Hitesh Patel @Hitesh_LPatel
Latest Research Paper Tweets, GenAI Tech lead @Oracle , ML Researcher @NYU United States Joined February 2024-
Tweets164
-
Followers182
-
Following891
-
Likes207
SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining This paper proposes SyncMask, a method to address the disparity between image and text information in fashion datasets for VLMs. It generates masks to synchronize attention between image…
DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering This paper presents DOCMASTER, a platform for annotating PDF documents, model training, and inference, focused on document question-answering. It addresses challenges in working…
WavLLM: Towards Robust and Adaptive Speech Large Language Model This paper introduces WavLLM, a speech LLM with dual encoders and prompt-aware weight adaptation, trained via a curriculum learning approach. It achieves state-of-the-art performance across various speech tasks,…
ARAGOG: Advanced RAG Output Grading The paper addresses the gap in extensive experimental comparisons of RAG methods. The study finds that Hypothetical Document Embedding (HyDE) and LLM reranking enhance retrieval precision significantly, while other methods show mixed results.…
Stable Code The paper introduces Stable Code, a code language model for code completion, reasoning, math, and other software engineering tasks. It includes a variant called stable code instruct for natural language interaction. The report details data, training, and evaluations,…
FABLES: Evaluating faithfulness and content selection in book-length summarization This paper evaluates faithfulness and content selection in summaries generated by LLMs for fictional books. They create a dataset called FABLES, comprising annotations on over 3,000 claims in…
Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models The paper addresses the challenge of balancing safety and helpfulness in LLMs to enhance user experience. It proposes methods for controlling both attributes without additional human…
BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text The paper introduces BioMedLM, a smaller GPT-style model trained exclusively on PubMed data. Despite its smaller size, it achieves competitive results in biomedical question-answering tasks, outperforming…
LONG-FORM FACTUALITY IN LARGE LANGUAGE MODELS The paper introduces SAFE, to evaluate long-form actuality using LLM by breaking down responses into individual facts and verifying them using search queries. It introduces an extended F1 score as a metric for long-form actuality.…
Sorry, Come Again? Prompting – Enhancing Comprehension and Diminishing Hallucination with [PAUSE] -injected Optimal Paraphrasing The paper investigates the impact of formality, readability, and concreteness on hallucination for 21 LLMs. It introduces SCA, an optimal…
MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering The paper introduces MFORT-QA, a method for Table QA using LLMs. It combines few-shot learning to retrieve relevant tables and contexts, and CoT prompting to decompose complex questions. RAG enhances the process by…
Fine-Tuning Language Models with Reward Learning on Policy The paper proposes Reward Learning on Policy (RLP), an unsupervised framework to refine reward models using policy samples, addressing off-distribution issues in RLHF. It utilizes multi-view learning for robust…
BP4ER: Bootstrap Prompting for Explicit Reasoning in Medical Dialogue Generation The paper introduces BP4ER, a method for medical dialogue generation that explicitly models multi-step reasoning processes without relying on extensive entity annotation. It employs least-to-most…
Gecko: Versatile Text Embeddings Distilled from Large Language Models The paper introduces Gecko, a compact text embedding model that achieves strong retrieval performance by distilling knowledge from LLMs. It utilizes a two-step distillation process, generating synthetic paired…
Jamba: A Hybrid Transformer-Mamba Language Model The paper introduces Jamba, a hybrid large language model combining Transformer and Mamba layers using a MoE architecture. Jamba achieves state-of-the-art performance on language model benchmarks and long-context evaluations…
ReALM: Reference Resolution As Language Modeling The paper explores using large language models (LLMs) for reference resolution, including non-conversational entities like on-screen elements. It demonstrates significant improvements over existing systems, achieving comparable…
Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference This paper explores the energy-efficient serving of LLMs in data centers, balancing performance with energy consumption. It examines various factors affecting energy usage, latency, and…
ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models This paper introduces ELITR-Bench, a new benchmark for evaluating long-context LLMs in a practical meeting assistant scenario. It addresses challenges posed by noisy and oral data from transcripts,…
ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search The paper introduces ProCQA, a large-scale programming question-answering dataset from Stackoverflow, facilitating naturally structured mixed-modal QA pairs. It proposes a…
Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows The paper introduces Language Rectified Flow as an alternative to diffusion language models for controlling sentence attributes and structure. LF utilizes neural ordinary differential…
Genevieve @genevie27359749
344 Followers 3K FollowingTough @Tough388518
0 Followers 148 FollowingDeepBrain AI @DeepBrain_ai
6K Followers 5K Following Deepbrain AI services AI technologies such as video and speech synthesis, live chatbots, and more required to create AI Humans. https://t.co/l6BCYy0n8lSigridBurke @Zfl15HYx1r9847q
0 Followers 124 FollowingCamille Simoes @CamilleSim91263
79 Followers 5K FollowingMeryl Linzey @MerLinzey
74 Followers 5K FollowingSusana Marca @susa_marca
76 Followers 5K FollowingSena Kohnen @KohnenKohn
53 Followers 5K FollowingDawn @dawn_wagner_
848 Followers 3K FollowingZara-rose Fleer @FleerZara23542
78 Followers 5K FollowingLexi-rose Uscio @lexi_usc
54 Followers 5K FollowingGenerative AI @generativeaihub
7K Followers 6K Following Inspired by Algorithms, Powered by Imagination: Unleashing the Potential of Generative AI. #GenerativeAI #deeplearning #AI #MachineLearningIsabel Camera @isab_cam
40 Followers 5K FollowingParshin Shojaee @ParshinShojaee
1K Followers 950 Following Ph.D. Student @VT_CS | AI for Math, Code, ReasoningSu Nedd @SuNedd67595
40 Followers 5K FollowingRibbit @origugua
252 Followers 2K Following @MyrrhaLabs | Prev. @Mirana ,@realResearchDAO; FINM @ourANU #DYORLemma @vcdealflow
4K Followers 1K Following Venture Capital & Media Deal Flow to your Inbox: https://t.co/2TgxMFSR7u Connecting Startups with Investors: DM us if you are RaisingJana Grunin @GruninJana39249
65 Followers 5K FollowingMeredith Mulhall @MerediMulhall
33 Followers 5K FollowingClaudine Kanis @ClaudineKa84525
34 Followers 5K Following 21 · Michigan · Claudine😝 · TOP1.95% onlyfansEve @hagitam39622078
9 Followers 765 FollowingLondon Singh @london_sin99108
112 Followers 3K FollowingIvana Chastant @ChastaIva
38 Followers 5K Followingps9opg8apl5enhn @3c9q5sf8y1561
13 Followers 1K Following We first transfer USDT to you TRC20, you return 90% to BEP20, you get 10% , 2K per day Our co hv a large amt of USDT need to from TRC20 convert to BEP20 networkAliza Canez @AlizaCanez3809
71 Followers 5K FollowingMisha Davis @Misha_Daviess
162 Followers 2K Following Washington State. lawyer. Diving and golf enthusiastsLu Xia @Lu_ICFO_Xia
153 Followers 245 Following Postdoc @MSCActions, 🤝Prof. F. Pelayo @garciadearquer, @ICFOnians, Spain; PhD from @RWTH / @fz_Juelich, Germany. Interests: H2O, CO2, NO3- electrolyzers.Francina Toelke @FrancinaTo91460
83 Followers 5K FollowingKailey Noggles @KaileyNogg15814
83 Followers 5K FollowingMarquita Livley @MarquitaL81920
90 Followers 5K FollowingAmy @lawson_amy74
114 Followers 3K FollowingMila Lyford @mil_lyfo
69 Followers 5K FollowingAli Behrouz @behrouz_ali
914 Followers 844 Following Ph.D. Student @cornell, interested in machine learning.Darek Kłeczek @dk21
3K Followers 2K Following Machine Learning, Kaggle and occasional pictures from Poland. Growth MLE at Weights & Biases.Minseon Kim @kim__minseon
297 Followers 356 Following Ph.D student, Graduate school of AI @KAIST | Adversarial robustness, Self supervised learning, Robustness in Diffusion model |Craig Smyth @CSmyth66587
20 Followers 80 FollowingAudie Copas @AudieAudi
79 Followers 5K FollowingParshin Shojaee @ParshinShojaee
1K Followers 950 Following Ph.D. Student @VT_CS | AI for Math, Code, ReasoningRibbit @origugua
252 Followers 2K Following @MyrrhaLabs | Prev. @Mirana ,@realResearchDAO; FINM @ourANU #DYORRoss Taylor @rosstaylor90
6K Followers 876 Following Something new 🥷. Previously: @paperswithcode, reasoning lead @metaai, Galactica LLM lead, Atlas ML (acq by Meta)Premashis Manna @MannaPremashis
656 Followers 522 Following Incoming Assistant Professor @OhioState, interested in single-molecule, directed evolution 🧬 , photosynthesis 🌿☀️.#CVPR2024 @CVPR
41K Followers 329 Following Official account for IEEE/CVF Conference on Computer Vision & Pattern Recognition. #CVPR2024 🇺🇸 hosts @CSProfKGD @abby621 @jbhuang0604 @hi_ice_boy @BoqingGoInternational Confere.. @3DVconf
5K Followers 45 Following Since 2013, 3DV has provided a premier platform for disseminating research results covering a broad variety of topics in computer vision and graphics.Alexander Wan @alexwan55
473 Followers 944 Following CS at Berkeley; @BerkeleyML @BerkeleyNLP; NLP researchSholto Douglas @_sholtodouglas
15K Followers 858 Following Scaling Gemini @Deepmind - working towards intelligence too cheap to meterTalkRL Podcast @TalkRLPodcast
3K Followers 58 Following TalkRL Podcast is All Reinforcement Learning, All the Time. Follow for interviews with brilliant folks from across the world of RL. Host @robinc. DMs open.Ali Behrouz @behrouz_ali
914 Followers 844 Following Ph.D. Student @cornell, interested in machine learning.Brendan Elliott @brendanelliott_
927 Followers 875 Following design @meta, mixing @atleeco, brendo.ethLucy Li @lucy3_li
4K Followers 2K Following @UCBerkeley PhD student + @allen_ai. Human-centered #NLProc, computational social science, AI fairness. she/her. https://t.co/rtSSUhWQnLMeg Young @megyoung0
3K Followers 1K Following For public power over surveillance and AI. Researcher @datasociety; DIY @critplat Fmr. @dlicornelltech @techpolicylabJames M. Zumel Dumlao @jmzumeldumlao
360 Followers 682 Following PhD student @umsi :: @IDEC_usfca alum :: Knowledge/Cultural Production, Science of Science :: he/him/hisSeth Lazar @sethlazar
7K Followers 2K Following ANU Philosophy Prof working on normative philosophy of computing. This place is bad. Find my work at linktree belowDarek Kłeczek @dk21
3K Followers 2K Following Machine Learning, Kaggle and occasional pictures from Poland. Growth MLE at Weights & Biases.Minseon Kim @kim__minseon
297 Followers 356 Following Ph.D student, Graduate school of AI @KAIST | Adversarial robustness, Self supervised learning, Robustness in Diffusion model |Div Garg @DivGarg9
17K Followers 99 Following Working on breaking things @MultiON_AI | RL + AI researcher | Adjunct Lecturer @Stanford CS | worked @nvidia Research, @apple SPG, @GoogleAI, @UberATGmaggie_albrecht @maggie_albrecht
2K Followers 5K Following Seriously, we have met before. All opinions are my own.Ryan Lowe @ryan_t_lowe
5K Followers 358 Following what is the place from which we are creating? ❤️✨🤠❤️Yasuo Yamasaki @yasuoyamasaki
270 Followers 1K FollowingRC Trustworthy Data S.. @RCTrustworthy
188 Followers 138 Following @[email protected] Human-centered research, #trustworthy data analytics in safety-critical applications, explainable #ML, #privacy-aware algorithms.Alexander Marx @dr_amarx
407 Followers 247 Following Postdoc @ETH | Prev. Postdoc Fellow @ETH_AI_Center, PhD student @CISPA and MPI for Informatics | Causality | Representation Learning | Machine LearningHongyang Zhang @hongyangzh
2K Followers 241 Following Assistant Professor at @UWCheritonCS @VectorInst Lead the SafeAI Lab CMU ML PhD @SCSatCMU Playing with Foundation ModelsMihir Patel @mvpatel2000
3K Followers 385 Following Research Engineer @MosaicML | cs, math bs/ms @StanfordNiloofar (Fatemeh) Mi.. @niloofar_mire
4K Followers 1K Following Postdoc @uwcse-@uwnlp, Ph.D. from @ucsd_cse /Privacy, ML, NLP, @winlpworkshop chair, @MSFTResearch - Semantic MachinesParastoo Abtahi 🔗h.. @parastooabtahi
5K Followers 1K Following Assistant Professor of CS @Princeton & @PrincetonHCI | Previously @RealityLabs & @MSFTResearch | PhD @Stanford | HCI, AR/VR, Spatial ComputingNorman Müller @Normanisation
548 Followers 207 Following AI researcher at Meta, 3D generative AI, former PhD Student @ TU Munich w/ Matthias NießnerChuang Gan @gan_chuang
4K Followers 456 Following Faculty Member at UMass Amherst; Principal researcher at MIT-IBM Watson AI Lab; Homepage: https://t.co/oXP6pqXCpoParrotGPT @parrotgpt
263 Followers 18 Following So knowledgeable about AI that people call us 'AInstein'Dmitry Alimov @dmitryalimov
6K Followers 7K Following Tech VC and entrepreneur. Curious. Investing and building in AI. Built companies in media and tech. Founder @frontiervc. Learned things @harvard, @stanfordAlan Karthikesalingam @alan_karthi
5K Followers 2K Following Health AI @GoogleHealth @GoogleAI @GoogleDeepMind including ✨Med-Gemini, AMIE, MedPaLM, MedPaLM-2, MedPaLM-M, CoDoC Hon Lecturer Vasc Surgery @ImperialVascNOELREPORTS 🇪🇺 .. @NOELreports
431K Followers 355 Following Media platform covering global conflict zones. Focus on the Russian-Ukrainian war. If you'd like to support our voluntary work: https://t.co/PmM2wwDA1Y.Cong Lu @cong_ml
638 Followers 867 Following Postdoctoral Research Fellow @UBC_CS in open-endedness, generative models, and deep RL. Prev: PhD @UniofOxford, Research Intern @Waymo, @MSFTResearch!Botos Csabi @csaba_botos
181 Followers 238 Following PhD candidate in Torr Vision Group, University of Oxford https://t.co/WzU6h3qhagGianfranco @gianfree97
34 Followers 206 Following Tech enthusiast with a focus on #ML and #NLP. When I'm not tinkering with code, you can find me in the pool, where I enjoy swimming and pushing my limitsfly51fly @fly51fly
5K Followers 2K Following BUPT prof | Sharing latest AI papers & insights | Join me in embracing the AI revolution! #MachineLearning #AI #InnovationXenova @xenovacom
6K Followers 284 Following Bringing the power of machine learning to the web. Currently working on Transformers.js (@huggingface 🤗)Ashwarya Maratha @AshwaryaMaratha
290 Followers 290 Following Upcoming Intern @ https://t.co/HngTQ54izb , Research @Macquarie_UniYan Yao @YanYao2
2K Followers 584 Following Cullen Professor @UHouston; Alumni of Stanford and UCLA; Father; Views my ownDirk H. Trauner @DirkTrauner
16K Followers 12K Following Penn Integrates Knowledge Professor, Natural Product Aficionado, Photopharmacologist, Fox Terrierist, and Unfulfilled Architect. #firstgenGlobal Topics @Globaltalks12
10K Followers 9K Following Trends, Information, Random thoughts and funfacts, Polls, Views and news about Global topics. Retweets are not endorsement 🇺🇲🇩🇪🇰🇷🇨🇭🇨🇿🇨🇦🇬🇧Manuel Gomez-Rodrigue.. @autreche
1K Followers 136 Following Human-centric machine learning at the Max Planck Institute for Software Systems.David Jurgens @david__jurgens
2K Followers 558 Following Associate Professor at @UMSI and @UMichCSE working in computational social science and NLP. PI of the Blablablab https://t.co/pt1UFJuBiUXiao Ma @infoxiao
4K Followers 3K Following research @googleai on responsible #ai. llm safety & reasoning. prev: @cornell_tech, @facebook @airbnb. views are mine. sh-i-ow. dr. 👩🎓SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining This paper proposes SyncMask, a method to address the disparity between image and text information in fashion datasets for VLMs. It generates masks to synchronize attention between image…
DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering This paper presents DOCMASTER, a platform for annotating PDF documents, model training, and inference, focused on document question-answering. It addresses challenges in working…
WavLLM: Towards Robust and Adaptive Speech Large Language Model This paper introduces WavLLM, a speech LLM with dual encoders and prompt-aware weight adaptation, trained via a curriculum learning approach. It achieves state-of-the-art performance across various speech tasks,…
ARAGOG: Advanced RAG Output Grading The paper addresses the gap in extensive experimental comparisons of RAG methods. The study finds that Hypothetical Document Embedding (HyDE) and LLM reranking enhance retrieval precision significantly, while other methods show mixed results.…
FABLES: Evaluating faithfulness and content selection in book-length summarization This paper evaluates faithfulness and content selection in summaries generated by LLMs for fictional books. They create a dataset called FABLES, comprising annotations on over 3,000 claims in…
Stable Code The paper introduces Stable Code, a code language model for code completion, reasoning, math, and other software engineering tasks. It includes a variant called stable code instruct for natural language interaction. The report details data, training, and evaluations,…
Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models The paper addresses the challenge of balancing safety and helpfulness in LLMs to enhance user experience. It proposes methods for controlling both attributes without additional human…
BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text The paper introduces BioMedLM, a smaller GPT-style model trained exclusively on PubMed data. Despite its smaller size, it achieves competitive results in biomedical question-answering tasks, outperforming…
LONG-FORM FACTUALITY IN LARGE LANGUAGE MODELS The paper introduces SAFE, to evaluate long-form actuality using LLM by breaking down responses into individual facts and verifying them using search queries. It introduces an extended F1 score as a metric for long-form actuality.…
BP4ER: Bootstrap Prompting for Explicit Reasoning in Medical Dialogue Generation The paper introduces BP4ER, a method for medical dialogue generation that explicitly models multi-step reasoning processes without relying on extensive entity annotation. It employs least-to-most…
Fine-Tuning Language Models with Reward Learning on Policy The paper proposes Reward Learning on Policy (RLP), an unsupervised framework to refine reward models using policy samples, addressing off-distribution issues in RLHF. It utilizes multi-view learning for robust…
MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering The paper introduces MFORT-QA, a method for Table QA using LLMs. It combines few-shot learning to retrieve relevant tables and contexts, and CoT prompting to decompose complex questions. RAG enhances the process by…
Sorry, Come Again? Prompting – Enhancing Comprehension and Diminishing Hallucination with [PAUSE] -injected Optimal Paraphrasing The paper investigates the impact of formality, readability, and concreteness on hallucination for 21 LLMs. It introduces SCA, an optimal…
Gecko: Versatile Text Embeddings Distilled from Large Language Models The paper introduces Gecko, a compact text embedding model that achieves strong retrieval performance by distilling knowledge from LLMs. It utilizes a two-step distillation process, generating synthetic paired…
Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference This paper explores the energy-efficient serving of LLMs in data centers, balancing performance with energy consumption. It examines various factors affecting energy usage, latency, and…
ReALM: Reference Resolution As Language Modeling The paper explores using large language models (LLMs) for reference resolution, including non-conversational entities like on-screen elements. It demonstrates significant improvements over existing systems, achieving comparable…
Jamba: A Hybrid Transformer-Mamba Language Model The paper introduces Jamba, a hybrid large language model combining Transformer and Mamba layers using a MoE architecture. Jamba achieves state-of-the-art performance on language model benchmarks and long-context evaluations…
ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models This paper introduces ELITR-Bench, a new benchmark for evaluating long-context LLMs in a practical meeting assistant scenario. It addresses challenges posed by noisy and oral data from transcripts,…
Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows The paper introduces Language Rectified Flow as an alternative to diffusion language models for controlling sentence attributes and structure. LF utilizes neural ordinary differential…
ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search The paper introduces ProCQA, a large-scale programming question-answering dataset from Stackoverflow, facilitating naturally structured mixed-modal QA pairs. It proposes a…