LP Morency @lpmorency
Associate Professor at CMU studying multimodal and Social AI. Ice hockey goalie. multicomp.cs.cmu.edu Pittsburgh, PA Joined April 2015-
Tweets72
-
Followers1K
-
Following21
-
Likes63
Curious about socially-intelligent AI? Check out our paper on underlying technical challenges, open questions, and opportunities to advance social intelligence in AI agents: Work w/ @lpmorency, @pliang279 📰Paper: arxiv.org/abs/2404.11023 💻Repo: github.com/l-mathur/socia… 🧵1/9
Agreed! Multimodal ML is not just a sub-area of various modalities. @lpmorency is one of the researchers who has believed in multimodal for years. Anyone interested in multimodal ML should check out his course on this topic, co-taught with @pliang279! cmu-multicomp-lab.github.io/mmml-course/fa…
Agreed! Multimodal ML is not just a sub-area of various modalities. @lpmorency is one of the researchers who has believed in multimodal for years. Anyone interested in multimodal ML should check out his course on this topic, co-taught with @pliang279! cmu-multicomp-lab.github.io/mmml-course/fa…
Excited to attend #NeurIPS2023 this week! Find me to chat about the foundations of multimodal machine learning, multisensory foundation models, interactive multimodal agents, and their applications. I'm also on the academic job market, you can find my statements on my website:…
Despite the successes of contrastive learning (eg CLIP), they have a fundamental limitation - it can only capture *shared* info between modalities, and ignores *unique* info To fix it, a thread for our #NeurIPS2023 paper w Zihao Martin @james_y_zou @lpmorency @rsalakhu:
Check out our #EMNLP2023 paper on Difference-Masking, an approach for choosing what to mask during continued pretraining!
Check out our #EMNLP2023 paper on Difference-Masking, an approach for choosing what to mask during continued pretraining!
If your downstream task data is quite different from your pretraining data, make sure you check out our new approach *Difference-Masking* at #EMNLP2023 findings. Excellent results on classifying citation networks, chemistry text, social videos, TV shows etc. see thread below:
If your downstream task data is quite different from your pretraining data, make sure you check out our new approach *Difference-Masking* at #EMNLP2023 findings. Excellent results on classifying citation networks, chemistry text, social videos, TV shows etc. see thread below:
In continued pretraining, how can we choose what to mask when the pretraining domain differs from the target domain? In our #EMNLP2023 paper, we propose Difference-Masking to address this problem and boost downstream task performance! Paper: arxiv.org/abs/2305.14577
Multimodal AI studies the info in each modality & how it relates or combines with other modalities. This past year, we've been working towards a **foundation** for multimodal AI: I'm excited to share our progress at #NeurIPS2023 & #ICMI2023: arxiv.org/abs/2302.12247 see long 🧵:
led by @_dongwonlee, with @chahuja Sanika Natu @lpmorency @LTIatCMU @mldcmu code and dataset publicly available paper: openaccess.thecvf.com/content/ICCV20… code: github.com/dondongwon/LPM…
At ICCV, we'll be presenting our work on a new dataset/benchmark for evaluating vision-language models for educational content! This is one of the first and few works to enable AI-based educational tutors. openaccess.thecvf.com/content/ICCV20…
Adapting Generative models for co-speech gestures to new speakers, but without forgetting the style of previous speakers? Let’s make it more challenging by only having 2-10 minutes of data for the new speakers. Website: chahuja.com/cdiffgan Find us at #ICCV2023 1/n
The Artificial Social Intelligence Workshop and Inaugural Social-IQ Challenge are happening soon @ICCVConference in Paris next week! 🇫🇷 This event will start at 9:15 am on Monday, October 2 in Room E01 (hybrid option available). Full schedule here: sites.google.com/view/asi-iccv-…
The Artificial Social Intelligence Workshop and Inaugural Social-IQ Challenge are happening soon @ICCVConference in Paris next week! 🇫🇷 This event will start at 9:15 am on Monday, October 2 in Room E01 (hybrid option available). Full schedule here: sites.google.com/view/asi-iccv-…
🔍 Louis-Philippe Morency @lpmorency breaks it down: 1️⃣ Modalities are often linked—statistically or semantically 2️⃣ Statistical links are bottom-up; Semantic links are top-down 3️⃣ Relationships can be complex—think dependencies 🧠 From a captivating talk - time to rethink how we…
Happening in ~2 hours at #ICML2023 930am @ exhibit hall 2 Also happy to chat about - understanding multimodal interactions and modeling them - models for many diverse modalities esp beyond image+text - Applications in health, robots, education, social intelligence & more DM me!
Happening in ~2 hours at #ICML2023 930am @ exhibit hall 2 Also happy to chat about - understanding multimodal interactions and modeling them - models for many diverse modalities esp beyond image+text - Applications in health, robots, education, social intelligence & more DM me!
📣 Final deadline for both workshop and challenge submissions has been extended to July 24 AoE!
If you're attending #ICML2023 don't miss our tutorial on multimodal ML (w @lpmorency) Content: 1. Three key principles of modality heterogeneity, connections & interactions 2. Six technical challenges 3. Open research questions Monday July 24, 930 am Hawaii time, Exhibit Hall 2
📣 July 21 is the paper deadline for the Artificial Social Intelligence Workshop and Social-IQ Challenge at ICCV 2023! Workshop and challenge papers can be submitted through the same CMT link. We welcome submissions 🎉 and more info is here: sites.google.com/view/asi-iccv-…
📣 July 21 is the paper deadline for the Artificial Social Intelligence Workshop and Social-IQ Challenge at ICCV 2023! Workshop and challenge papers can be submitted through the same CMT link. We welcome submissions 🎉 and more info is here: sites.google.com/view/asi-iccv-…
(ACL 2023) Can you control language model generation with only 8 samples? Check out our paper on few-shot human-in-the-loop text generation control: arxiv.org/abs/2211.05750. ACL Findings Spotlight: Mon 7-9pm ET (Metropolitan Centre) RepL4NLP Workshop: Thu 11-12pm ET (Harbour B)
If you are #ACL2023, learn about a simple data intervention approach to reduce gender bias in language models at my poster presentation on Tuesday at 11:00 AM EDT! Thanks to my co-authors and mentors @pliang279 and @lpmorency for their guidance. #NLP #MachineLearning
I'm on the faculty market in fall 2023! I work on foundations of multimodal ML applied to NLP, socially intelligent AI & health. My research & teaching cs.cmu.edu/~pliang/ If I could be a good fit for your department, I'd love to chat at #ACL2023NLP & #ICML2023 DM/email me!
Graham Neubig @gneubig
31K Followers 588 Following Associate professor at CMU, studying natural language processing and machine learning.Jacob Andreas @jacobandreas
14K Followers 958 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJwShruti Rijhwani @shrutirij
4K Followers 499 Following * Research Scientist @GoogleDeepMind * #NLProc research * PhD from @LTIatCMU * Amateur woodworker, scuba diver, foosball playerAkari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳Kyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Shaily @shaily99
5K Followers 2K Following PhD @LTIatCMU Prev: @GoogleAI @MSFTResearch. Working on ethics and evaluation in #NLProc. Usually ranting, often about research & DEI. 📚 @readsndrantsYonatan Bisk @ybisk
3K Followers 883 Following Assistant Professor (he/him) @LTIatCMU/@SCSatCMU - embodied #NLProc Stealing ideas from @_Hao_Zhu @viddivj @_Yingshan @SoYeonTiffMin, @FernJared @abitha___Gabriel Ilharco @gabriel_ilharco
4K Followers 1K Following Building cool things @xAI. Prev. PhD at UW, Google AILanguage Technologies.. @LTIatCMU
9K Followers 233 Following The Language Technologies Institute in Carnegie Mellon University's @SCSatCMUGreg Durrett @gregd_nlp
6K Followers 753 Following CS professor at UT Austin. I do NLP most of the time. he/himDiyi Yang @Diyi_Yang
14K Followers 2K Following Assistant Professor @Stanford CS @StanfordNLP @StanfordAILab. Formerly @GeorgiaTech. Computational Social Science & NLPXin Eric Wang @xwang_lk
8K Followers 1K Following Multimodal and Embodied AI Researcher / Professor @UCSC. Director of https://t.co/Y4swOBag21. AI for Humanity in the long run. he/himDaniel Fried @dan_fried
3K Followers 798 Following Assistant prof. @LTIatCMU @SCSatCMU, working on NLP: language interfaces, applied pragmatics, language-to-code, grounding. 🐘: @[email protected]Saujas Vaduguru @saujasv
401 Followers 542 Following PhD student @LTIatCMU | Previous: Student @iiit_hyderabad, Intern @ChandarLab @Mila_Quebec | he/him/hisAbdulrahman Tabaza @embed_dim
4 Followers 870 Following enjoyer of various vector spaces, encoders and modalitiesOllie Liu @olliezliu
149 Followers 547 Following 👨🍳 research @MSFTResearch; phd student in ml/nlp @CSatUSC. 🎓 alum @mldcmu. 🧐 multi-modal foundation models, decision making, ai4science.Yubin Kim @ybkim95_ai
28 Followers 158 Following Graduate student @MIT conducting research on Healthcare AI and Wearable Sensors with Personal Robots.Xinyi Zhou @XinyiZhouXZ
338 Followers 331 Following postdoc @uwcse | AI, social computing, m/disinformationAanuoluwapo Abidoye @MedAlresearcher
84 Followers 2K Following Nascent Datascientist|MedAI Researcher # data science, # machine learning, # deep learning, # computational neuroscience(neural coding and brain computing)Ella Minzhi Li @EllaMinzhiLi
145 Followers 105 Following CS PhD student at NUS @wing_nus 🇸🇬, incoming visiting PhD at Stanford @stanfordnlp🌲, NLP researcher📒kai hung 🦉🏕️ @kaimhung7
57 Followers 521 Following CS undergrad @RiceUniversity. Prev @berkeley_ai @nyu_courant. Interested in statistical ml, optimal transport, graphs, and healthcare.Ashutosh Mehra @ashutoshmehra
2K Followers 5K Following Senior Principal Scientist at Adobe. Working on Acrobat AI Assistant, LLMs, and document ML.Xin Zhou @THELMDOFZHOUXIN
33 Followers 537 Following A third year undergraduate student in Huazhong University of Science and Technology (HUST) | As I have always been.Markus Rauhalahti, Ph.. @MRauhalahti
855 Followers 5K Following Independent researcher: molecular design/nanotech, human-AI collab, informetrics, DIY-scihw. Prev compchem/biophys/info phd&postdoc @helsinkiuniWentao Li @waterlee23
96 Followers 1K FollowingMohamed Abdo @mo_568_mo
315 Followers 1K Following PhD student.#AI 🤖 researcher and engineer 👨💻 . It is love that makes the impossible possible.Shota Natenadze @shotanat
189 Followers 1K Following I'm Senior Data Scientist at @EpamSystems, passionate about machine learning, LLMs, and statistics.Shrikar @Shrikarhaha
157 Followers 2K Following Currently: Research @iiscbangalore Building: Explainable AI systems in Healthcare Interests: Startups, TechForGood, Product Loves: Physics,Poems,Football&FoodJHB @ku21fan
137 Followers 343 Following Win-winな関係を目指したい. Korean. I usually use Japanese on Twitter, not to forget the Japanese language. INTP/INTJ. NLP to OCR to MultimodalCarlos Rodríguez-Par.. @Crp94
918 Followers 3K Following AI & Climate @polimi @EIEEorg Before: @EdinburghUni @UWaterloo @uc3m @SeddiTech @urjc Don't believe the hype 🧠👨🏻💻🪐🎸🚴♂️🏀☕📚🔻Victor Reyna @VicReynaG
280 Followers 2K Following #Firstgen. Data Scientist • Interests: DS | ML | AI for Social Good • 🇵🇪 Volunteer @Neuromatch / @_LXAISiddarth1 @Siddarth_chess
143 Followers 2K Following 25. Scientist making robots smarter! Chess player? Maybe.Madhu Korada @manoj_korada
39 Followers 785 Following MRSD Student @CMU_Robotics | Ex-Research Engineer @roboticssystemzneo @neobyd
52 Followers 391 FollowingChirag Desai @realcid1
509 Followers 3K Following Pr Statistical Programmer.#SAS #Data Analyst #ML #DL #DataScience #Kaggle #ML developer #PyTorch #TensorFlow #finance #stocks #investing #macroeconomyAlok Kumar @alok_kumar00
51 Followers 2K Following Less opinionated, Read, listen| Deep learning|Computer Vision|Spaceadddddd @anandnew38
333 Followers 5K FollowingAbhimanyu Talwar @abhimanyu7c2
209 Followers 2K Following NLP at @TheLevelAI. Creator of QuickFinAI, natural language search for finance. Previously: Debt investor at @BlackRocklong @copermaxim
63 Followers 2K FollowingAnna Ciaunica @annaci.. @AnnaCiaunica
12K Followers 10K Following Philosopher/Cognitive scientist |PI working on Self-Consciousness, Embodiment & Social Interactions in Humans & Artificial Agents | RT not endorsementAkshay Goindani @AkshayGoindani1
19 Followers 213 FollowingNishat Anjum Bristy @BristyNishat
35 Followers 301 Following Graduate student @CMU-Pitt Joint Computational Biology Program (CPCB)Ruibin Yuan @abc43992899
142 Followers 210 Following ML PhD Student @HKUST, Music Tech MS @CarnegieMellon. Co-Founder of Multimodal Art Projection Community (MAP)Ying Shen @YingShen_ys
111 Followers 100 FollowingJiayi Xin @RainaXin
18 Followers 69 Following HKU '24 BASc(AppliedAI) | Laidlaw Scholar | Work hard, play hard :)Eshaan Tanwar @Eshaant2000
15 Followers 239 FollowingArif Ahmad @arif_ahmad_py
304 Followers 7K Following All things AI, Computer Science and Circuits! Prev. @GoogleAIIbrahim Ahmad @Ibrahim63433664
85 Followers 3K FollowingMatthew Yang @batthew_
2 Followers 31 Followingvagrog50 @vagsanrog
9 Followers 70 FollowingShubhashis Roy Dipta @iamdipta007
253 Followers 1K Following PhD @umbc || Multimodal (NLP + CV) || 🏠 https://t.co/XFDVDULgwS || 📝 https://t.co/UaVN46IIe4 || ✍️ https://t.co/PxOoQefIDdChunLin Ren @ChunLin_R
6 Followers 23 FollowingAI Overlords @OverlordsAi
15 Followers 635 Following Just curating a bunch of AI/ML accounts for my own use.Mihaly Hanics @HanicsResearch
52 Followers 318 Following @CEU Data Science MSc student, interested in ML, Discrete maths, Graph theory/networks, anything theoretical. Research assistant, developer. BSc Electrical eng.Kevin Joo @cokecoda
73 Followers 190 Following Research Associate @ CMU RI | MS CS '23 @ UMD CS | #Multimodality #AffectiveComputing #HumanCenteredComputing #ComputerVision #MachineLearningWenke Huang @wenke_huang
9 Followers 196 FollowingGraham Neubig @gneubig
31K Followers 588 Following Associate professor at CMU, studying natural language processing and machine learning.Jacob Andreas @jacobandreas
14K Followers 958 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJwKyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Yonatan Bisk @ybisk
3K Followers 883 Following Assistant Professor (he/him) @LTIatCMU/@SCSatCMU - embodied #NLProc Stealing ideas from @_Hao_Zhu @viddivj @_Yingshan @SoYeonTiffMin, @FernJared @abitha___Language Technologies.. @LTIatCMU
9K Followers 233 Following The Language Technologies Institute in Carnegie Mellon University's @SCSatCMUDiyi Yang @Diyi_Yang
14K Followers 2K Following Assistant Professor @Stanford CS @StanfordNLP @StanfordAILab. Formerly @GeorgiaTech. Computational Social Science & NLPDaniel Fried @dan_fried
3K Followers 798 Following Assistant prof. @LTIatCMU @SCSatCMU, working on NLP: language interfaces, applied pragmatics, language-to-code, grounding. 🐘: @[email protected]Maarten Sap (he/him) @MaartenSap
5K Followers 645 Following Working on #NLProc for social good. Currently at @LTIatCMU, previously at @UWNLP, @MSFTResearch, and @allen_ai. 🏳🌈Leena Mathur @lmathur_
628 Followers 915 Following PhD student @SCSatCMU @LTIatCMU. I work on multimodal AI, embodied AI, & human-machine interaction w/ @lpmorency. prev @USC, @Caltech, @EPFLDong Won (Don) Lee @_dongwonlee
86 Followers 133 Following grad student at Personal Robots Group @MIT advised by @cynthiabreazeal, @lpmorency working on multimodal social agents. MS/BS in machine learning @mldcmuCMU School of Compute.. @SCSatCMU
47K Followers 784 Following The School of Computer Science at @carnegiemellon is one of the world's premier institutions for computer science research and education.Carnegie Mellon Unive.. @CarnegieMellon
78K Followers 2K Following United by curiosity and driven by passion, we reach across disciplines, forge new ground and deploy our expertise to make real change that benefits humankind.Andrej Risteski @risteski_a
3K Followers 2K Following Machine learning researcher. Assistant Professor, ML department at CMU (@mldcmu).Russ Salakhutdinov @rsalakhu
100K Followers 141 Following UPMC Professor of Computer Science at Carnegie Mellon University, ex-Director of AI research at @Apple, co-founder Perceptual Machines (acquired by Apple)David Mortensen @dmort27
2K Followers 2K Following I make colorless green GPUs sleep brriously @LTIatCMU. phonology • morphology • language change • #NLProc data resources.Rada Mihalcea @radamihalcea
9K Followers 600 Following Janice M. Jenkins Collegiate Professor of Computer Science at U. Michigan, Director @Michigan_AI Lab, Researcher #NLProc, #AI.Emma Strubell @strubell
4K Followers 936 Following assistant professor @LTIatCMU & visiting scientist @allen_ai. natural language processing and efficient ML. she/her/dad (2 dogs). 🏳️🌈. hiking and food. BLM.ACL Anthology @aclanthology
6K Followers 13 Following Host of scientistic papers for @aclmeeting and other venues in the field of Natural Language Processing Not closely monitored, so responses may be delayed.Machine Learning Dept.. @mldcmu
17K Followers 370 Following The top education and research institution in the 🌎 for #AI and #machinelearning | Research → https://t.co/jUD0hZ8SFx | Learn more ↓Chaitanya Ahuja @chahuja
328 Followers 699 Following Research Scientist @AIatMeta, PhD from @LTIatCMU @SCSatCMU ML researcher, and an avid bicyclistPaul Liang @pliang279
5K Followers 910 Following PhD student @mldcmu @SCSatCMU. Foundations of multimodal learning & applications in social AI, NLP, and healthcare with @lpmorency and @rsalakhu.Our @FDA Milestone! @deliberate_ai AI-COA™ is part of ISTAND, Breaking New Ground in AI and Mental Health! bit.ly/3S6cZjC #DigitalHealth #HealthTech #Medtech #Multimodal #AI #PharmaInnovation #ClinicalTrials #Depression #Anxiety #AIEthics #AIinHealthcare
FDA's Innovative Science and Technology Approaches for New Drugs (ISTAND) Pilot Program has accepted a submission of the first artificial intelligence-based and digital health technology for neuroscience: fda.gov/drugs/drug-saf…
EVENT: Paul Liang from CMU will present "Foundations of Multisensory #AI" in a Duke CS-ECE Colloquium on Feb. 1, 1:30-2:30 PM in LSRC D-106 with lunch at 1:15 PM. Join us! bit.ly/dukecs-ece-1fe…
Agreed! Multimodal ML is not just a sub-area of various modalities. @lpmorency is one of the researchers who has believed in multimodal for years. Anyone interested in multimodal ML should check out his course on this topic, co-taught with @pliang279! cmu-multicomp-lab.github.io/mmml-course/fa…
Five years ago, multimodal research like vision & language was considered a subarea of either computer vision or NLP. Multimodal researchers often faced skepticism about their field. Today, it is widely realized that multimodal is both now & future. #GotToHaveYourResearchBelief
Excited to attend #NeurIPS2023 this week! Find me to chat about the foundations of multimodal machine learning, multisensory foundation models, interactive multimodal agents, and their applications. I'm also on the academic job market, you can find my statements on my website:…
In multimodal contrastive learning, how can we capture task-relevant information unique to each modality beyond shared information? At #NeurIPS2023 Wed 13 Dec 5PM, Hall B1+B2 #815, we will be presenting Factorized Contrastive Learning, which addresses this problem.
Despite the successes of contrastive learning (eg CLIP), they have a fundamental limitation - it can only capture *shared* info between modalities, and ignores *unique* info To fix it, a thread for our #NeurIPS2023 paper w Zihao Martin @james_y_zou @lpmorency @rsalakhu:
Despite the successes of contrastive learning (eg CLIP), they have a fundamental limitation - it can only capture *shared* info between modalities, and ignores *unique* info To fix it, a thread for our #NeurIPS2023 paper w Zihao Martin @james_y_zou @lpmorency @rsalakhu:
Check out our #EMNLP2023 paper on Difference-Masking, an approach for choosing what to mask during continued pretraining!
In continued pretraining, how can we choose what to mask when the pretraining domain differs from the target domain? In our #EMNLP2023 paper, we propose Difference-Masking to address this problem and boost downstream task performance! Paper: arxiv.org/abs/2305.14577
If your downstream task data is quite different from your pretraining data, make sure you check out our new approach *Difference-Masking* at #EMNLP2023 findings. Excellent results on classifying citation networks, chemistry text, social videos, TV shows etc. see thread below:
In continued pretraining, how can we choose what to mask when the pretraining domain differs from the target domain? In our #EMNLP2023 paper, we propose Difference-Masking to address this problem and boost downstream task performance! Paper: arxiv.org/abs/2305.14577
In continued pretraining, how can we choose what to mask when the pretraining domain differs from the target domain? In our #EMNLP2023 paper, we propose Difference-Masking to address this problem and boost downstream task performance! Paper: arxiv.org/abs/2305.14577
Multimodal AI studies the info in each modality & how it relates or combines with other modalities. This past year, we've been working towards a **foundation** for multimodal AI: I'm excited to share our progress at #NeurIPS2023 & #ICMI2023: arxiv.org/abs/2302.12247 see long 🧵:
led by @_dongwonlee, with @chahuja Sanika Natu @lpmorency @LTIatCMU @mldcmu code and dataset publicly available paper: openaccess.thecvf.com/content/ICCV20… code: github.com/dondongwon/LPM…
🔍 Louis-Philippe Morency @lpmorency breaks it down: 1️⃣ Modalities are often linked—statistically or semantically 2️⃣ Statistical links are bottom-up; Semantic links are top-down 3️⃣ Relationships can be complex—think dependencies 🧠 From a captivating talk - time to rethink how we…
icymi @ #ICML2023, the latest multimodal ML tutorial slides are posted here: cmu-multicomp-lab.github.io/mmml-tutorial/… along with a reading list of important work covered in the tutorial, as well as slides and videos for previous versions (more application focused)
If you're attending #ICML2023 don't miss our tutorial on multimodal ML (w @lpmorency) Content: 1. Three key principles of modality heterogeneity, connections & interactions 2. Six technical challenges 3. Open research questions Monday July 24, 930 am Hawaii time, Exhibit Hall 2
Happening in ~2 hours at #ICML2023 930am @ exhibit hall 2 Also happy to chat about - understanding multimodal interactions and modeling them - models for many diverse modalities esp beyond image+text - Applications in health, robots, education, social intelligence & more DM me!
If you're attending #ICML2023 don't miss our tutorial on multimodal ML (w @lpmorency) Content: 1. Three key principles of modality heterogeneity, connections & interactions 2. Six technical challenges 3. Open research questions Monday July 24, 930 am Hawaii time, Exhibit Hall 2
📣 Final deadline for both workshop and challenge submissions has been extended to July 24 AoE!
Excited to announce the Artificial Social Intelligence Workshop and Inaugural Social-IQ Challenge, to be held together @ICCVConference! This full-day workshop will occur on October 2 in Paris 🇫🇷, with an interactive hybrid option available too. sites.google.com/view/asi-iccv-…
If you're attending #ICML2023 don't miss our tutorial on multimodal ML (w @lpmorency) Content: 1. Three key principles of modality heterogeneity, connections & interactions 2. Six technical challenges 3. Open research questions Monday July 24, 930 am Hawaii time, Exhibit Hall 2
📣 July 21 is the paper deadline for the Artificial Social Intelligence Workshop and Social-IQ Challenge at ICCV 2023! Workshop and challenge papers can be submitted through the same CMT link. We welcome submissions 🎉 and more info is here: sites.google.com/view/asi-iccv-…
Excited to announce the Artificial Social Intelligence Workshop and Inaugural Social-IQ Challenge, to be held together @ICCVConference! This full-day workshop will occur on October 2 in Paris 🇫🇷, with an interactive hybrid option available too. sites.google.com/view/asi-iccv-…
We all know that LMs can generate biased and toxic content :-( At #ACL2023NLP we propose a method for *few-shot* debiasing of trained LMs: modifying as few as *10* sentences and fine-tuning the LM results in strong reductions in bias: arxiv.org/abs/2306.04597 see full thread:
If you are #ACL2023, learn about a simple data intervention approach to reduce gender bias in language models at my poster presentation on Tuesday at 11:00 AM EDT! Thanks to my co-authors and mentors @pliang279 and @lpmorency for their guidance. #NLP #MachineLearning
At #ACL2023NLP, we'll be presenting our latest work on controlling the distribution of LM-generated text in order to mitigate bias and promote fairness & personalization. We achieve extreme few-shot control, using as few as 8 samples of human feedback! arxiv.org/abs/2211.05750
(ACL 2023) Can you control language model generation with only 8 samples? Check out our paper on few-shot human-in-the-loop text generation control: arxiv.org/abs/2211.05750. ACL Findings Spotlight: Mon 7-9pm ET (Metropolitan Centre) RepL4NLP Workshop: Thu 11-12pm ET (Harbour B)
(ACL 2023) Can you control language model generation with only 8 samples? Check out our paper on few-shot human-in-the-loop text generation control: arxiv.org/abs/2211.05750. ACL Findings Spotlight: Mon 7-9pm ET (Metropolitan Centre) RepL4NLP Workshop: Thu 11-12pm ET (Harbour B)