Leo Boytsov @srchvrs
Sr. Research Scientist @AWS Labs (ph-D @LTIatCMU) working on unnatural language processing, speaking πtorch & C++. Opinions sampled from MY OWN 100T param LM. searchivarius.org/about Pittsburgh, PA Joined November 2009-
Tweets24K
-
Followers7K
-
Following2K
-
Likes31K
In the embedding search setup, we normally combine a fast embedding model and an accurate but slow reranker model. The newly released @JinaAI_ -rerankers are small in size and almost as accurate as our base reranker. This means given a time constraint, it can scoring more…
In the embedding search setup, we normally combine a fast embedding model and an accurate but slow reranker model. The newly released @JinaAI_ -rerankers are small in size and almost as accurate as our base reranker. This means given a time constraint, it can scoring more… https://t.co/wnRe0LO6kf
New findings: We just evaluated Gemini 1.5 Pro on our recent benchmark that tests the impact of context size on reasoning performance - it is much better than 1.0 in long contexts! Though still falls behind GPT4. Also, CoT prompting now improves accuracy (unlike with 1.0). (1/4)
Let's benchmark and use more open models trained on well documented and open datasets.
In machine learning there are three key factors that affect your model performance: data, data, data.
In machine learning there are three key factors that affect your model performance: data, data, data.
This is probably the first encoder-decoder model in the recent model race.
This is probably the first encoder-decoder model in the recent model race.
@ecardenas300 @ebkauf 💯! Rockstar team leads to this x.com/bobvanluijt/st…
@ecardenas300 @ebkauf 💯! Rockstar team leads to this x.com/bobvanluijt/st…
(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingDelip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈Jo Kristian Bergum @jobergum
8K Followers 810 Following Distinguished Engineer @vespaengine. Tweets about Vespa, search, recommendation, ranking, and IR. CET. #StandWithUkraine 💙💛Sasha Rush @srush_nlp
51K Followers 464 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzKyunghyun Cho @kchonyc
60K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Akari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳Tim Dettmers @Tim_Dettmers
28K Followers 819 Following PhD Student at @UW. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.Felix Hill @FelixHill84
9K Followers 776 Following Research Scientist, Deepmind I try to think hard about everything I tweet, esp on 90s football and 80s music None of my opinions are really someone else'sLuca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai, open source science fan, @QueerInAI organizer 🤖☕️🍕they/themSam Bowman @sleepinyourhat
35K Followers 3K Following AI alignment + LLMs at NYU & Anthropic. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.Nils Reimers @Nils_Reimers
10K Followers 434 Following Director of Machine Learning @Cohere | ex-huggingface | Creator of SBERT (https://t.co/MKKOMfuQ4C)Jimmy Lin @lintool
13K Followers 842 Following I profess CS-ly at the @UWaterloo and gaze into the technological crystal ball at @Primal. I used to write code for @Twitter and slides for @Cloudera.Thomas Wolf @Thom_Wolf
67K Followers 4K Following Co-founder and CSO @HuggingFace - open-source and open-scienceKayo Yin @kayo_yin
8K Followers 555 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵yobibyte @y0b1byte
15K Followers 2K Following Kurin ViTaly, senior research scientist @IsomorphicLabs, ML PhD from @UniofOxford on RL, Multitask learning & Graphsrohan anil @_arohan_
12K Followers 2K Following Principal Engineer, @GoogleDeepMind Gemini. prev PaLM-2. Tinkering with optimization and distributed systems. opinions are my own.Sara Hooker @sarahookr
39K Followers 7K Following I lead @CohereForAI. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, @trustworthy_ml. Changing spaces where breakthroughs happen.Nathan Schneider @complingy
4K Followers 1K Following Computational Linguist and Professional Nerd at Georgetown University he/him pronouns, ALL the prepositions @[email protected] @complingy.bsky.social♻️ Leshem Choshen.. @LChoshen
3K Followers 552 Following 🥇 #NLProc researcher 🥈 Opinionatedly Summarizing #ML & #NLP papers 🥉 Good science #scientivism Let's pretrain together @IBMResearch & @MIT_CSAILOfir Press @OfirPress
9K Followers 3K Following I build tough benchmarks for LMs and then I get the LMs to solve them. Postdoc @Princeton. PhD from @nlpnoah @UW. Ex-visiting researcher @MetaAI & @MosaicML.Phillip Lindsay @EastLAPinche
50 Followers 311 FollowingVitalik Butterin @0xflashmine
2K Followers 1K Following arXiv & IACR news, skateboarding, reading. tweets reflect your views. hey guys did u know i worked for joe louisbin at consensysRyan Connor 🟪 @_RyanRConnor
711 Followers 3K Following Research @blockworksres. The most profitable arb is time horizon. e/acc since before it had a name. at ryanconnor on farcasterProgrammatic 101 @101Programmatic
2K Followers 5K Following Exploring the world of #programmatic advertising and #adtechMichael Scharf @michael_scharf
608 Followers 3K Following freelancer, interested in patterns, modeling and writing excellent software. I like to understand both sides of political debates...Richard Taubin @taubinator
232 Followers 614 Following Tech innovator & marketing guru at MPRESSED. Ex-Air Force, digital artist, family man. Passionate about making a difference. #DigitalMarketing #TechLifeAbdulrahman Tabaza @embed_dim
2 Followers 447 Following Enjoyer of various vector spaces and modalitiesWill @solidwillity
117 Followers 1K FollowingChris T. N. @chris_t_ng
121 Followers 1K Following #nlp #deeplearning @Microsoft, previously @Samsung , @_skyhiveZhijing Jin @ZhijingJin
3K Followers 1K Following Final-year PhD @MPI_IS & @ETH_en w/ @bschoelkopf. Research on (1) @CausalNLP and (2) NLP4SocialGood @NLP4SG. Mentor and mentee @ACLMentorship.Jordan Gong @jordan__gong
41 Followers 2K FollowingJacob Valdez @jvboid
1K Followers 7K Following 24 | building @HumanRobotsAI | [email protected] | +1.469.968.9490 | https://t.co/V5Odmcls1FWhitney Clark @WhitneyCla58959
1K Followers 2K Following baby , come to my profile and follow me😋 👉 Follow me and let have fun on private😗 😸John Yang @jyangballin
2K Followers 441 Following CS/NLP MS student @princeton_nlp Previously @Berkeley_EECSJon Saad-Falcon @JonSaadFalcon
441 Followers 186 Following CS PhD + MBA @Stanford | Previously @databricks @allen_ai @GeorgiaTechAlbert Jiang @AlbertQJiang
2K Followers 406 Following AI4Maths @Cambridge_CL Science @MistralAI I bake my own opinions at temperature=2.0Alessandro Stolfo @alesstolfo
678 Followers 397 Following PhD Student @ ETH Zürich in #NLProc | Prev. @oracle LabsAlexander Perevalov @Perevalov_A
72 Followers 91 Following 👨🎓 PhD Student & Research Assistant & Research Project Lead 🇩🇪 Hochschule Anhalt // HTWK Leipzig // Uni Paderborn 🇷🇺 From Perm, RussiaMemo Sparkfield @MemoSparkfield
855 Followers 1K Following Exploring the future of AI, AGI, Gamification, and Computer Programming. Passionate about tech's transformative potential. Let's connect: @memosparkfieldhelena sarin @NeuralBricolage
18K Followers 395 Following getting off-manifold in interesting ways: engineering artist constructing the future artifacts; GANalog™️ models; generative potteryVaidya Shankar @gubbi_sparrow
15 Followers 72 Followingreluctant_curmugeon @DuhemQuiner
48 Followers 291 Following Reformed ML Person Now Moonlighting as a Rogue Servitor.Hugo @Mldhug
37 Followers 336 Following PhD student in multimodal learning for audio understanding at @telecomparis, ex-MVA (ENS Paris Saclay)Males @males9341
241 Followers 4K Following To be prepared against surprise is to be trained. To be prepared for surprise is to be educated. 🎎🎐 Facts do not fall in the face of discomfort 🌗Sunny Sanyal @SunnySanyal9
336 Followers 788 Following PhD student @UTexasECE| Former @AmazonScience | Member of @MLfoundations and @wncg_UT, studied at 🇮🇳🇨🇳🇺🇲Prateek @Prateek74021452
12 Followers 130 FollowingLethoashur @lethoashur76913
1 Followers 344 FollowingV_iv @Viv2060702
1 Followers 185 Following I swear in the name of God, don't miss an opportunity to earn 500-5000usdc every day. https://t.co/7GfK9FVXpMDavid Stafford @davidstafford
740 Followers 2K Following AI and robotics. Bit twiddling. Opinions are my own.b @0hi
44 Followers 312 FollowingSimon Guo 🦝 @simonguozirui
1K Followers 4K Following Incoming CS PhD student @Stanford and curr training models at @cohere | 🎓 @Berkeley_EECS | prev built things at @ @anyscalecompute @nvidiapengch fan @FanPengch
199 Followers 5K FollowingAB M @abdelmehdi_ab
51 Followers 1K FollowingDanial Namazifard @IamDanialNamazi
61 Followers 400 Following MSc Student in AI, NLP Researcher @ UT #NLProc #MachineLearningIsla @Isla07684053503
5 Followers 811 Followingemma-xrug.eth🚇🚲 @wotlango
2K Followers 3K Following Climate Web3 Finance & DAO Enthusiast.Dentralized Finance thinking/NVDA/Regen101/S0S Trainer. Love planet Earth 🌎 Let's Save Our Planet. Solarpunk NomadAnmol Chhabra @AnmolCh37766217
6 Followers 173 Following Ex Sde-Intern @Readyly, @Trell | Python & JS Developer | IITISM'25 | 🎹 | 21 | Learning Golang_JaneD_A8 @A8Janed71093
2 Followers 368 Following(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingDelip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈Jo Kristian Bergum @jobergum
8K Followers 810 Following Distinguished Engineer @vespaengine. Tweets about Vespa, search, recommendation, ranking, and IR. CET. #StandWithUkraine 💙💛Lucas Beyer (bl16) @giffmana
56K Followers 444 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistSasha Rush @srush_nlp
51K Followers 464 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzYi Tay @YiTayML
28K Followers 97 Following Chief scientist & Co-founder @RekaAILabs past: Research Scientist @Google Brain 🧠 currently learning to be a dad 🍼👶Kyunghyun Cho @kchonyc
60K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Graham Neubig @gneubig
30K Followers 582 Following Associate professor at CMU, studying natural language processing and machine learning.Christopher Manning @chrmanning
126K Followers 114 Following Director, @StanfordAILab. Assoc. Director, @StanfordHAI. Founder, @stanfordnlp. Prof. CS & Linguistics, @Stanford. IP @aixventureshq. 🇦🇺 Do #NLProc & #AI. 👋Akari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳Tim Dettmers @Tim_Dettmers
28K Followers 819 Following PhD Student at @UW. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.Felix Hill @FelixHill84
9K Followers 776 Following Research Scientist, Deepmind I try to think hard about everything I tweet, esp on 90s football and 80s music None of my opinions are really someone else'sLuca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai, open source science fan, @QueerInAI organizer 🤖☕️🍕they/themSam Bowman @sleepinyourhat
35K Followers 3K Following AI alignment + LLMs at NYU & Anthropic. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.Nils Reimers @Nils_Reimers
10K Followers 434 Following Director of Machine Learning @Cohere | ex-huggingface | Creator of SBERT (https://t.co/MKKOMfuQ4C)François Fleuret @francoisfleuret
30K Followers 475 Following Prof. @Unige_en, Adjunct Prof. @EPFL_en, Research Fellow @idiap_ch, co-founder @nc_shape. AI and machine learning since 1994. I like reality.Jacob Andreas @jacobandreas
13K Followers 955 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJwJimmy Lin @lintool
13K Followers 842 Following I profess CS-ly at the @UWaterloo and gaze into the technological crystal ball at @Primal. I used to write code for @Twitter and slides for @Cloudera.Rishabh Agarwal @agarwl_
6K Followers 541 Following Senior Research Scientist, @GoogleDeepMind, ex-🧠. Agents that make decisions. NeurIPS Best Paper (RLiable). Mila, IIT Bombay.Milvus @milvusio
3K Followers 5K Following The most widely adopted open source vector database for #AI #OpenSource #VectorSearch 💬Discord: https://t.co/9yOD2GjWv4 🔗Find us: https://t.co/BbTzkz9bHNAlbert Jiang @AlbertQJiang
2K Followers 406 Following AI4Maths @Cambridge_CL Science @MistralAI I bake my own opinions at temperature=2.0Alessandro Stolfo @alesstolfo
678 Followers 397 Following PhD Student @ ETH Zürich in #NLProc | Prev. @oracle LabsMagdalena Kaiser @mag_kaiser
140 Followers 97 Following PhD student at Max Planck Institute for Informatics. Question Answering. Information Retrieval. Natural Language Processing.NWS Pittsburgh @NWSPittsburgh
52K Followers 284 Following Official Twitter Account for National Weather Service Pittsburgh. Details: https://t.co/TurFt4MvnUDaphne Ippolito @daphneipp
1K Followers 72 Following I am a senior research scientist at Google. I research topics in natural language generation.Moritz Laurer @MoritzLaurer
2K Followers 1K Following 🤗 Machine Learning Engineer @HuggingFace. PhD researcher @VUAmsterdamLifan Yuan @lifan__yuan
276 Followers 116 Following NLPer @TsinghuaNLP; Incoming PhD student @IllinoisCSJohn Yang @jyangballin
2K Followers 441 Following CS/NLP MS student @princeton_nlp Previously @Berkeley_EECSLukas Galke @LukasGalke
661 Followers 1K Following How machines learn to communicate, postdoc @MPI_NL | Natural Language Processing, Lifelong Machine Learning | @[email protected]Ioana Baldini @ioanauoft
711 Followers 1K Following Researcher. Immigrant. Mom. STEM. And if you insist Dr. Playing with ideas at IBM Research AI.David Picard @david_picard
3K Followers 310 Following Computer Vision/Machine Learning research @ImagineEnpc / LIGM , École des Ponts. Music & overall happiness. A few flowers too. Born well below 350ppm.Korede @Akinpeluakorede
47 Followers 570 Following Ph.D. Candidate| Mechanical Engineering @lsu Master's candidate| Computer Science @lsu| Natural Language ProcessingSumit @_reachsumit
1K Followers 384 Following Senior ML Engineer @Meta | prev: @TikTok_us, @Amazon, @Samsung | UChicago Alum https://t.co/hcCJ2n979W 🇮🇳→🇰🇷→🇦🇺→🇨🇦→🇺🇲Nayan Saxena @SaxenaNayan
2K Followers 2K Following Brought artificial intelligence to @RBC, @Glowforge, @Wombo, @Bell & beyondYubei Chen @Yubei_Chen
470 Followers 335 Following Assistant Professor, ECE @ UC Davis, Unsupervised Learning, NeuroAI Co-Founder at https://t.co/d0GT9i7fATFangyuan Xu @brunchavecmoi
319 Followers 498 Following 许方园👩🏻💻phd student @ ut austin, interested in nlpQintong Li @qintong_li
230 Followers 244 Following A PhD student interested in NLP and ML. I’m working on text generation and its downstream tasks.The TWIML AI Podcast @twimlai
13K Followers 2K Following This Week in #MachineLearning & #AI (podcast) brings you the most interesting and important stories from the world of #ML and artificial intelligence.Antoine Louis @antoinelouis_
193 Followers 147 Following CS PhD @MaastrichtU. Prev intern @Cisco. NLP, IR, QA.Intuitive Machines @Int_Machines
95K Followers 376 Following We open access to the Moon for the progress of humanity.Adyasha Maharana @adyasha10
545 Followers 644 Following PhD Student @uncnlp. Interests: data efficiency, vision+language, causality, AI+health. Previously PRIOR@allen_ai, @AdobeResearch, @sciomellc, @IHME_UW, @IITKgpYu Gu @yugu_nlp
871 Followers 567 Following Ph.D student in NLP @osunlp. ex-Research Intern @MSFTResearch. #NLProcAnne @anne_youw
96 Followers 92 Following CS PhD student @cornell_tech. Prev: @metaai, @Cambridge_Uni, @centralesupelecKhanh Nguyen @khanhxuannguyen
1K Followers 457 Following Postdoc at CHAI Berkeley with Prof. Stuart Russell, Prev. Postdoc at Princeton NLP, PhD @umdcs, Human-AI Communication, Interactive Learning, NLP.Asaf Yehudai @AsafYehudai
316 Followers 732 Following #NLProc researcher, CS Ph.D. student at @HebrewU (@nlphuj), and a researcher at @ibmresearch.Carla Brown 🇪🇺�.. @carlambrown
40K Followers 1K Following Comedy Writer, Ex-Glamour Model. My wits won't sag.Huizhuo Yuan @HuizhuoY
722 Followers 915 Following Graduate student @UCLA AGI lab, Researcher on LLMs, Diffusion Models, Reinforcement Learning, Games and AI for Science. Opinions are my own.Peter Hase @peterbhase
2K Followers 684 Following Google PhD Fellow at @uncnlp. Interested in interpretable ML, natural language processing, AI Safety, and Effective Altruism.Yihe Deng @Yihe__Deng
2K Followers 1K Following CS PhD student @UCLA | Prev. Applied Scientist Intern @AWS | LLM, Multi-modal learningJordan Ford @jrdnfrd
86 Followers 337 Following 🤖 Robotics Entrepreneur @RubiconRobotics 💻 Automating everything but the fun stuff 🗺 Perception | Localization | Mapping | Controls 🎓 PhD @CMU_RoboticsJason Corso @_JasonCorso_
1K Followers 200 Following Corso is a Professor at U Michigan and Co-Founder of Voxel51 who makes the category-defining data+model codevelopment ML Tool: FiftyOneHaidar Khan @haidarkk1
181 Followers 58 Following Research Scientist (Currently @SDAIA_SA, ex-Amazon). PhD CS @rpi. Building LLMs in KSA. Scale smarter, not harder. Opinions generated from an independent LLM.Bing He @binghe2727
67 Followers 377 Following CS PhD@Georgia Tech, Actively search for 2024 full-time positions. PhD research areas: ML/AI, NLP, computational social science; Ex-intern@Amazon Search/A9.comHasan Hammoud @hammh0a
639 Followers 551 Following Ph.D. candidate in Computer Vision and Machine Learning @KaustVision.Boxin Wang @wbx_life
547 Followers 462 Following Research Scientist at NVIDIA @nvidia. UIUC Ph.D. @IllinoisCS in Trustworthy and Scalable LLM. Previously at MSR @MSFTResearch, Google Research @googleai.Rajiv Shah @rajistics
2K Followers 332 Following occasionally funny videos along with practical AI posts, now at ML/AI @snowflakedb - was @huggingface @datarobot @snorkelaiMechanical Dirk @mechanicaldirk
547 Followers 244 Following Principal Engineer at @allen_ai. Engineering Lead of the OLMo project.Institute for Foundat.. @MLFoundations
1K Followers 1K Following IFML is an NSF funded National AI Institute, a collaboration between @UTAustin, @UW, @WichitaState, and @MSFTResearch.Sheng Shen @shengs1123
1K Followers 536 Following Ph.D. student @berkeley_ai; Building 🦙@MetaAi; Former @MSFTResearch, @allen_ai, @GoogleDeepMindHaotian Liu @imhaotian
6K Followers 398 Following building intelligence @xAI, creator of #LLaVA, cs @UWMadison, prev @MSFTResearchPan Lu @lupantech
4K Followers 1K Following PhD @CS_UCLA @uclanlp | Amazon/Bloomberg/Qualcomm/UCLA Fellows | Ex @Tsinghua_Uni @MSFTResearch @allen_ai @Adobe | #NLPoc, LLMs, Reasoning, AI4Math, AI4ScienceThe best few-shot classifier is... 🥁 Llama? Mistral? Flan? 🌟How about Roberta!🌟 In our new @naaclmeeting paper, we claim we were just missing the right objective!
@srchvrs @natolambert My favorite takeaway of the Llama 3 announcement so far is that you don't have to decide between PPO and DPO: just use both!
@srchvrs @LukasGalke And also for the next survey (thanks already shared this survey with a few people) x.com/ElronBandel/st…
The best few-shot classifier is... 🥁 Llama? Mistral? Flan? 🌟How about Roberta!🌟 In our new @naaclmeeting paper, we claim we were just missing the right objective!
I got tenure! It was fitting that I got to celebrate with the lab right after the news. Working together for the last 6.5 years has been a blast.
@srush_nlp Gains are diminishing though at least in SuperGLUE like benchmarks, aren’t they? Are there any challenging non-generative benchmarks that generative models perform poorly whereas encoder-based models are sort of ok that will be excellent with scaling? Can’t think of any
@srush_nlp I think DeBERTa is a good example of this scaling experiments and often performs very well in corresponding benchmarks. Lack of generation inherently limits its usage and applicability which may explain disinterest in this direction.
@Dorialexander @srush_nlp @mmitchell_ai Do you have an example to share ? My synthetic data is shit, I don't know if my prompts are bad, if the model is too dumb/wrongly called (ie temperature), or if I'm too demanding
@srush_nlp Maybe it is because de-noising objective is "wasting" tokens compared to autoregressive models. E.g. when you mask 15% of tokens, then after 1 epoch you've backpropogated loss from only 15% of your tokens, compared to 100% in next token prediction loss.
That was fast!
Llama 3!! 🦙🎉 I put together a quick video going through the release notes, how performance is reported and the plans for a 400B+ model, and then diving into a demo showing how to build a RAG system with Llama 3 and DSPy, and then most excitingly 🥁, Using DSPy's MIPRO…
@srchvrs Well, if you include QA, multi-stage systems date back to at least the 1960s: dl.acm.org/doi/10.1145/36…
The earliest public acknowledgment that Bing uses a multi-stage architecture that I'm aware of is Jan Pedersen's keynote at the SIGIR 2010 industry track, titled "Query Understanding at Bing". (Slides no longer available on the web, but I have a copy of the pptx.)
I say *explicitly* because, of course, there were already many published papers on LTR by then - it was obvious they were all rerankers, but none of them were explicit about reranking a candidate list, and none discussed first-stage retrieval.
The earliest *academic* paper that *explicitly* describes multi-stage ranking that I'm aware of is Matveeva et al. from SIGIR 2006: dl.acm.org/doi/10.1145/11…
In the embedding search setup, we normally combine a fast embedding model and an accurate but slow reranker model. The newly released @JinaAI_ -rerankers are small in size and almost as accurate as our base reranker. This means given a time constraint, it can scoring more…
2 new tiny Apache 2.0 reranker models just got released by @JinaAI_. Despite their small size/latency, they perform competitively on benchmarks, reportedly outperforming bge-reranker-base and mxbai-rerank-base on MTEB Retrieval. Models: huggingface.co/jinaai/jina-re… Details in 🧵
Today we're joined by @Dahoas1 from @GeorgiaTech to discuss the reasoning capability of language models and the potential to improve it with traditional RL methods 🎧 / 🎥 Listen to the episode at: twimlai.com/go/680. 📖 CHAPTERS 00:00 - Introduction 02:19 - RL vs RLHF…
All while being - Cleanly licensed Apache 2, under @linuxfoundation (do anything with it!) - The world's greenest 7B model 🌲 (by per token, energy consumption) - Trained on 2.25T of tokens You can find out more from our full writeup here: blog.rwkv.com/p/eaglex-v2-so…
Scholars aspire to expand the boundaries of knowledge but I must admit I've really enjoyed contracting the boundaries of knowledge. My favorite kind of research has involved questioning consensus. Do we really know what we think we know, or are we falling for hype and groupthink?
One prompt does not fit all language models ☝️ Luckily for you, DSPy automates the task of prompt engineering! Here is a thread with a few things to know about the collection of compilers in DSPy. It is also outlined in a new blog post from @CShorten30 and I, “Your Language…