JaneDing
@JaneDing_AI
Data Science junior @Umich · Starting research in vision-language models and pragmatic generation · Exploring how AI communicates like humans
🔎 New Toolkit Released: VLM-Lens 🔎 github.com/compling-wat/v… In the past 10 months, our lab, together with collaborators @ziqiao_ma @SLED_AI @jzhou_jz, developed a simple and streamlined interpretability toolkit for VLMs supporting 16 state-of-the-art models across the board!
![fredahshi's tweet card. [EMNLP 2025 Demo] Extracting internal representations from vision-language models. Beta version. - compling-wat/vlm-lens](https://pbs.twimg.com/card_img/1989526674870829056/QrZjhZzf?format=jpg&name=orig)
Over the past few months, I’ve heard the same complaint from nearly every collaborator working on computational cogsci + behavioral and mechanistic interpretability: “Open-source VLMs are a pain to run, let alone analyze.” We finally decided to do something about it (thanks…
Excited to attend #COLM2025 in Montréal this week! I’ll be presenting our paper "Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation", in Poster Session 4. Looking forward to meeting many of you there! ☺️ vlm-reg.github.io
Regrettably can’t attend #COLM2025 due to deadlines, but @JaneDing_AI and @SLED_AI will be presenting our work. :) @JaneDing_AI is an exceptional undergraduate researcher and a great collaborator! Go meet her at COLM if you’re curious about her work on mechanistic…
Vision-Language Models (VLMs) can describe the environment, but can they refer within it? Our findings reveal a critical gap: VLMs fall short of pragmatic optimality. We identify 3 key failures of pragmatic competence in referring expression generation with VLMs: (1) cannot…
+1 on this! Mixed-effects models are such an underrated protocol for behavioral analysis that AI researchers often overlook. Behavioral data are almost never independent: clustering, repeated measures, and hierarchical structures abound. Mixed-effects models account for these…
I'd highlight the point on generalization: to make a "poor generalization" argument, we need systematic evaluations. A promising protocol is prompting multiple LMs and treating each as an individual in mixed-effect models. arxiv.org/pdf/2502.09589 w/ @tom_yixuan_wang (2/n)
Our study on pragmatic generation is accepted to #COLM2025! Missed the first COLM last year (no suitable ongoing project at the time😅). Heard it’s a great place to connect with LM folks, excited to join for round two finally.
Vision-Language Models (VLMs) can describe the environment, but can they refer within it? Our findings reveal a critical gap: VLMs fall short of pragmatic optimality. We identify 3 key failures of pragmatic competence in referring expression generation with VLMs: (1) cannot…
Thrilled to finally share SimWorld — the result of over a year’s work of the team. Simulators have been foundational for embodied AI research (I’ve worked with AI2Thor, CARLA, Genesis…), and SimWorld pushes this further with photorealistic Unreal-based rendering and scalable…
P.S., We are building @GrowAiLikeChild, an open-source community uniting researchers from computer science, cognitive science, psychology, linguistics, philosophy, and beyond. Instead of putting growing up and scaling up into opposite camps, let's build and evaluate human-like AI…
Vision-Language Models (VLMs) can describe the environment, but can they refer within it? Our findings reveal a critical gap: VLMs fall short of pragmatic optimality. We identify 3 key failures of pragmatic competence in referring expression generation with VLMs: (1) cannot…
United States Tendenze
- 1. Mamdani 283K posts
- 2. Kandi 4,738 posts
- 3. Mama Joyce 1,294 posts
- 4. #ItsGoodToBeRight N/A
- 5. #HMGxBO7Sweeps 1,494 posts
- 6. Egg Bowl 2,191 posts
- 7. Brandon Aiyuk N/A
- 8. Chance Moore N/A
- 9. #BY9sweepstakes N/A
- 10. Ukraine 598K posts
- 11. Adolis Garcia 1,954 posts
- 12. #AleMeRepresenta N/A
- 13. Putin 209K posts
- 14. Richie Saunders N/A
- 15. Wisconsin 8,411 posts
- 16. Joshua 40.9K posts
- 17. El Bombi N/A
- 18. #DanSeats N/A
- 19. Nolan Jones N/A
- 20. Kiffin 11K posts
Something went wrong.
Something went wrong.