Streamline product requirement management with AI-assisted workflows, automated conflict checks, and changelog extraction for clear traceability.

R packages

Tools and Statistical Procedures in Plant Science

评测视觉大模型图片提取信息和推理能力

Linear mixed model genome scans for many traits

🚧 Under Construction: Parent structure for mesoscale Ca²⁺ imaging analysis pipelines for allen atlas LMM coefficient bar plots, behavior state metrics, peaks, pearson modularity and connectivity and supplemental

GeoLocator: A Location-Integrated Large Multimodal Model (LMM) for Inferring Geo-Privacy

An educational AI-powered financial literacy platform that teaches beginners how markets react to real-world events using historical examples and a Socratic approach.

[ICLR'26] Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology

Utilities for field trial analysis.

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]

Linear mixed model data analysis

Above human intelligence.

LLM4DD: Large language models for decreasing driveability in autonomous driving system simulator scenarios.

An LLM chat bot-like website that seeks to assist with various resources that display updated and trustworthy information on various topics, a platform to direct users toward relevant resources

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning

A Novel Method to Visualize Multimodal AI Sentiment Arcs in Long-Form Narratives

PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models