Bharath Hariharan (@bharathharihar3) 's Twitter Profile
Bharath Hariharan

@bharathharihar3

Associate Professor @ CS, Cornell University. Computer vision / ML researcher

ID: 1277775881348493315

linkhttp://home.bharathh.info calendar_today30-06-2020 01:30:23

97 Tweet

403 Followers

113 Following

Tapomayukh "Tapo" Bhattacharjee (@tapobhat) 's Twitter Profile Photo

Congrats Rohan Banerjee and the team on getting nominated for Best paper award at #ICRA2025 for their work on “To ask or not to ask: Human-in-the-loop contextual bandits with applications in robot-assisted feeding”. Check out his presentation in Room 302 on Tuesday at the Awards

Greg Durrett (@gregd_nlp) 's Twitter Profile Photo

Revoking visas to Chinese PhD students is economically shortsighted and inhumane. Most Chinese PhD students stay in the U.S. after graduation (first image, stats from 2022). They're staying and building technology in the U.S., not taking it to China. Immigrant students create

Revoking visas to Chinese PhD students is economically shortsighted and inhumane.

Most Chinese PhD students stay in the U.S. after graduation (first image, stats from 2022). They're staying and building technology in the U.S., not taking it to China.

Immigrant students create
Tapomayukh "Tapo" Bhattacharjee (@tapobhat) 's Twitter Profile Photo

So proud of what we achieved with the PhyRC Challenge at #ICRA2025 with the support of our generous sponsors Kinova and Hello Robot! From simulation to real-world assistive care tasks -- robot-assisted dressing and bed-bathing -- this was an ambitious undertaking.

Bharath Hariharan (@bharathharihar3) 's Twitter Profile Photo

For those at CVPR, Aditya will be presenting this poster tomorrow at 10:30 (Exhibit hall D, Poster #34). Come hear about why neural field derivatives are noisy, and how we resurrect image processing ideas for neural fields!

Jelani Nelson (@minilek) 's Twitter Profile Photo

Receiving the Turing Award, Andrew Barto thanks the federal government (especially AFOSR) for supporting work on reinforcement learning before it was popular, and says without it “none of this would have ever happened”. RL is now at the heart of training/finetuning LLMs,

Receiving the Turing Award, Andrew Barto thanks the federal government (especially <a href="/AFOSR/">AFOSR</a>) for supporting work on reinforcement learning before it was popular, and says without it “none of this would have ever happened”.

RL is now at the heart of training/finetuning LLMs,
Bharath Hariharan (@bharathharihar3) 's Twitter Profile Photo

If you are at CVPR, come to poster # 297 at 4 pm today to hear Utkarsh Mall talk about DiSciPLE: an LLM+evolutionary framework for fitting interpretable programs to data! disciple.cs.columbia.edu

Chuanruo Ning (@tritiumac) 's Twitter Profile Photo

How can robots solve tasks that demand both semantic and physical reasoning, like playing real-world Angry Birds, without tons of data? We introduce Prompting with the Future: an MPC framework that fuses a pretrained VLM with an interactive digital twin for grounded, open-world

Bharath Hariharan (@bharathharihar3) 's Twitter Profile Photo

Utkarsh is doing wonderful work on understanding foundation models for scientific applications. He has also been an amazing mentor for all the students in my group. He will be a great advisor!

ICLR 2025 (@iclr_conf) 's Twitter Profile Photo

Policies on LLMs Usage at ICLR 2026 have been released: Policy 1⃣ Any use of an LLM must be disclosed Policy 2⃣ ICLR authors and reviewers are ultimately responsible for their contributions Full policy here 👉blog.iclr.cc/2025/08/26/pol…

ICLR 2025 (@iclr_conf) 's Twitter Profile Photo

The Abstract deadline is soon: 11:59pm, Sep 19 (Anywhere on Earth). Don’t wait until the last minute 😉 Best of luck to everyone submitting!

Bharath Hariharan (@bharathharihar3) 's Twitter Profile Photo

Oh god I miss this so much. I was told that grad school was the high point of research life; I just didn't realize how high it was.