Adi Chinchure
@adityachinchure
Followers
306
Following
13K
Media
770
Statuses
2K
PhD student @UBC_CS, @VectorInst | Video Reasoning + Generation | prev @BorealisAI @TTIC_Connect | Photography & Av Geek
Vancouver, British Columbia
Joined August 2010
Here's our #CVPR2025 work: we benchmark video understanding models on their reasoning capabilities. Check it out below ⬇️.
Unexpected events grab human attention & push AI models beyond their training data. 🤔. How well do VLMs reason about these critical, novel scenarios?. 🦢 Introducing Black Swan #CVPR2025!. Co-lead: @adityachinchure.w/ @AlbertBoyangLi @VeredShwartz. 🔗
0
0
5
RT @oscmansan: I’m happy to share that our paper "Controlling Multimodal LLMs via Reward-guided Decoding" has been accepted to #ICCV2025! 🎉….
0
30
0
RT @deyneka_e: The fastest way to get smarter is to read smarter people. I went through @tbpn’s Metis List and pulled together blogs from….
0
154
0
RT @PShravannayak: A Hindu wedding without a sacred fire? A Chinese banquet with forks?.Do text-to-image models meet cultural expectations,….
0
23
0
RT @jason_lee328: Introducing MolmoAct . Our Action Reasoning Model that can Reason in Space . (1/)🧵⬇️
0
37
0
RT @agermanidis: Why I think that advancing simulation is the most important thing to be working on in AI
0
13
0
RT @random_walker: Many people have told us that this is one of the most memorable opening paragraphs they've come across in a book. 🙏 The….
0
41
0
RT @OwainEvans_UK: New paper & surprising result. LLMs transmit traits to other models via hidden signals in data. Datasets consisting only….
0
1K
0
RT @JacksonAtkinsX: LLMs can now self-optimize. A new method allows an AI to rewrite its own prompts to achieve up to 35x greater efficie….
0
333
0
RT @SFU_CompSci: What a day at the Vision & Learning Workshop at #ICML2025!. With an incredible lineup of speakers to lighting talks on rec….
0
30
0
RT @ShivamChandhok2: 🚀⚡️Excited to share 2 papers accepted at #ACL2025 on #Multimodal Vision-Language Models (#VLM). ✨Response Wide Shut? S….
0
3
0
RT @_vaishnavh: 📢 New paper on creativity & multi-token prediction! We design minimal open-ended tasks to argue:. → LLMs are limited in cre….
0
40
0
0
4
0
RT @IAmEricHedlin: Come to poster #103 tomorrow morning to find out how to make hypernetworks stable and scalable #CVPR25 . .
0
13
0
RT @Sahithya_Ravi: Presenting this work with @adityachinchure at #CVPR2025 today:. 🖼 Poster #304.📍 ExHall D.🕥 10:30 AM – 12:30 PM. We inves….
0
4
0
Come find our work at the #CVPR2025 poster session tomorrow 🚀.
On Sunday, June 15, @Sahithya_Ravi and @adityachinchure will present their Black Swan benchmark for reasoning about surprising events in videos (10:30 - 12:30 Poster Session 5 @ ExHall D). 2/3
0
0
2
It’s great to see #CVPR2025 recognize the efforts of dedicated reviewers 🎉 - we really need more such reviewers in the AI/CV/NLP community in this era of LLM-written low quality reviews!. If you’re here at CVPR and interested in video reasoning, DM me and let’s chat!
0
1
6
RT @UBC_NLP: Great food, even better company. UBC NLP’s potluck brought together flavors and stories from around the world 🌎 Thanks to ever….
0
5
0
RT @IVADO_Qc: 🙌 And that's a wrap on our Thematic Semester on LLMs and Transformers with the @SimonsInstitute!. Stay tuned for a deep dive….
0
4
0