Hao Liu
5 papers · Latest:
LLM-Oriented Information Retrieval: A Denoising-First Perspective
This paper argues that denoising is the primary bottleneck in LLM-oriented information retrieval, proposing a framework and techniques.
Learning Generalizable Multimodal Representations for Software Vulnerability Detection
MultiVul improves software vulnerability detection by combining code and comments using a multimodal contrastive learning framework.
Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks
Introduces StepSTEM, a new benchmark and evaluation framework for fine-grained, cross-modal STEM reasoning in MLLMs, revealing current models struggle.
NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results
NTIRE 2026 challenge overview: methods and results for video saliency prediction using a new 2,000-video dataset and crowdsourced fixations.
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
ECHO is a new diffusion-based VLM for chest X-ray report generation that achieves 8x faster inference with one-step block diffusion.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.