Ranjay Krishna

Ranjay Krishna on Hugging Face Daily Papers: 17 papers, 2 in the top 3 of their day, 457 upvotes.

  1. MolmoPoint: Better Pointing for VLMs with Grounding Tokens 8 upvotes, #26 of 2026-03-31
  2. MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation 8 upvotes, #27 of 2026-03-18
  3. Video-Based Reward Modeling for Computer-Use Agents 41 upvotes, #4 of 2026-03-13
  4. Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding 26 upvotes, #15 of 2026-01-16
  5. PointArena: Probing Multimodal Grounding Through Language-Guided Pointing 11 upvotes, #14 of 2025-05-16
  6. Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation 13 upvotes, #14 of 2025-02-21
  7. Perception Tokens Enhance Visual Reasoning in Multimodal Language Models 16 upvotes, #12 of 2024-12-11
  8. Negative Token Merging: Image-based Adversarial Feature Guidance 21 upvotes, #9 of 2024-12-06
  9. Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment 20 upvotes, #6 of 2024-11-28
  10. One Diffusion to Generate Them All 24 upvotes, #6 of 2024-11-26
  11. NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples 35 upvotes, #3 of 2024-10-21
  12. Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models 89 upvotes, #1 of 2024-09-26
  13. Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model 20 upvotes, #4 of 2024-08-02
  14. Efficient Inference of Vision Instruction-Following Models with Elastic Cache 15 upvotes, #8 of 2024-07-26
  15. Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions 9 upvotes, #9 of 2024-07-10
  16. Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps 10 upvotes, #8 of 2024-07-10
  17. Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models 17 upvotes, #9 of 2024-06-14

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.