Marija Stanojevic
@mstanojevic118
Followers
282
Following
946
Media
23
Statuses
305
ML, NLP, ML4Health, MultiModality, and STEM geek. Travel enthusiast. [email protected]
Joined June 2010
I truly enjoyed giving this lecture on Machine Unlearning and was positively surprised by the interest of the audience! Hope to do it again next year!.
š Join @mstanojevic118 from EudAImonia Science for an insightful talk on Machine Unlearning in LLMs and MMs. Discover how to enhance AI ethics, privacy, and compliance. š¤ Register now:
0
0
1
RT @jxmnop: New Research:. a lot of talk today about "what happens" inside a language model, since they spend the exact same amount of compā¦.
0
150
0
RT @AI21Labs: Introducing Jamba, our groundbreaking SSM-Transformer open model!. As the first production-grade model based on Mamba architeā¦.
0
246
0
While companies are trying to find the talent they don't have, the interviews are mostly testing the alignment of candidate's knowledge with the talent they already have.
0
1
2
When can I buy this for my husband? š.
Folding clothes with $250 robot arms. I've added another motor to improve mobility and extend the reach. The CAD files and the code are public at: (video at 2x speed)
0
0
1
RT @kchonyc: a tiny bit of a cat is out now; we train our own large (medium) sized LM on our own proprietary data from scratch ourselves atā¦.
0
6
0
RT @DrJimFan: Foundation Agent: a roadmap to build generally capable embodied AI that acts skillfully across many worlds, virtual or real.ā¦.
0
259
0
Insane! So exciting!.
Livestream of @Neuralink demonstrating āTelepathyā ā controlling a computer and playing video games just by thinking.
0
0
0
RT @srush_nlp: If you know Torch, I think you can code for GPU now with OpenAI's Triton language. We made some puzzles to help you rewireā¦.
0
197
0
Great resource!.
Holy! The Machine Learning Engineering Open Book repo has just crossed 9k stars on github! . That's insane as I have started writing it ~6 month ago!. Thank you so much for your vote of confidence! It's super encouraging to continue investing into this
0
0
1
RT @chelseabfinn: Introducing a new, fully open robotics dataset!. - 76k episodes.- 564 unique scenes.- 100 contributors.- 13 labs/institutā¦.
0
148
0
RT @DrJimFan: Today is the beginning of our moonshot to solve embodied AGI in the physical world. Iām so excited to announce Project GR00T,ā¦.
0
1K
0
While everyone is talking about NVIDIA Blackwell GPU, I am equally impressed by speed and quality of AI software development. With a support for all kinds of tasks and data, including preprocessing, training, finetuning, and postprocessing they make it easy for anyone to add ML.
0
0
0
RT @emnlpmeeting: EMNLP 2024 invites the submission of long and short papers featuring substantial, original, and unpublished research on eā¦.
2024.emnlp.org
Official website for the 2024 Conference on Empirical Methods in Natural Language Processing
0
48
0
Why is this done only up to the age of 84 when that's an average living time in some countries? It would also be interesting to see how it compares with data from other countries.
What do people die from at different ages?. I hadnāt seen a satisfying chart that showed causes of death in different age groups all at once, so I just made it myself. Turns out, in the US, āexternal causesā are a majority of deaths until ~age 40.
1
0
0
RT @DrJimFan: We live in such strange times. Apple, a company famous for its secrecy, published a paper with staggering amount of details oā¦.
0
730
0
RT @srush_nlp: @DimitrisPapail I'm biased but I think this paper is pretty cool too (at ICLR this year).
arxiv.org
Language models produce a distribution over the next token; can we use this information to recover the prompt tokens? We consider the problem of language model inversion and show that next-token...
0
8
0
RT @soumithchintala: Here's details on Meta's 24k H100 Cluster Pods that we use for Llama3 training. * Network: two versions RoCEv2 or Infiā¦.
0
192
0