most citedSearch-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs

1 citations · 1 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CL2026

Search-on-Graph-R1: Training Large Language Models to Search Knowledge Graphs with Reinforcement Learning

Jia Ao Sun, Hao Yu, Fengran Mo +4

Knowledge graph question answering (KGQA) requires navigating from topic entities to an answer several relations away. Recent methods prompt a frontier LLM to explore the graph thr…

cs.LG2026

QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides

Zhengyang Zhuge, Hao Yu, Xin Wang +4

Rollout generation is a major bottleneck in Reinforcement Learning (RL) for Mixture-of-Experts (MoE) Large Language Models, motivating low-precision rollout acceleration such as FP…

cs.CL2026

AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages

Hao Yu, Tianyi Xu, Michael A. Hedderich +3

Large language models (LLMs) are increasingly multilingual, yet open models continue to underperform relative to proprietary systems, with the gap most pronounced for African langu…

cs.CL20261 cited

Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs

Jia Ao Sun, Hao Yu, Fabrizio Gotti +6

Large language models (LLMs) augmented with knowledge graphs (KGs) offer a promising approach for knowledge-intensive reasoning. Central to this approach is the selection of approp…

cs.CL2026

Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection

Junhao Liu, Haonan Yu, Zhenyu Yan +1

As Large Language Models (LLMs) scale to handle massive context windows, achieving surgical feature-level interpretation is essential for high-stakes tasks like legal auditing and…

cs.CV2025

VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference

Shengling Qin, Hao Yu, Chenxin Wu +10

This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when t…