Manu Gaur @gaur_manu
used to do physics, now multiplying matrices @CarnegieMellon | prev @IIIT_Hyderabad manugaurdl.github.io New Delhi, India Joined May 2012-
Tweets2K
-
Followers513
-
Following871
-
Likes19K
great blog by @setlur_amrith @aviral_kumar2 on driving knowledge acquisition during training by incentivizing the model to chain existing asymmetric capabilities. basically stitching order from chaos!
stuck in Paris, speedrunning @giffmana’s recent talk on VLMs. really great stuff, especially at the end!
Great research work. The thread is a gold mine for anyone interested in understanding diffusion language modelling and how it fares with AR models!
Great research work. The thread is a gold mine for anyone interested in understanding diffusion language modelling and how it fares with AR models!
Yup. the linear layer can reconstruct using the residual stream as long as the image is scaled. It works even if you initialize siglip with random weights :
Yup. the linear layer can reconstruct using the residual stream as long as the image is scaled. It works even if you initialize siglip with random weights : https://t.co/vlmoW3sz4v
Moving beyond MCQ to tasks that evaluate free-form generation is crucial to develop systems that better understand instructions and leverage EXISTING knowledge more effectively. From my work - gemini knows the prominent point of difference (aces VQA), but fails to independently…
Moving beyond MCQ to tasks that evaluate free-form generation is crucial to develop systems that better understand instructions and leverage EXISTING knowledge more effectively. From my work - gemini knows the prominent point of difference (aces VQA), but fails to independently… https://t.co/oENP5zxcX9
"On MMMU Pro , a visual question-answering benchmark with 10 choices, we obtain 51% shortcut-accuracy without showing the image or the question" Cambrian did show language shortcuts made by MLLMs on popular VQA datasets, but shortcuts using just the multiple choices is insane!
"On MMMU Pro , a visual question-answering benchmark with 10 choices, we obtain 51% shortcut-accuracy without showing the image or the question" Cambrian did show language shortcuts made by MLLMs on popular VQA datasets, but shortcuts using just the multiple choices is insane! https://t.co/4A6rgVNzsT
MCQ is great for checking existence of specific knowledge i.e if model fails to answer, it definitely lacks it. However, providing the answer along with the task prompt biases model's output towards the very concept that is being evaluated. This raises questions about whether the…
MCQ is great for checking existence of specific knowledge i.e if model fails to answer, it definitely lacks it. However, providing the answer along with the task prompt biases model's output towards the very concept that is being evaluated. This raises questions about whether the…
feeling dumb that I never thought of it this way. makes total sense, a linear classifier learns the "ideal" vector W_j for each class. with CLIP, we can simply replace the learnt W_j with text embeddings - so the text encoder effectively is a hypernetwork.
the fomo is very real for those outside the frontier labs. Curiosity driven research remains a healthy escape (for me at least)— feynman style, detached from the outcomes and pursued solely for the love of the game. Whether or not I succeed, I’d certainly enjoy the ride.
the fomo is very real for those outside the frontier labs. Curiosity driven research remains a healthy escape (for me at least)— feynman style, detached from the outcomes and pursued solely for the love of the game. Whether or not I succeed, I’d certainly enjoy the ride.
This is who runs this account
This is who runs this account https://t.co/qsyM58A0ZX
lance armstrong's favourite policy gradient method!
lance armstrong's favourite policy gradient method!
“there was no importance to what I was doing, but ultimately there was” :)
“there was no importance to what I was doing, but ultimately there was” :) https://t.co/EpYTNU5tVu
you can take a man out of physics, but you can't take the physics out of the man 😉 great talk by kaiming!
Yanqing Liu @YanqingLiu83931
34 Followers 98 Following student researcher @Google; Phd student @ucsc; B.Eng. in CS @ZJU_China
thinkingbets @thinkingbets
157 Followers 725 Following ml | quant | crypto systematic asymmetry hunter
pdawg @prathamgrv
16K Followers 2K Following pre doctoral researcher @MSFTResearch || part time @TensorTonic
Rohin Manvi @rohin_manvi
506 Followers 356 Following phd-ing @berkeley_ai | research @liquidai_ | prev @stanford @stanfordailab, @meta
Dharmesh Kakadia @dharmeshkakadia
1K Followers 6K Following Building https://t.co/VcaMs28aTa to give post-training superpower to everyone. @mixtrainai Past @nuro @zoox @Microsoft @MSFTResearch
VegetaAvatar @VeGeTaX29
19 Followers 6K Following
Harman Singh @Harman26Singh
992 Followers 2K Following ??, Prev: Gemini @GoogleDeepMind, AI Resident @MetaAI. Creating intelligence.
Sathish @Sathishkuna1
104 Followers 2K Following Engineer .Currently building LanguageLift . #100xdevs✨
Pankaj Gupta @pankaj_ipynb
62 Followers 2K Following The English language can not fully capture the depth and complexity of my thoughts; So I'm incorporate Emojis into my work to better express myself 😉.
Rohan Choudhury @rchoudhury997
496 Followers 508 Following phd student at cmu https://t.co/pjU847PL2f
MiriamSamuel @3Wgk1F060S0S75
29 Followers 2K Following
Yuvraj Singh @YuvrajS9886
2K Followers 525 Following Ex - @turboml, @puch_ai | @iitmadras (left), @iiserkol, @UofMaryland, AIISC | YESIST '24 Finalist | Multimodal LLMs Research| Building SmolHub ☺️, NeatRL
dogs so cute that cou... @dogssaveworld
117K Followers 65K Following
Sumeet Motwani @sumeetrm
1K Followers 2K Following Research Intern@Microsoft Phi | ML PhD at Oxford, Previously CS at UC Berkeley
Connor Treacy @theconnortreacy
18K Followers 13K Following
Social Use @socialuseai
255K Followers 7K Following Where Social meets AI: Exploring the future of connected intelligence
Ayush Upadhyay @upadh3387_ayush
3 Followers 9 Following
huduga @zaph0id
655 Followers 4K Following Finding the cadence of life. Hoarder of books, stories and experiences, entrepreneur.
NinetyOne @Nin3tyOne
737 Followers 4K Following 🇨🇦 | Psalm 91 | He/Him | Minecraft | YouTube | RTC? @bezemphy @swagrum77_ LEGENDS https://t.co/E4UflQvfVw
Santosh Patapati @ IC... @santoshpatapati
146 Followers 477 Following Computer Vision Optimization and Theory. prev @3blue1brown, @UW, & Stealth (acq $1M+)
Eshaan Modi @eshaan_modi
51 Followers 106 Following
Vivek Gupta @keviv9
3K Followers 5K Following Assistant Professor @SCAI_ASU; PostDoc @cogcomp @Penn, ed-@UUtah,@iitkanpur. @Bloomberg @MSFTResearch Fellow; ex-@MetaAI @IBM @Verisk @samsungresearch @Synopsys
Səbuhi Abbaszadə @SAbbaszad70856
15 Followers 1K Following
Greg Cook @GregCook2011
2K Followers 7K Following To the stars. SMA. The future takes time. Synthesizer, Polymath. Views expressed here are my own.
ozan @ozanpali
84 Followers 865 Following
Udoh Richard @UdohRichar41532
65 Followers 1K Following
coreVista @SoftVista
62 Followers 342 Following AI research & development Engineer, Designer, Inventor, Architect Co-Founder @ Bestyon Medical Networks
Ian Liu 劉以恆 @duckiesfloat
63 Followers 1K Following MS @BrownBiostats | Data Science Graduate & Classical Chinese Dancer @FTCNorthern | 🇺🇸🇹🇼
Xuheng Li @xuhengli_
950 Followers 2K Following CS PhD candidate @UCLA, supervised by @QuanquanGu | RL, deep learning theory, diffusion model | Previously BSc @PKU1898 | Stargazer
Arjun Choudhry @Arjun_7m
266 Followers 1K Following 1st Year ML PhD @GeorgiaTech. Previously @AutonLab @SCSatCMU, @UTSAAII, @UQAM, @dtu_delhi. Interests: Multimodal FMs, Structured Data, Efficiency
Bhavika Devnani @BhavikaDevnani1
10 Followers 292 Following ML PhD Student @ Georgia Tech | AI @ Apple
Bm Fatiur Rahman @BmFatiur
7 Followers 331 Following
Sparsh Tewatia @spteotia
72 Followers 3K Following Next token prediction enjoyer Currently doing MS in AI
Huy Le @huile1611
69 Followers 2K Following Working on generalizing and optimizing foundation multimodal models 👀✍️🤖🌍 @Mila_Quebec & @UMontrealDIRO
Sd @Sd91470555
88 Followers 3K Following
lakshya @lakshyaag
692 Followers 391 Following AI engineering in Private Equity @BainandCompany, prev @mcgillu, edtech startup, @UnivofDelhi
rasdani @rasdani_
471 Followers 3K Following
Tairan He @TairanHe99
5K Followers 766 Following Robotics&AI PhD Student @CMU_Robotics Research Intern at @NVIDIA Prev: @MSFTResearch @sjtu1896 Emboddied AI; Humanoid; Robot Learning
Jiayi Pan @jiayi_pirate
13K Followers 1K Following 🧑🍳 Reasoning Agents @xAI | PhD on Leave @Berkeley_AI | Views Are My Own
Oğuzhan Fatih Kar @oguzhanthefatih
923 Followers 542 Following Machine Learning Researcher at @Apple. CS PhD @EPFL_en on multimodal foundation models. Previously @Google, @METU_ODTU, @aselsan.
Yuxiang Wei @YuxiangWei9
709 Followers 263 Following PhD candidate @IllinoisCDS | Researcher @AIatMeta (Meta FAIR). Code LLM training.
Charlie Snell @sea_snell
8K Followers 6K Following PhD student @berkeley_ai; research @cursor_ai; prev @GoogleDeepMind. My friend told me to tweet more. I stare at my computer a lot and make things
Gavin Guo @Zhen4good
562 Followers 466 Following Embodiment @MSL Previously @Apple Siri @MITIBMLab @MIT_CSAIL @BerkeleyPhysics Opinions Are My Own
Arnab @ArnabMondal96
2K Followers 488 Following ML Researcher @Apple | PhD @mcgillu + @Mila_Quebec | Undergrad @IITKgp | Formerly: @MSFTResearch @ServiceNowRSRCH @samsungresearch
Yanqing Liu @YanqingLiu83931
34 Followers 98 Following student researcher @Google; Phd student @ucsc; B.Eng. in CS @ZJU_China
罗杰斯 🇺🇦 @dhbrojas
141 Followers 806 Following Research Engineer 智谱 https://t.co/vrJX6VOASs | Advanced Computing 清华大学
Rohin Manvi @rohin_manvi
506 Followers 356 Following phd-ing @berkeley_ai | research @liquidai_ | prev @stanford @stanfordailab, @meta
pdawg @prathamgrv
16K Followers 2K Following pre doctoral researcher @MSFTResearch || part time @TensorTonic
Zhi Rui Tam @zraytam
478 Followers 319 Following Research scientist at Appier. PhD at NTU. Try to make stochastic parrot smarter through yelling tokens.
Hensen Juang @basedjensen
12K Followers 1K Following inference cluster janitor / Sys admin cum architect
Wenhao Chai @wenhaocha1
2K Followers 2K Following Ph.D. Student @PrincetonCS. Prev @Stanford @UW @pika_labs @MSFTResearch @UofIllinois @ZJU_China. I used to work on computer vision, but it's not all I do.
Joy Hsu @joycjhsu
3K Followers 302 Following CS PhD-ing @stanford & @knighthennessy. Studying visual reasoning, neuro-symbolic learning, and visual concepts @stanfordailab & @stanfordsvl.
tokenbender @tokenbender
9K Followers 696 Following playing reward lottery• chaotic neutral • critique by creating
Nader Khalil🍊 @NaderLikeLadder
9K Followers 3K Following Director of Developer Tech @ NVIDIA, Co-founder/CEO https://t.co/GCUjRDOu73 acquired by NVIDIA • I laugh til I cry it's not the same on zoom •YC W20 | UCSB • views are my own
Keenan Crane @keenanisalive
37K Followers 483 Following Digital Geometer, Assoc. Prof. of Computer Science & Robotics @CarnegieMellon @SCSatCMU and member of the @GeomCollective. There are four lights.
Dharmesh Kakadia @dharmeshkakadia
1K Followers 6K Following Building https://t.co/VcaMs28aTa to give post-training superpower to everyone. @mixtrainai Past @nuro @zoox @Microsoft @MSFTResearch
Hao Liu @haoliuhl
5K Followers 175 Following Incoming Assistant Professor of Machine Learning @CarnegieMellon, Research Scientist at Google DeepMind, Berkeley PhD @Berkeley_AI
Yuvraj Singh @YuvrajS9886
2K Followers 525 Following Ex - @turboml, @puch_ai | @iitmadras (left), @iiserkol, @UofMaryland, AIISC | YESIST '24 Finalist | Multimodal LLMs Research| Building SmolHub ☺️, NeatRL
Pankaj Gupta @pankaj_ipynb
62 Followers 2K Following The English language can not fully capture the depth and complexity of my thoughts; So I'm incorporate Emojis into my work to better express myself 😉.
Ifigeneia Apostolopou... @ifaposto
563 Followers 71 Following
Sumeet Motwani @sumeetrm
1K Followers 2K Following Research Intern@Microsoft Phi | ML PhD at Oxford, Previously CS at UC Berkeley
Oscar Mañas @oscmansan
1K Followers 2K Following Visiting researcher @AIatMeta, PhD candidate @Mila_Quebec @UMontrealDIRO. Working on multimodal vision+language learning. Català a Montreal.
Santosh Patapati @ IC... @santoshpatapati
146 Followers 477 Following Computer Vision Optimization and Theory. prev @3blue1brown, @UW, & Stealth (acq $1M+)
leloy! @leloykun
6K Followers 4K Following Math @ AdMU • NanoGPT speedrunner • Muon fan 🤍 • prev ML @ XPD • 2x IOI & 2x ICPC • https://t.co/nfO038itfn
CMU Robotics Institut... @CMU_Robotics
21K Followers 267 Following Pioneering the future of robotics since 1979. We’re transforming industries and everyday life through cutting-edge innovation and world-class education.
Seohong Park @seohong_park
4K Followers 532 Following Reinforcement learning | CS Ph.D. student @berkeley_ai
Arjun Choudhry @Arjun_7m
266 Followers 1K Following 1st Year ML PhD @GeorgiaTech. Previously @AutonLab @SCSatCMU, @UTSAAII, @UQAM, @dtu_delhi. Interests: Multimodal FMs, Structured Data, Efficiency
Xuheng Li @xuhengli_
950 Followers 2K Following CS PhD candidate @UCLA, supervised by @QuanquanGu | RL, deep learning theory, diffusion model | Previously BSc @PKU1898 | Stargazer
Zhiqiu Lin @ZhiqiuLin
528 Followers 327 Following PhD Student at Carnegie Mellon University | Computer Vision and Language | Generative AI
Sparsh Tewatia @spteotia
72 Followers 3K Following Next token prediction enjoyer Currently doing MS in AI
Bhavika Devnani @BhavikaDevnani1
10 Followers 292 Following ML PhD Student @ Georgia Tech | AI @ Apple
Gabriel Sarch @GabrielSarch
681 Followers 687 Following Ph.D. Candidate at Carnegie Mellon University @mldcmu @cmuneurosci. Prev. @yutori_ai @MSFTResearch. Incoming postdoc @PrincetonPLI.
Zhaoyang Wang @zhaoyangwang_
774 Followers 8K Following CS PhD student at the University of Birmingham. Research interests: Automated Machine Learning (Bayesian optimization), Reinforcement Learning.
Gabriel Rodriguez @grod__17
64 Followers 300 Following MSR Student @CMU_Robotics, Prev. Intern @MITLL, Dual BS @EmbryRiddle, Co-Op @TXTSystems. Robotics & Control.
Siva Reddy @sivareddyg
6K Followers 1K Following Assistant Professor @Mila_Quebec @McGillU @ServiceNowRSRCH; Postdoc @StanfordNLP; PhD @EdinburghNLP; Natural Language Processor #NLProc
Ananya Bal @Bal_Ananya
10 Followers 93 Following
Anushka CVPR 25✈️ @_anushkaagarwal
724 Followers 5K Following Research Engineer Intern @ Flawless|Machine learning Engineer @Neuralgarage| Research Intern @Airlab CMU| 3D VisionTrends for United States
You might like
