5 papers
DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning
Yunhai Hu, Junwei Zhou, Yumo Cao +8
Effective retrieval in complex domains requires bridging the gap between structured metadata and unstructured content. Existing systems typically isolate these capabilities, relyin…
PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding
Bradley McDanel, Sai Qian Zhang, Yunhai Hu +1
Speculative decoding accelerates large language model inference by using smaller draft models to generate candidate tokens for parallel verification. However, current approaches ar…
DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
Yunhai Hu, Tianhua Xia, Zining Liu +6
Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language mode…
MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search
Yunhai Hu, Yilun Zhao, Chen Zhao +1
We introduce MCTS-RAG, a novel approach that enhances the reasoning capabilities of small language models on knowledge-intensive tasks by leveraging retrieval-augmented generation…
Speculative Decoding and Beyond: An In-Depth Survey of Techniques
Yunhai Hu, Zining Liu, Zhenyuan Dong +3
Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization app…