Zekun Wang (Seeking 25Fall PhD) 🔥 @ZenMoore1
🥷 #LLM #AGI Research Intern @01AI_Yi @hkust @ETH; 💼 Formerly @BAAIBeijing #Langboat; 🔥 Looking for #25Fall PhD! zenmoore.github.io Beijing, China Joined June 2020-
Tweets604
-
Followers1K
-
Following670
-
Likes1K
AutoCrawler A Progressive Understanding Web Agent for Web Crawler Generation Web automation is a significant technique that accomplishes complicated web tasks by automating common web actions, enhancing operational efficiency, and reducing the need for manual intervention.
Are LLMs biased toward themselves? Frontier LLMs give higher scores to their own outputs in self-eval. We find evidence that this bias is caused by LLM's ability to recognize their own outputs This could interfere with safety techniques like reward modeling & constitutional AI
VBench update: We support evaluating Image-to-Video (I2V) models at 𝗩𝗕𝗲𝗻𝗰𝗵-𝗜𝟮𝗩 🖼️ Image Suite: multi-scale, multi-aspect-ratio, comprehensive content variety 📏 Dimensions: video-image consistency, camera motion, video quality, etc. 👨💻 Code: github.com/Vchitect/VBench
New Model Alert! One overlooked ability of multimodal models is their ability to reason over multiple images. Lots of existing LMMs like LLaVA, BLIP, Fuyu, etc can only support single image input. GPT-4v can only accept multiple images prepended to the text. How to enable LMMs…
New Model Alert! One overlooked ability of multimodal models is their ability to reason over multiple images. Lots of existing LMMs like LLaVA, BLIP, Fuyu, etc can only support single image input. GPT-4v can only accept multiple images prepended to the text. How to enable LMMs… https://t.co/6FPxICGRl7
Only true long context language modeing is message-passing via gradient descent (sometimes w/ retrieval)
LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding Improves the performance of existing retriever models by enriching document embeddings with contextual information. 📝arxiv.org/abs/2404.05825
In text-to-image generation, evaluating how well the generated image matches the prompt is a major challenge. We address this with VQAScore: a SOTA metric that significantly surpasses CLIPScore, PickScore, ImageReward, TIFA, and more! VQAScore works especially well on complex…
[1/n] 🎉🎉🎉 Excited to share our latest work: "The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis"! We delve into the dynamics of LLMs across different scales and domains. 💡Highlights include: 🗺️ Comprehensive Model Evaluation:…
Say hello to Grok-1's new PyTorch+HuggingFace edition! 🚀 314 billion parameters, 3.8x faster inference. Easy to use, open-source, and optimized by Colossal-AI. 🤖 Dive in: #Grok1 #ColossalAI🌟 github.com/hpcaitech/Colo… Download Now: huggingface.co/hpcai-tech/gro…
What are the best practices for remote collaboration? I'm frustrated with the inefficient communication. 1. I have a complete project documentation system, but it seems like no one pays attention to it. 2. We use Slack and WeChat for team communication, but responses are…
Beihang University of China released the tech paper of LlamaFactory🦙🌟 Demo: huggingface.co/spaces/hiyouga… Tech report: huggingface.co/papers/2403.13…
🚀𝐂𝐨𝐝𝐞𝐔𝐥𝐭𝐫𝐚𝐅𝐞𝐞𝐝𝐛𝐚𝐜𝐤: 𝐀𝐧 𝐋𝐋𝐌-𝐚𝐬-𝐚-𝐉𝐮𝐝𝐠𝐞 𝐃𝐚𝐭𝐚𝐬𝐞𝐭 𝐟𝐨𝐫 𝐀𝐥𝐢𝐠𝐧𝐢𝐧𝐠 𝐋𝐚𝐫𝐠𝐞 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥𝐬 𝐭𝐨 𝐂𝐨𝐝𝐢𝐧𝐠 𝐏𝐫𝐞𝐟𝐞𝐫𝐞𝐧𝐜𝐞𝐬 @AtonKamanda @sahraouh 📝Paper: arxiv.org/abs/2403.09032 💻Code: github.com/martin-wey/Cod…
🤔 Can we teach LLMs to understand protein sequences? 🧬 Introducing ProtLLM, a versatile cross-modal LLM that bridges the gap between natural language and protein. Paper: arxiv.org/abs/2403.07920 Page: protllm.github.io/project/ 1/🧵
lol 😂😅😅😂
Introducing MetaGPT's Data Interpreter: Open Source and Better "Devin". Data Interpreter has achieved state-of-the-art scores in machine learning, mathematical reasoning, and open-ended tasks, and can analyze stocks, imitate websites, and train models. Data Interpreter is an…
Yi models TECH REPORT just went live! Sharing our humble explorations launching, improving, innovating our base, chat, and vision-language models. Kudos to @01AI_Yi team behind the scenes. Love to hear the feedback from the community! arxiv.org/abs/2403.04652
New!🔥Yi-9B🔥has been open-sourced from @01AI_Yi. It stands out as the top-performing similar-sized language model friendly to developers, excelling in code and math. Welcome to give it a try and share how you solve problems! huggingface.co/01-ai/Yi-9B
Nice work! Knowledge Augmentation + Agent Learning + Self-Training.
Nice work! Knowledge Augmentation + Agent Learning + Self-Training.
Pramukhms2007 Ms @pramukhms235383
0 Followers 8 FollowingAdvait Patole @advait_patole
14 Followers 971 FollowingDamian Pérsico @PersicoDamian
84 Followers 435 FollowingPhillip Lindsay @EastLAPinche
60 Followers 386 FollowingQingcheng Zeng @SteveZeng7
562 Followers 1K Following PhD-ing @linguisticsNU with @rfpvjr / I do research in computational social science and linguistic-motivated NLP / A big fan of @Arsenaljack_new @jacknew95318499
53 Followers 315 FollowingTaicheng Guo (Looking.. @taioooorange
112 Followers 472 Following PhD student in Computer Science at University of Notre Dame @NotreDame, Previously @KAUST_News @mbzuaiJack FitzGerald @jgmfitz
4 Followers 187 Following Principal, Applied Scientist at Amazon AGI org; AI model and system builder; LLM researchthenormalone @AkNiloy6
352 Followers 4K Following ML Engineer | Researcher | Musician | Lifelong Liverpool Fan 🇧🇩Arnav Gupta @arnav_g97
18 Followers 207 Following i post demos | i do knowledge graphs | ml | nlp automating investors thought processAli Athar @AliAthar1401
71 Followers 366 Following 🌟 AI PhD student in South Korea | Researching AI, NLP, and healthcare applications 💻 | MS degree from NUST 🎓 | Travel lover.18 Aryan Prasad @aryan_prasad18
2 Followers 48 FollowingWilliam Sun @williamsun2020
123 Followers 1K FollowingOrangeCat @WinstonYan45075
16 Followers 268 FollowingJoseph Manuel Blanco .. @blanco_joseph02
54 Followers 665 Following Full Stack Software Developer Technology Enthusiast SaaS Entrepreneur 3 Years of experiencexland2023 @xland202352226
301 Followers 3K FollowingDr Nobody @TheRealDrNobody
772 Followers 3K Following CS Student. My mission, over 3 years, is to ensure 100,000 of us STEM students stay in college, stay in our careers, and THRIVE amidst the AI hype of doom.Siyan Zhao @siyan_zhao
779 Followers 486 Following CS PhD student @UCLA | Interested in decision making, LLMs, generative models | Bachelors @UofT EngSciZhenting Wang @wang1999_zt
74 Followers 230 Following PhD Student @RutgersCS. Trustworthy and Responsible Generative Artificial Intelligence. Intern @SonyAI_global (current) @Meta GenAI (incoming)Merovingian @merovingianAI
6 Followers 62 Following my realistic and sometimes unethical thoughts about tech and AIc62cx6qs94 @1039jqlchw9q
1 Followers 318 Following The team offers short-term investments in cryptocurrencies. With a rigorous plan, you can earn between $500 and $5,000. Click to join TG: https://t.co/TfuzTb7YsaSparsh Jain @sparshjain21
61 Followers 778 Following Research Intern @AI4Bharat, IIT Madras || Ex- Data Science Intern @Culinda || Data Science || ML enthusiastSongge Zhang @songge_zhang
83 Followers 279 Following PhD student at HK PolyU and IOP, CAS. In-sensor and neuromorphic computing/wafer-scale 2D electronics|Working with Yang Chai, Xiao-Ming Tao, Guangyu ZhangFabio Baroni @Fabiothebest89
2K Followers 5K Following Ethical hacker, pen tester, dev, web designer, vulnerability assessment, forensics, malware analysis. @pentestguru FounderICX @icxdao
5K Followers 65 Following We contribute to the ICX decentralized and AI powered social network.Kunvar Thaman @firstuserhere
218 Followers 630 Following Taking apart neural networks and putting them back together for a living Social profiles: https://t.co/OxoeMvCw3abmf @bfoading
223 Followers 2K Following ENSPY| IT Engineer | ENS-yde-Math |MBA Candidate-USA|Devops| AI Enthusiast |IT Project manager|Founder GOHZEJitendra Sharma @jkumarsharma998
817 Followers 6K Following Curious about Research in AI. NLP and Computer Vision Interest me. Curious about truth and existence. Views are personal.AI & Partners @AI_and_Partners
1K Followers 6K Following The European Union AI Act coming into force in 2024 aims to address problems associated with the use, development and/or deployment of AI systems.N Sreeram @NSreeram5
53 Followers 499 Followingdori chen @dori6753
10 Followers 102 FollowingGruSome @DeepBNN
22 Followers 530 FollowingJindong Gu @Jindong73504766
283 Followers 886 Following Senior Research Fellow in University of Oxford @OxfordTVG Faculty Researcher @Google #ResponsibleAI #AISafety #GenAI Homepage: https://t.co/YOSVO3jb6hAlo @Hal90910
0 Followers 2K FollowingDustin Groves @Oracle4191
12 Followers 124 Followingꜛᴛ͎ꜜ @Incuriator
193 Followers 5K FollowingDan Fu @realDanFu
4K Followers 176 Following CS PhD Candidate at Stanford, systems for machine learning. Sometimes YouTuber/podcaster. Academic Partner, @togethercompute.Jindong Gu @Jindong73504766
283 Followers 886 Following Senior Research Fellow in University of Oxford @OxfordTVG Faculty Researcher @Google #ResponsibleAI #AISafety #GenAI Homepage: https://t.co/YOSVO3jb6hSiyan Zhao @siyan_zhao
779 Followers 486 Following CS PhD student @UCLA | Interested in decision making, LLMs, generative models | Bachelors @UofT EngSciYiqing Xie @YiqingXXX
61 Followers 82 Following ✨ NLP for Code & Code for NLP 🎓 PhD student @LTIatCMU; MSCS @dmguiuc. 👩💻 Intern (incoming) @meta; (previous) @MSFTResearch; @AlibabaDAMO.Haotong Qin @qin_haotong
129 Followers 159 Following Postdoctoral Researcher @ETH_en. Formerly @Beihang1952, @CVL_ETH, @BytedanceTalk, @MSFTResearch, and @TencentGlobal. | Email: [email protected]Tiezhen WANG @Xianbao_QIAN
908 Followers 347 Following Engineer at HuggingFace, ex-Googler on TFLite / micro. Ideas are my own.Di Chang @DiChang10
698 Followers 1K Following PhD @CSatUSC|BSc @TU_Muenchen|BEng @dlut1949|Previous @TikTok_US @EPFL| Working on 3D Computer Vision, Generative Model |17‘ Camaro SS 1LEwallhaven.cc @wallhaven
4K Followers 3 Following Official Twitter for wallhaven.cc: The best wallpapers on the net!Ceyuan Yang @CeyuanY
1K Followers 372 Following Researcher on Computer Vision, especially in content recreation.Zora Zhiruo Wang @ZhiruoW
528 Followers 183 Following PhD student @LTIatCMU | previously: intern @Amazon Alexa AI | assistant researcher @Microsoft Research, Asia | intern @TencentSiuuu.AI @SiuuuAI
3K Followers 4 Following https://t.co/Y2K4eVCwC2, your personal creative writing copilot. Powered by @AIWaves_IncYangyi Chen @YangyiChen6666
491 Followers 330 Following CS Ph.D. student at UIUC @IllinoisCS, focus on multimodal and large language models.Zhen Wang @zhenwang9102
475 Followers 448 FollowingAIWaves @AIWaves_Inc
3K Followers 6 Following @SiuuuAI | LLMs for creative writing | Language AgentsTianyu Chen @TianyuC71403718
16 Followers 148 Following Microsoft Research Intern & PhD. candidate of BUAASophia在斯坦福 @HeySophiaHong
6K Followers 211 Following 🌲 清华毕业 | 斯坦福在读 👩🏻💻 萌新创业者 | 做了 https://t.co/RK4pvHAZ5Z @UseAIAnywhere 💡 AI前沿 | 创业思考 | 出海产品 | 留学生活 ✨ 全网同名Yu Gu @yugu_nlp
877 Followers 568 Following Ph.D student in NLP @osunlp. ex-Research Intern @MSFTResearch. #NLProcAdina Yakup @AdeenaY8
2K Followers 454 Following @huggingface 🤗 | Contributing to Chinese ML community.Bowen Tan @BowenTan8
98 Followers 133 Following PhD student @LTIatCMU @SCSatCMU; Member @llm360; Prev. student researcher @GoogleYining Ye @Yining_Ye
120 Followers 153 Following NLP researcher at @TsinghuaNLP, working on Tool Learning, Reasoning, AI-Agent,views expressed here are my ownMahdi Kamani @MMKamani7
502 Followers 1K Following Efficient GenAI @AMD PhD of Informatics @PennState. ML & CV researcher, prev @WyzeCam @Twitter @HoneywellHeming Xia @hemingkx
573 Followers 1K Following Ph.D. student @HongKongPolyU | Prev MEng & BSc @PKU1898 | Prev Intern @MSFTResearch (MSRA) | NLP | Language ModelingXu Tan @xutan_tx
1K Followers 517 Following Principal Researcher and Research Manager @ Microsoft, working on generative AI and its application on language/speech/music/avatar.Da Yin @Wade_Yin9712
774 Followers 421 Following PhD @uclanlp | Intern at AI2 Mosaic @ai2_mosaic | Amazon PhD Fellow in 2023 @AmazonScienceETH Zürich @ETH
90K Followers 567 Following Dies ist der offizielle deutsche Twitter-Kanal der ETH Zürich. Hier lesen Sie das Neuste aus Wissenschaft, Technologie & Lehre. English account: @eth_enMikaStars★ @MikaStars39_
174 Followers 614 Following Second year B.A. / B.S. in @ZJU_China Prev: Bsc in @Polytechnique Devoted in LLM Architecture & InterpretabilityYifei Li @YifeiLiPKU
290 Followers 391 Following Ph.D. student @osunlp | Prev MSc @PKU1898 | BEng @NEUChina | Prev Intern @MSFTResearch (MSRA) | LLM & NLPerQintong Li @qintong_li
236 Followers 244 Following A PhD student interested in NLP and ML. I’m working on text generation and its downstream tasks.Vaibhav (VB) Srivasta.. @reach_vb
11K Followers 169 Following GPU poor @Huggingface | F1 fan | Here for @at_sofdog’s wisdom | *opinions my ownZilong Wang @zlwang_cs
320 Followers 163 Following Ph.D. Student @ucsd_cse @shangdatalab | Solve real problems with awesome NLP | Intern @GoogleCloud | Previously @pku1898 @GoogleAI @MSFTResearch @AdobeResearchSonglin Yang @SonglinYang4
2K Followers 2K Following PhD student @MIT_CSAIL. Prev. @ShanghaiTechUni @SUSTechSZ. Working on scalable and principled methods in #ML & #NLProc. INTP | 5w4 | sx/sp | she/herWanru Zhao (Looking f.. @Renee42581826
513 Followers 2K Following Postgraduate Student @CaMLSys @Cambridge_CL | Ex-Intern @DGLGraph @AWS and @CambridgeJBS | Do not go gentle into that good night 🧗Manurag Khullar @manuragkhullar
151 Followers 368 Following Forbes India's 1.5 Billion under 1.5 Billion | ML/Sci Comp Grad at UPenn, Liberal Arts @ashokauniv | Ex-Tech Policy @nitiaayog | Jack of All, Master of Pun🌈Howard Yen @HowardYen1
103 Followers 183 FollowingShuhuai-Ren @RenShuhuai
234 Followers 491 Following CS Ph.D. student @pku1898 | Previously @AmazonScience @AlibabaGroup @TencentGlobal | NLP, vision-language multimodalityAlexis Chevalier @AlexisChvlr
100 Followers 79 Following NLP postdoc @PrincetonPLI. Formerly researching mathematical logic @IAS and @UniOfOxfordHistoric Vids @historyinmemes
5.2M Followers 210 Following Daily history lessons. Education through memes!Semantic Scholar Rese.. @ai2_s2research
571 Followers 23 Following Research team @allen_ai working on AI, HCI, ML, NLP, accessibility, and comp. social science in support of @SemanticScholar's mission of accelerating science.Zirui "Colin" Wang @zwcolin
189 Followers 332 Following CS @princeton_nlp @princetonPLI | prev @HDSIUCSD @CogSciUCSD, @CarnegieMellon. synergize model understanding & generation; multimodality; He/Him.yanjungao @Serena_pancakes
589 Followers 423 Following Clinical NLP Postdoc UW-Madison #UWSMPH. Ph.D. in Computer Science and Engineering #PennState. #NLProc & #AI researcher. Piano, Ballet & Skiing.Troy Luhman @LuhmanTroy
890 Followers 148 FollowingPreference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data abs: arxiv.org/abs/2404.14367 project page: understanding-rlhf.github.io code: github.com/Asap7772/under… "On-policy sampling generally improves performance and efficiency" "A negative gradient improves over…
More exciting news today -- Gemini 1.5 Pro result is out! Gemini 1.5 Pro API-0409-preview now achieves #2 on the leaderboard, surpassing #3 GPT4-0125-preview to almost top-1! Gemini shows even stronger performance on longer prompts, in which it ranks joint #1 with the latest…
Congrats @GoogleDeepMind on shipping Gemini 1.5 Pro to public review! Upon capacity & latency testing, we have now brought Gemini 1.5 Pro up to the Arena🤖 Big improvement from Pro 1.0 to 1.5 across the board, and exceptionally strong long context understanding. Come test and…
Only true long context language modeing is message-passing via gradient descent (sometimes w/ retrieval)
Adapting LLaMA Decoder to Vision Transformer This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first "LLaMAfy" a standard ViT step-by-step
[CV] AnyV2V: A Plug-and-Play Framework For Any Video-to-Video Editing Tasks M Ku, C Wei, W Ren, H Yang, W Chen [University of Waterloo & Harmony.AI] (2024) arxiv.org/abs/2403.14468 - AnyV2V is a novel plug-and-play framework for video-to-video editing tasks. It…
[LG] A Survey on Uncertainty Quantification for Deep Learning: An Uncertainty Source Perspective arxiv.org/abs/2302.13425 - DNN models can achieve high accuracy but also make overconfident incorrect predictions, causing issues in high-stake applications like autonomous…
Video editing made easy! We propose AnyV2V to address any video editing tasks without any training. 1. Choose your favorite image editing model to edit the first frame of a video. 2. Use an image-to-video model to propagate the edit results to other frames through feature…
AnyV2V A Plug-and-Play Framework For Any Video-to-Video Editing Tasks Video-to-video editing involves editing a source video along with additional control (such as text prompts, subjects, or styles) to generate a new video that aligns with the source video and the provided
I think easy-to-hard generalization is necessary if we want to train a LLM that can solve problems that human can’t solve. We make one of the earliest efforts towards this goal.
🌟Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision 🌟 arxiv.org/abs/2403.09472 How can we keep improving AI systems when their capabilities surpass those of human supervisors? (1/n)
Beihang University of China released the tech paper of LlamaFactory🦙🌟 Demo: huggingface.co/spaces/hiyouga… Tech report: huggingface.co/papers/2403.13…
@stats_feed 🇯🇵 World's Greatest Japanese Inventions/ Discoveries 🇯🇵 1️⃣ Android Robots 🤖 2️⃣ Flash Memory 💾 3️⃣ Bullet Train 🚅 4️⃣ 3D Printing 🖨 5️⃣ CRISPR 🧬 6️⃣ QR Code 📇 7️⃣ Lithium Ion Battery 🔋 8️⃣ Blue LED Light 🚦 9️⃣ Pocket Calculator 🧮 🔟 Portable EKG 🫀 1️⃣1️⃣ Camera Phone 🤳🏽…
Really excited that our paper "A PhD Student’s🧑🎓 Perspective on Research in NLP in the Era of #LLMs" will be at #COLING2024! We brainstormed 45 topics💡 that students can work on despite the LLMs. Co-led by @OanaIgnatRo @ZhijingJin and @radamihalcea with contributions from many.
“What should I work on?” is a question we hear more & more often from NLP students, during a time when the media rhetoric is that “it’s been all solved” Turns out there are many NLP research areas rich for exploration—here is our answer from 20+ students arxiv.org/abs/2305.12544
Jensen Huang is the new Taylor Swift
Welcome to join the open-source community @grok😉
Thrilled to share our latest work, TAPILOT-CROSSING🚀. It's a leap forward for what LLMs can achieve in Interactive Data Analysis. Highlights: 🎯 1024 human-agent interactions for evaluation, involving long code generation and multi-choice questions. 🎯An economical multi-agent…
Prompt Learning: forcing human beings to fit machines Instruct Learning: forcing machines to fit human beings
Google Deepmind presents SIMA the first generalist AI agent to follow natural-language instructions in a broad range of 3D virtual environments and video games. It can complete tasks similar to a human, and outperforms an agent trained in just one setting.
Kudos to the Team! Glad to see that it achieves 37.9 on our CMMMU and 36.6 on MMMU, which is amazing! Try out our CMMMU on lmms-lab.github.io and eval.ai/web/challenges…. Let's begin the Chinese MModal Competition!
[1/5] 🚀 Announcing DeepSeek-VL, sota 1.3B and 7B visual-language models! Paper: arxiv.org/abs/2403.05525 GitHub: github.com/deepseek-ai/De… 📚 Diverse training corpus 👯 Hybrid Vision Encoder 🧠 3-stage training strategy 🆓 Totally free for commercial use and fully open-source
Thanks @_akhaliq for sharing our work! Code is here: github.com/pkunlp-icler/F…
An Image is Worth 1/2 Tokens After Layer 2 Plug-and-Play Inference Acceleration for Large Vision-Language Models In this study, we identify the inefficient attention phenomena in Large Vision-Language Models (LVLMs), notably within prominent models like LLaVA-1.5, QwenVL-Chat…