Bhuvan Sachdeva

40 posts

Bhuvan Sachdeva banner
Bhuvan Sachdeva

Bhuvan Sachdeva

@SachdevaBhuvan

Visiting Researcher at @MSFTResearch | Past Research at @AmazonScience Looking for Research Engineer roles!

Joined Aralık 2019
847 Following89 Followers
Bhuvan Sachdeva retweeted
Lorenzo Xiao
Lorenzo Xiao@lrzneedresearch·
Made a public RL-for-LLMs reading list because I was trying to prepare for my interviews 96 papers, 5 categories, 24 subtopics, mostly around the 2025-2026 wave, with notes on what’s worth reading carefully vs what you can skim. Hopefully useful if you’re getting into RLHF/agentic RL/ reward modeling, or just cramming for interviews. algoroxyolo.github.io/blog/2026/rl-r… Note: Paper selection mainly adhere to me and @sun_hanchi's taste... Make sure you follow me so I can have the incentive to update this and the agentic system design series #RLHF #LLM #AIAgents
English
18
89
930
51.5K
Bhuvan Sachdeva
Bhuvan Sachdeva@SachdevaBhuvan·
@_Creation22 Does a given sequence have a single solution only? For example, take a sequence that has all the numbers in order from 1 to 25, except 12. You can use 12 from the start and decompose 21 into 1 and 2. This way, the sequence can be missing 12 or 21.
English
0
0
0
726
Srajan
Srajan@_Creation22·
One of the hardest problems I have seen asked in a phone screen round.
Srajan tweet media
English
115
19
1.3K
475.2K
Bhuvan Sachdeva
Bhuvan Sachdeva@SachdevaBhuvan·
(5/5) For more details, check out the paper: arxiv.org/abs/2511.18787. Happy to answer questions! Shoutout to my amazing co-authors and mentor Vineeth N B.
English
0
0
3
146
Bhuvan Sachdeva
Bhuvan Sachdeva@SachdevaBhuvan·
(4/5) Why use PGF? PGF-guided selection enables alternative datasets that rival or surpass direct finetuning when supervision data is scarce.
Bhuvan Sachdeva tweet media
English
1
0
1
235
Bhuvan Sachdeva
Bhuvan Sachdeva@SachdevaBhuvan·
New paper: Understanding Task Transfer in Vision–Language Models How does finetuning a model on one task affect its performance on other tasks? @karan_uppal3 and @abhinav_java are presenting this work at Unireps, NeurIPS!! 📍 Ballroom 20D ⏰ 3:45 PM – 5:00 PM Come and say Hi!🧵
Bhuvan Sachdeva tweet media
English
1
5
16
7.3K
Bhuvan Sachdeva retweeted
Amit Sharma
Amit Sharma@amt_shrma·
Honored to be among the top three finalists for the 2025 TMLR Outstanding Paper Award. With the advent of LLMs, this paper helped me clarify what causal reasoning is, and I'm glad many others found it useful too. I believe it also offers a path forward in building causal agents and advancing scientific discovery. Some reflections below.
English
1
10
54
3.3K
Bhuvan Sachdeva
Bhuvan Sachdeva@SachdevaBhuvan·
@AkariAsai Hi! Are you planning to work on multimodal models or AI for healthcare? I’m applying for Fall 2026 and would love to explore these directions.
English
0
0
0
401
Akari Asai
Akari Asai@AkariAsai·
1/ Hiring PhD students at CMU SCS (LTI/MLD) for Fall 2026 (Deadline 12/10) 🎓 I work on open, reliable LMs: augmented LMs & agents (RAG, tool use, deep research), safety (hallucinations, copyright), and AI for science, code & multilinguality & open to bold new ideas! FAQ in 🧵
English
19
120
635
143.8K
Bhuvan Sachdeva retweeted
Shashank Kirtania
Shashank Kirtania@5hv5hvnk·
Excited to share that our paper “STACKFEED”, in collaboration with @namak_kun will be presented at EMNLP 2025! 🎉We explore how to make knowledge bases in RAG systems editable and adaptive instead of staying static and stale.
Shashank Kirtania tweet media
English
1
18
25
3.7K
Bhuvan Sachdeva retweeted
Jon Barron
Jon Barron@jon_barron·
It looks like @CVPR has implemented a new mandatory "Compute Reporting Form" that must be submitted alongside any paper submission. Though I am sympathetic to the motivations for this change, I am opposed to it for a variety of reasons:
#CVPR2026@CVPR

#AI research has an invisible cost: compute Starting with #CVPR2026, authors will report their compute usage. Aggregated data will help the community understand who can participate, what is sustainable, and how resources are used, promoting more transparent & equitable research.

English
3
33
226
93.9K
Nalin Wadhwa
Nalin Wadhwa@nalin_wadhwa·
I’m super excited to be joining @LingmingZhang at @UofIllinois as a PhD student from Fall 25. I will be working on ML, SE and everything in between. As always, DMs open to chat about cool ideas and collaborate!
English
13
0
122
6.3K
Bhuvan Sachdeva
Bhuvan Sachdeva@SachdevaBhuvan·
@jxmnop @rishi_d_jha @jxmnop @rishi_d_jha kudos, the paper is well written. Question: Since the setup only considers two embedding distributions at a time, does it make sense to consider the latent space universal, or is it a function of the two primary distributions and varies with different pairs?
English
0
0
0
23
dr. jack morris
dr. jack morris@jxmnop·
this was joint work with my friends @rishi_d_jha, collin zhang, and vitaly shmatikov at Cornell Tech our paper "Harnessing the Universal Geometry of Embeddings" is on ArXiv today: arxiv.org/abs/2505.12540
dr. jack morris tweet media
English
13
34
601
32.5K
dr. jack morris
dr. jack morris@jxmnop·
excited to finally share on arxiv what we've known for a while now: All Embedding Models Learn The Same Thing embeddings from different models are SO similar that we can map between them based on structure alone. without *any* paired data feels like magic, but it's real:🧵
dr. jack morris@jxmnop

this is sick all i'll say is that these GIFs are proof that the biggest bet of my research career is gonna pay off excited to say more soon

English
124
598
6.2K
908.2K
Bhuvan Sachdeva retweeted
Chris Offner
Chris Offner@chrisoffner3d·
I felt a great disturbance in the Force, as if millions of computer vision researchers suddenly cried out in terror...
Chris Offner tweet media
English
21
22
384
40.9K

Discover

@sun_hanchi @_Creation22 @karan_uppal3 @abhinav_java @AkariAsai @namak_kun @CVPR @nalin_wadhwa