Skip to content

@tianyi-lab Tianyi Lab @ UMD

Change the repository type filter

All

    Repositories list

    18 repositories

    • HallusionBench

      Public
      [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
      benchmarkbenchmarkslmmhallucinationgpt-4large-language-modelsllmllavalarge-vision-language-modelsvlms
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •8•305•0•0•Updated Oct 14, 2025Oct 14, 2025

    • RuleR

      Public
      [NAACL'25] RuleR: Improving LLM Controllability by Rule-based Data Recycling
      Python
      •1•14•1•0•Updated Sep 27, 2025Sep 27, 2025

    • Mosaic-IT

      Public
      [ACL'25] Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning
      Python
      •3•20•0•0•Updated Sep 27, 2025Sep 27, 2025

    • ColorBench

      Public
      [NeurIPS'25] ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
      Python
      •
      Apache License 2.0
      •0•27•0•0•Updated Sep 27, 2025Sep 27, 2025

    • DisCL

      Public
      [ICCV 2025] Diffusion Curriculum (DisCL)
      Jupyter Notebook
      •0•13•2•0•Updated Sep 26, 2025Sep 26, 2025

    • FaSTAR

      Public
      Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
      Jupyter Notebook
      •
      BSD 3-Clause "New" or "Revised" License
      •2•28•0•0•Updated Jun 27, 2025Jun 27, 2025

    • Superfiltering

      Public
      [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
      Python
      •14•179•0•0•Updated Jun 25, 2025Jun 25, 2025

    • Cherry_LLM

      Public
      [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other models
      Python
      •26•398•1•0•Updated Jun 25, 2025Jun 25, 2025

    • MiP-Overthinking

      Public
      [COLM'25] Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
      Python
      •
      MIT License
      •1•35•1•0•Updated Jun 5, 2025Jun 5, 2025

    • C3PO

      Public
      [COLM 2025] "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"
      Jupyter Notebook
      •
      Apache License 2.0
      •1•18•1•0•Updated Apr 9, 2025Apr 9, 2025

    • CoSTAR

      Public
      Cost-Sensitive Toolpath Agent for Multi-turn Image Editing
      Jupyter Notebook
      •
      BSD 3-Clause "New" or "Revised" License
      •1•23•0•0•Updated Mar 26, 2025Mar 26, 2025

    • R2-T2

      Public
      [ICML 2025] Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"
      Python
      •
      MIT License
      •2•16•1•0•Updated Mar 10, 2025Mar 10, 2025

    • MosT

      Public
      Code for "Many-objective multi-solution transport"
      Python
      •0•2•0•0•Updated Feb 28, 2025Feb 28, 2025

    • BenTo

      Public
      [ICLR 2025] "BENTO: benchmark reduction with in-context learning transferability"
      Python
      •
      Apache License 2.0
      •0•4•0•0•Updated Oct 18, 2024Oct 18, 2024

    • MoE-Embedding

      Public
      [ICLR 2025 Oral] "Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free"
      Python
      •11•82•1•1•Updated Oct 15, 2024Oct 15, 2024

    • DEBATunE

      Public
      [ACL'24] Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
      Python
      •2•22•0•0•Updated Sep 14, 2024Sep 14, 2024

    • Reflection_Tuning

      Public
      [ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
      Python
      •30•363•0•0•Updated Sep 6, 2024Sep 6, 2024

    • mctune

      Public
      [ACL'24] Multi-Objective Linguistic Control of Large Language Models
      Python
      •0•2•0•0•Updated Jun 30, 2024Jun 30, 2024