2 citations · 3 across the 18 of their papers we have counts for
19 papers
VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair
Shicheng Liu, Adam Kahirov, Qi Zhang +5
Multimodal agents are increasingly used for data visualization tasks but remain limited in autonomous review. Unlike humans, they may fail to recognize when a visualization is inco…
CoDS: Robust Collaborative Perception via Expert-driven Detection and BEV Segmentation
Jinlong Wang, Yuang Jia, Junhong Lin +2
Collaborative perception breaks through single-view limitations via multi-agent information exchange. However, multi-source noise such as pose errors and communication delays degra…
Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction
Junhong Lin, Jinlong Wang, Xianda Guo +6
Single-frame surround-view reconstruction faces severe geometric instability and rendering artifacts due to minimal inter-camera overlap. While existing methods rely on complex dec…
VGOcc: Learning Visual-Geometric Gaussians for Vision-Centric 3D Driving Occupancy Prediction
Junhong Lin, Xianda Guo, Kangli Wang +4
Vision-only occupancy prediction requires recovering a semantic 3D occupancy field from calibrated surround-view images, where each view provides observations with ambiguous depth…
CoSAG: Compact Semantic Anchor Gaussians via Training-Free Rate-Distortion Coding
Yuang Jia, Jinlong Wang, Junhong Lin +2
Open-vocabulary 3D scene understanding is commonly achieved by embedding 2D vision-language features such as CLIP into a 3D Gaussian Splatting scene, turning it into a text-queryab…
HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
Xinyue Zeng, Junhong Lin, Yujun Yan +4
The reliability of Large Language Models (LLMs) in high-stakes domains such as healthcare, law, and scientific discovery is often compromised by hallucinations. These failures typi…
How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
Junhong Lin, Bing Zhang, Song Wang +4
Large language models (LLMs) continue to struggle with knowledge-intensive questions that require up-to-date information and multi-hop reasoning. Augmenting LLMs with hybrid extern…
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…
Layered Division and Global Allocation for Community Detection in Multilayer Network
Fanghao Hu, Zhi Cai, Bang Wang
Community detection in multilayer networks (CDMN) is to divide a set of entities with multiple relation types into a few disjoint subsets, which has many applications in the Web, t…
VGD: Visual Geometry Gaussian Splatting for Feed-Forward Surround-view Driving Reconstruction
Junhong Lin, Kangli Wang, Shunzhou Wang +3
Feed-forward surround-view autonomous driving scene reconstruction offers fast, generalizable inference ability, which faces the core challenge of ensuring generalization while ele…
HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations
Shuaicheng Zhang, Haohui Wang, Junhong Lin +5
Graph heterophily, where connected nodes have different labels, has attracted significant interest recently. Most existing works adopt a simplified approach - using low-pass filter…
Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs
Junhong Lin, Song Wang, Xiaojie Guo +2
Large language models (LLMs) excel at many language understanding tasks but struggle to reason over knowledge that evolves. To address this, recent work has explored augmenting LLM…
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
Junhong Lin, Shicheng Liu, Jinyeop Song +3
Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide…
LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection
Xinyue Zeng, Haohui Wang, Junhong Lin +3
The proliferation of open-sourced Large Language Models (LLMs) and diverse downstream tasks necessitates efficient model selection, given the impracticality of fine-tuning all cand…
Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models
Junhong Lin, Xinyue Zeng, Jie Zhu +4
Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode…
Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
Song Wang, Junhong Lin, Xiaojie Guo +3
While large language models (LLMs) have made significant progress in processing and reasoning over knowledge graphs, current methods suffer from a high non-retrieval rate. This lim…
ConstellationNet: Reinventing Spatial Clustering through GNNs
Aidan Gao, Junhong Lin
Spatial clustering is a crucial field, finding universal use across criminology, pathology, and urban planning. However, most spatial clustering algorithms cannot pull information…
When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark
Junhong Lin, Xiaojie Guo, Shuaicheng Zhang +2
Graph mining has become crucial in fields such as social science, finance, and cybersecurity. Many large-scale real-world networks exhibit both heterogeneity, where multiple node a…
PAC-Bayesian Adversarially Robust Generalization Bounds for Graph Neural Network
Tan Sun, Junhong Lin
Graph neural networks (GNNs) have gained popularity for various graph-related tasks. However, similar to deep neural networks, GNNs are also vulnerable to adversarial attacks. Empi…