Manish Pandey
@manishgenai.bsky.social
Co-Founder @FreeDoctr 🧬⚕️ ,
Building a collaborative Platform for Patients and Doctors. 🌐🩻
#GraphML, #GeometricDL, #Gen AI #ML ,#RL, #LLM, #AIForHealthcare
https://www.linkedin.com/in/manish-genai/
Building a collaborative Platform for Patients and Doctors. 🌐🩻
#GraphML, #GeometricDL, #Gen AI #ML ,#RL, #LLM, #AIForHealthcare
https://www.linkedin.com/in/manish-genai/
Reposted by Manish Pandey
NEW PREPRINT
A detailed overview of 32 popular predictive performance metrics for prediction models
arxiv.org/abs/2412.10288
A detailed overview of 32 popular predictive performance metrics for prediction models
arxiv.org/abs/2412.10288
December 16, 2024 at 8:44 AM
NEW PREPRINT
A detailed overview of 32 popular predictive performance metrics for prediction models
arxiv.org/abs/2412.10288
A detailed overview of 32 popular predictive performance metrics for prediction models
arxiv.org/abs/2412.10288
Reposted by Manish Pandey
Excited for the #NeurIPS2024 workshops today! I'll be speaking at:
(1) Science of DL (panel, 3:10-4:10, scienceofdlworkshop.github.io/schedule/)
(2) "Time Series in the Age of Large Models" (talk, 4:39-5:14, neurips-time-series-workshop.github.io).
(1) Science of DL (panel, 3:10-4:10, scienceofdlworkshop.github.io/schedule/)
(2) "Time Series in the Age of Large Models" (talk, 4:39-5:14, neurips-time-series-workshop.github.io).
Schedule | SciForDL'24
scienceofdlworkshop.github.io
December 15, 2024 at 5:51 PM
Excited for the #NeurIPS2024 workshops today! I'll be speaking at:
(1) Science of DL (panel, 3:10-4:10, scienceofdlworkshop.github.io/schedule/)
(2) "Time Series in the Age of Large Models" (talk, 4:39-5:14, neurips-time-series-workshop.github.io).
(1) Science of DL (panel, 3:10-4:10, scienceofdlworkshop.github.io/schedule/)
(2) "Time Series in the Age of Large Models" (talk, 4:39-5:14, neurips-time-series-workshop.github.io).
Reposted by Manish Pandey
As a reminder, we will have our poster session tomorrow:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
Graph Transformers (GTs) can handle long-range dependencies and resolve information bottlenecks, but they’re computationally expensive. Our new model, Spexphormer, helps scale them to much larger graphs – check it out at NeurIPS next week, or the preview here!
[1/13]
#NeurIPS2024
[1/13]
#NeurIPS2024
December 12, 2024 at 12:29 AM
As a reminder, we will have our poster session tomorrow:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
📍 East Exhibit Hall, Poster #3010
📄 arxiv.org/abs/2411.16278
💻 github.com/hamed1375/Sp...
To motivate you further, we have some insights gained from the attention score analysis of this work, which I'll share in this thread:
Reposted by Manish Pandey
Gemini 2.0 Flash outperforms 1.5 Pro on key benchmarks at 2X speed
Now available in anychat try it out:
🤗 huggingface.co/spaces/akha...
Now available in anychat try it out:
🤗 huggingface.co/spaces/akha...
Anychat - a Hugging Face Space by akhaliq
huggingface.co
December 12, 2024 at 1:01 AM
Gemini 2.0 Flash outperforms 1.5 Pro on key benchmarks at 2X speed
Now available in anychat try it out:
🤗 huggingface.co/spaces/akha...
Now available in anychat try it out:
🤗 huggingface.co/spaces/akha...
Reposted by Manish Pandey
If you are a radiologist, imager, or otherwise just interested in imaging, I'm working on a starter pack of radiologists and imagers to follow to create a positive imaging community here.
If you want to be included or know other people to include, drop them in the replies
go.bsky.app/Gmkg4yX
If you want to be included or know other people to include, drop them in the replies
go.bsky.app/Gmkg4yX
November 11, 2024 at 2:35 AM
If you are a radiologist, imager, or otherwise just interested in imaging, I'm working on a starter pack of radiologists and imagers to follow to create a positive imaging community here.
If you want to be included or know other people to include, drop them in the replies
go.bsky.app/Gmkg4yX
If you want to be included or know other people to include, drop them in the replies
go.bsky.app/Gmkg4yX
Reposted by Manish Pandey
Couldn't find a machine learning for health starter pack so I made one.
DM/Reply if you want to be added!
go.bsky.app/PJKJ8vK
DM/Reply if you want to be added!
go.bsky.app/PJKJ8vK
November 17, 2024 at 6:34 AM
Couldn't find a machine learning for health starter pack so I made one.
DM/Reply if you want to be added!
go.bsky.app/PJKJ8vK
DM/Reply if you want to be added!
go.bsky.app/PJKJ8vK
Reposted by Manish Pandey
Updated: 6 benchmarks testing spatial and agent reasoning of LLM/VLMs
arxiv.org/abs/2410.06468 does spatial cognition
arxiv.org/abs/2307.06281 MMBench
arxiv.org/abs/2411.13543 BALROG
arxiv.org/abs/2410.07765 GameTraversalBenchmark
3dsrbench.github.io 3DSRBenchmark
open-eqa.github.io Open-EQA
arxiv.org/abs/2410.06468 does spatial cognition
arxiv.org/abs/2307.06281 MMBench
arxiv.org/abs/2411.13543 BALROG
arxiv.org/abs/2410.07765 GameTraversalBenchmark
3dsrbench.github.io 3DSRBenchmark
open-eqa.github.io Open-EQA
November 26, 2024 at 8:25 AM
Updated: 6 benchmarks testing spatial and agent reasoning of LLM/VLMs
arxiv.org/abs/2410.06468 does spatial cognition
arxiv.org/abs/2307.06281 MMBench
arxiv.org/abs/2411.13543 BALROG
arxiv.org/abs/2410.07765 GameTraversalBenchmark
3dsrbench.github.io 3DSRBenchmark
open-eqa.github.io Open-EQA
arxiv.org/abs/2410.06468 does spatial cognition
arxiv.org/abs/2307.06281 MMBench
arxiv.org/abs/2411.13543 BALROG
arxiv.org/abs/2410.07765 GameTraversalBenchmark
3dsrbench.github.io 3DSRBenchmark
open-eqa.github.io Open-EQA
Reposted by Manish Pandey
Medically adapted foundation models (think Med-*) turn out to be more hot air than hot stuff. Correcting for fatal flaws in evaluation, the current crop are no better on balance than generic foundation models, even on the very tasks for which benefits are claimed.
arxiv.org/abs/2411.04118
arxiv.org/abs/2411.04118
Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pret...
arxiv.org
November 26, 2024 at 6:12 PM
Medically adapted foundation models (think Med-*) turn out to be more hot air than hot stuff. Correcting for fatal flaws in evaluation, the current crop are no better on balance than generic foundation models, even on the very tasks for which benefits are claimed.
arxiv.org/abs/2411.04118
arxiv.org/abs/2411.04118
Reposted by Manish Pandey
The opportunities, challenges and outlook for LLM-based agents in medicine and healthcare—our paper published today
nature.com/articles/s42...
nature.com/articles/s42...
LLM-based agentic systems in medicine and healthcare - Nature Machine Intelligence
Large language model-based agentic systems can process input information, plan and decide, recall and reflect, interact and collaborate, leverage various tools and act. This opens up a wealth of oppor...
nature.com
December 5, 2024 at 1:29 PM
The opportunities, challenges and outlook for LLM-based agents in medicine and healthcare—our paper published today
nature.com/articles/s42...
nature.com/articles/s42...
Reposted by Manish Pandey
In a gratuitous attempt to acquire more followers myself 😁, I've made a start on a "starter pack". Hopefully as more people from 🐦 make it over to 🦋, we can extend this a bit. Suggestions welcome!
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
November 15, 2024 at 8:04 PM
In a gratuitous attempt to acquire more followers myself 😁, I've made a start on a "starter pack". Hopefully as more people from 🐦 make it over to 🦋, we can extend this a bit. Suggestions welcome!
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
Reposted by Manish Pandey
Three BioML starter packs now!
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
Pack 3: go.bsky.app/NAKYUok
DM if you want to be included (or nominate people who should be!)
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
Pack 3: go.bsky.app/NAKYUok
DM if you want to be included (or nominate people who should be!)
December 3, 2024 at 3:27 AM
Three BioML starter packs now!
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
Pack 3: go.bsky.app/NAKYUok
DM if you want to be included (or nominate people who should be!)
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
Pack 3: go.bsky.app/NAKYUok
DM if you want to be included (or nominate people who should be!)
Reposted by Manish Pandey
Stop by our #NeurIPS tutorial on Experimental Design & Analysis for AI Researchers! 📊
neurips.cc/virtual/2024/tutorial/99528
Are you an AI researcher interested in comparing models/methods? Then your conclusions rely on well-designed experiments. We'll cover best practices + case studies. 👇
neurips.cc/virtual/2024/tutorial/99528
Are you an AI researcher interested in comparing models/methods? Then your conclusions rely on well-designed experiments. We'll cover best practices + case studies. 👇
NeurIPS Tutorial Experimental Design and Analysis for AI ResearchersNeurIPS 2024
neurips.cc
December 7, 2024 at 6:15 PM
Stop by our #NeurIPS tutorial on Experimental Design & Analysis for AI Researchers! 📊
neurips.cc/virtual/2024/tutorial/99528
Are you an AI researcher interested in comparing models/methods? Then your conclusions rely on well-designed experiments. We'll cover best practices + case studies. 👇
neurips.cc/virtual/2024/tutorial/99528
Are you an AI researcher interested in comparing models/methods? Then your conclusions rely on well-designed experiments. We'll cover best practices + case studies. 👇
Reposted by Manish Pandey
🚨 Reverse Thinking Makes LLMs Stronger Reasoners
We can often reason from a problem to a solution and also in reverse to enhance our overall reasoning. RevThink shows that LLMs can also benefit from reverse thinking 👉 13.53% gains + sample efficiency + strong generalization (on 4 OOD datasets)!
We can often reason from a problem to a solution and also in reverse to enhance our overall reasoning. RevThink shows that LLMs can also benefit from reverse thinking 👉 13.53% gains + sample efficiency + strong generalization (on 4 OOD datasets)!
December 2, 2024 at 7:29 PM
🚨 Reverse Thinking Makes LLMs Stronger Reasoners
We can often reason from a problem to a solution and also in reverse to enhance our overall reasoning. RevThink shows that LLMs can also benefit from reverse thinking 👉 13.53% gains + sample efficiency + strong generalization (on 4 OOD datasets)!
We can often reason from a problem to a solution and also in reverse to enhance our overall reasoning. RevThink shows that LLMs can also benefit from reverse thinking 👉 13.53% gains + sample efficiency + strong generalization (on 4 OOD datasets)!
Reposted by Manish Pandey
This is one of my all time favorite papers:
openreview.net/forum?id=ByJ...
It shows that, under fair experimental evaluation, lstms do just as well as a bunch of “improvements”
openreview.net/forum?id=ByJ...
It shows that, under fair experimental evaluation, lstms do just as well as a bunch of “improvements”
On the State of the Art of Evaluation in Neural Language Models
Show that LSTMs are as good or better than recent innovations for LM and that model evaluation is often unreliable.
openreview.net
December 7, 2024 at 3:51 PM
This is one of my all time favorite papers:
openreview.net/forum?id=ByJ...
It shows that, under fair experimental evaluation, lstms do just as well as a bunch of “improvements”
openreview.net/forum?id=ByJ...
It shows that, under fair experimental evaluation, lstms do just as well as a bunch of “improvements”
Reposted by Manish Pandey
Ahead of NeurIPS next week, we published our Papers of the month, a selection of fresh AI ideas worth knowing about.
graphcore-research.github.io/papers-of-th...
graphcore-research.github.io/papers-of-th...
November Papers: An LLM Feast
This month we’ve got an all-LLM menu of papers for you, with summaries of four great works exploring many different aspects of crafting systems for LLM training and inference.
graphcore-research.github.io
December 6, 2024 at 11:59 PM
Ahead of NeurIPS next week, we published our Papers of the month, a selection of fresh AI ideas worth knowing about.
graphcore-research.github.io/papers-of-th...
graphcore-research.github.io/papers-of-th...
Reposted by Manish Pandey
I had a recent great interview with @PeterDiamandis . Dont miss it:
www.youtube.com/watch?v=n1BV...
www.youtube.com/watch?v=n1BV...
Ex-Google China President on How China Is Shaping the Future of AI w/ Kai-Fu Lee | EP #134
YouTube video by Peter H. Diamandis
www.youtube.com
December 6, 2024 at 11:24 PM
I had a recent great interview with @PeterDiamandis . Dont miss it:
www.youtube.com/watch?v=n1BV...
www.youtube.com/watch?v=n1BV...
Reposted by Manish Pandey
« RSNA has been called radiology’s Super Bowl and this year didn’t disappoint. RSNA 2024 showed that radiology is prepared to fully embrace AI – and a future in which humans and machines collaborate to deliver better patient care » @brian-casey.bsky.social
theimagingwire.com/2024/12/04/a...
theimagingwire.com/2024/12/04/a...
RSNA Goes All-In on AI - The Imaging Wire
It’s been AI all the time this week at RSNA 2024.
theimagingwire.com
December 6, 2024 at 9:23 PM
« RSNA has been called radiology’s Super Bowl and this year didn’t disappoint. RSNA 2024 showed that radiology is prepared to fully embrace AI – and a future in which humans and machines collaborate to deliver better patient care » @brian-casey.bsky.social
theimagingwire.com/2024/12/04/a...
theimagingwire.com/2024/12/04/a...
Reposted by Manish Pandey
1/ I get the impulse to simplify things for a popular science articule, but I don't think "fake and sucks" versus "real and dangerous" is an accurate reflection of the debates in #AI.
The real debates are of course more nuanced, and interesting...
Small 🧵
The real debates are of course more nuanced, and interesting...
Small 🧵
One of the most important debates in tech right now is the group of folks who think AI is fake and sucks vs. the people who think AI is real and dangerous. I wrote about why I'm in the latter camp, and talked about my differences with Gary Marcus www.platformer.news/ai-skeptics-...
December 6, 2024 at 11:34 PM
1/ I get the impulse to simplify things for a popular science articule, but I don't think "fake and sucks" versus "real and dangerous" is an accurate reflection of the debates in #AI.
The real debates are of course more nuanced, and interesting...
Small 🧵
The real debates are of course more nuanced, and interesting...
Small 🧵
Reposted by Manish Pandey
🚀 Our mission to strengthen the multilingual open-source ecosystem continues!👇
Is MMLU Western-centric? 🤔
As part of a massive cross-institutional collaboration:
🗽Find MMLU is heavily overfit to western culture
🔍 Professional annotation of cultural sensitivity data
🌍 Release improved Global-MMLU 42 languages
📜 Paper: arxiv.org/pdf/2412.03304
📂 Data: hf.co/datasets/Coh...
As part of a massive cross-institutional collaboration:
🗽Find MMLU is heavily overfit to western culture
🔍 Professional annotation of cultural sensitivity data
🌍 Release improved Global-MMLU 42 languages
📜 Paper: arxiv.org/pdf/2412.03304
📂 Data: hf.co/datasets/Coh...
December 6, 2024 at 11:04 PM
🚀 Our mission to strengthen the multilingual open-source ecosystem continues!👇
Reposted by Manish Pandey
OpenAI announced a new RL finetuning API. You can do this on open models w the repo we used to train Tulu 3.
Expanding reinforcement learning with verifiable rewards to more domains and with better answer extraction and to more domains in our near roadmap.
https://buff.ly/3V4JEIJ
Expanding reinforcement learning with verifiable rewards to more domains and with better answer extraction and to more domains in our near roadmap.
https://buff.ly/3V4JEIJ
December 6, 2024 at 6:27 PM
OpenAI announced a new RL finetuning API. You can do this on open models w the repo we used to train Tulu 3.
Expanding reinforcement learning with verifiable rewards to more domains and with better answer extraction and to more domains in our near roadmap.
https://buff.ly/3V4JEIJ
Expanding reinforcement learning with verifiable rewards to more domains and with better answer extraction and to more domains in our near roadmap.
https://buff.ly/3V4JEIJ
Reposted by Manish Pandey
Glad to see synthetic data really coming to the fore in 3D Vision recently! Here's MegaSaM showing stunning results from synthetic data: mega-sam.github.io
December 6, 2024 at 6:47 PM
Glad to see synthetic data really coming to the fore in 3D Vision recently! Here's MegaSaM showing stunning results from synthetic data: mega-sam.github.io
Reposted by Manish Pandey
31% of US adults use generative AI for healthcare 🤯But most AI systems answer questions assertively—even when they don’t have the necessary context. Introducing #MediQ a framework that enables LLMs to recognize uncertainty🤔and ask the right questions❓when info is missing: 🧵
December 6, 2024 at 10:51 PM
31% of US adults use generative AI for healthcare 🤯But most AI systems answer questions assertively—even when they don’t have the necessary context. Introducing #MediQ a framework that enables LLMs to recognize uncertainty🤔and ask the right questions❓when info is missing: 🧵