collaborators

8 papers

cs.LG2026

DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation

Zining Liu, Yunhai Hu, Tianhua Xia +4

Speculative decoding (SD) has proven to be an effective technique for accelerating autoregressive generation in large language models (LLMs) however, its application to vision-lang…

cs.AI2026

DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution

Yunhai Hu, Zining Liu, Xiangyang Yin +5

Speculative reasoning has recently been proposed as a means to accelerate reasoning-intensive generation in large multimodal models, but its effectiveness is often constrained by m…

cs.IR2026

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…

cs.CL2025

AutoNeural: Co-Designing Vision-Language Models for NPU Inference

Wei Chen, Liangmin Wu, Yunhai Hu +9

While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrat…

cs.CL2025

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…

cs.CL2025

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…