Log inSign up
user avatar
Wei Lin @ CVPR 2025
@WeiLinCV
Research associate @ ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz. Collab with MIT-IBM Watson AI Lab. PhD@TU Graz
Graz, Austria
wlin-at.github.io
Joined January 2022
211
Following
133
Followers
RepliesMedia
  • user avatar
    Wei Lin @ CVPR 2025
    @WeiLinCV
    Jan 27
    Excited to share our paper “PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies” has been accepted to ICLR 2026 🎉 🥳This work means a lot to me as it's my first time serving as the last author supervising a Master student Huge congrats to Lukas Selch!
    Image
  • user avatar
    Wei Lin @ CVPR 2025
    @WeiLinCV
    Sep 8, 2025
    🚀 🚀 We are introducing VisualOverload🎨🖼️, a VQA benchmark designed to test fundamental vision skills in visually dense scenes. 2,720 Q&A pairs across 6 tasks, 150 high-res artworks, and private ground truth. Even top VLMs hit only ~20% on the hardest tasks. Try it yourself🤖👉
    user avatar
    Paul Gavrikov
    @PaulGavrikov
    Sep 8, 2025
    Is basic image understanding solved in today’s SOTA VLMs? Not quite. We present VisualOverload, a VQA benchmark testing simple vision skills (like counting & OCR) in dense scenes. Even the best model (o3) only scores 19.8% on our hardest split.
    Image
  • user avatar
    Wei Lin @ CVPR 2025
    @WeiLinCV
    Jun 25, 2025
    🚨 New @ICCVConference 2025 paper! Can GPT-4o actually localize an object from just a few examples? Turns out not really. In our @ICCVConference paper, we propose a simple fix: teach it from video tracking data. Results? Better few-shot localization, stronger context grounding.
    user avatar
    Sivan Doveh
    @SivanDoveh
    Jun 25, 2025
    IPLOC accepted to ICCV25 ☺️ Thanks to all the people that were part of it 🩷 The idea for this paper came by a lake during a visit to Graz for a talk. It has traveled with me through too many countries and too many wars, and it’s now a complete piece of work.
  • user avatar
    Wei Lin @ CVPR 2025
    @WeiLinCV
    Jun 16, 2025
    Check our new work pLSTM that brings the power of linear RNNs to arbitrary DAGs and multi-dimensional data, enabling parallel computation and long-range modeling. It outperforms Transformers on extrapolation tasks and handles images, graphs, and grids with remarkable efficiency.
  • user avatar
    Wei Lin @ CVPR 2025
    @WeiLinCV
    Jun 14, 2025
    Check out our poster and talk with Guofeng at #355 in ExHall D. PerLA, is our new 3D language assistant that helps LLMs better understand the physical world! PerLA fuses local details and global context from point clouds using cross-attention + GNNs, and achieves SOTA on 3D bench
    Image