Lijuan Wang

Lijuan Wang on Hugging Face Daily Papers: 17 papers, 5 in the top 3 of their day, 295 upvotes.

  1. ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs 20 upvotes, #5 of 2025-06-16
  2. SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement 14 upvotes, #10 of 2025-04-11
  3. Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models 4 upvotes, #20 of 2025-03-27
  4. MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities 10 upvotes, #7 of 2024-08-02
  5. VideoGUI: A Benchmark for GUI Automation from Instructional Videos 8 upvotes, #13 of 2024-06-17
  6. MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos 23 upvotes, #10 of 2024-06-13
  7. List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs 14 upvotes, #8 of 2024-04-26
  8. StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis 20 upvotes, #4 of 2024-01-31
  9. Interfacing Foundation Models' Embeddings 10 upvotes, #11 of 2023-12-13
  10. Segment and Caption Anything 21 upvotes, #6 of 2023-12-05
  11. GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation 14 upvotes, #7 of 2023-11-14
  12. MM-VID: Advancing Video Understanding with GPT-4V(ision) 20 upvotes, #2 of 2023-10-31
  13. DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design 14 upvotes, #3 of 2023-10-24
  14. Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation 17 upvotes, #4 of 2023-10-13
  15. Multimodal Foundation Models: From Specialists to General-Purpose Assistants 41 upvotes, #2 of 2023-09-20
  16. ORES: Open-vocabulary Responsible Visual Synthesis 8 upvotes, #2 of 2023-08-29
  17. MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities 19 upvotes, #2 of 2023-08-07

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.