to…
TVA: A Version-aware Temporal Graph Storage System for Real-time Analytics
Wenhao Li, Zhanhao Zhao, Jinhao Dong +4
Analyzing temporal graphs can reveal valuable insights that are typically hidden in static graphs. Unfortunately, existing graph storage systems either lack native temporal support…
RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference
Wenhao Li, Jinhao Dong, Hailin Zhang +3
Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budge…
MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
Wenhan Ma, Jianyu Wei, Liang Zhao +10
Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabilities into one model remains…
Scaling Agentic Capabilities via Grounded Interaction Synthesis
Wenhang Shi, Jinhao Dong, Yiren Chen +4
General agentic intelligence hinges on the ability to interact with diverse real-world tools to complete complex tasks, a capability fundamentally tied to the quality of interactio…
Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
Wenhang Shi, Yiren Chen, Shuqing Bian +5
While prompt engineering is instrumental in maximizing the capabilities of Large Language Models (LLMs) during inference, the role of prompts during training remains critically und…