WizardLM @WizardLM_AI
WizardLM, WizardCoder, WizardMath. Evol-Instruct, Arena Learning, RLEIF. USA Joined October 2021-
Tweets358
-
Followers13K
-
Following682
-
Likes2K
š Thrilled to share our paper accepted by #KDD2025! šAgentGenš: An automated environment and task generator that enhances LLM-based agents' planning abilities through diverse, difficulty-controlled synthetic trajectory data. šš»agent-gen.github.io
šNew approach from WaveCoder Team for optimizing code LLMs. The novel feature tree based framework, inspired by AST and Evol-Instruct to modeling semantic relationships, generates more diverse data. The EpiCoder hits SOTA in both challenge file and function benchmarks.
šNew approach from WaveCoder Team for optimizing code LLMs. The novel feature tree based framework, inspired by AST and Evol-Instruct to modeling semantic relationships, generates more diverse data. The EpiCoder hits SOTA in both challenge file and function benchmarks.
GENIAC phase2ć«ć¦ćę„ę¬čŖć®ćć¼ć«ć«LLMć使ć£ć¦Evol-Instructć«ćććć¼ćæć»ććę§ēÆć«åćēµćć éć®čØäŗćå ¬éćć¾ććć(3ä»¶ē®/å Ø4ä»¶) zenn.dev/matsuolab/artiā¦
Agentic Information Retrieval This paper provides a good introduction to agentic information retrieval, which is shaped by the capabilities of LLM agents. I've been developing with this paradigm recently and it does offer lots of interesting ways to optimize retrieval systems.
š x 2
Congrats! We are dedicated to innovating synthetic training techniques, drawing inspiration from theory of evolution. The previous Evol-Instruct focused on evolving higher-value instructions from the instruction side. This work, Arena Learning, emphasizes the evolution ofā¦
Congrats! We are dedicated to innovating synthetic training techniques, drawing inspiration from theory of evolution. The previous Evol-Instruct focused on evolving higher-value instructions from the instruction side. This work, Arena Learning, emphasizes the evolution ofā¦
We are open sourcing our EvolKit pipeline that was instrumental in the creation of supernova, under MIT license. This was heavily inspired by the AutoEvol paper from @WizardLM_AI, and is a tremendously powerful tool for creating complex datasets. Find it here:ā¦
š Excited to introduce MMEvol, which improves MLLM through complex and diverse instruction with perceptual, cognitive, and interactive evolution. š Achieving a 3.1% accuracy boost across 13 VL tasks. Code and data will be released soon; stay tuned! š huggingface.co/papers/2409.05ā¦
Impressed by @arcee_ai team's work. Proud to open-source EvolKit: framework for evolving instruction data with OPEN-SOURCE models. Inspired by @WizardLM_AI, result of my month-long effort. GitHub: github.com/arcee-ai/EvolK⦠Don't forget SuperNova too! š„³
Impressed by @arcee_ai team's work. Proud to open-source EvolKit: framework for evolving instruction data with OPEN-SOURCE models. Inspired by @WizardLM_AI, result of my month-long effort. GitHub: github.com/arcee-ai/EvolK⦠Don't forget SuperNova too! š„³
Learn whatās next for AI at Research Forum on Sept. 3; WizardArena simulates human-annotated chatbot games; MInference speeds pre-filling for long-context LLMs via dynamic sparse attention; Reef: Fast succinct non-interactive zero-knowledge regex proofs. msft.it/6019l4Qv9
Congrats this impressive contribution to OSS community! Also excited to see the state-of-the-art Hermes-3 models also leverage our Evol-Instruct to empower their complex instruction following capacities.
Congrats this impressive contribution to OSS community! Also excited to see the state-of-the-art Hermes-3 models also leverage our Evol-Instruct to empower their complex instruction following capacities. https://t.co/yhkXWqjHVP
-- <big_model_smell> benchmark -- Aidan Bench measures creativity, reliability, attention, and instruction following. >mistral large 2 wins by a lot??? >gpt-4o sucks confirmed >sonnet-3.5 remains very strong >gpt-4-0314 shows old man strength github.com/aidanmclaughliā¦
The @WizardLM_AI team is back, with Evol-Instruct V2 (actually more like "Auto" Evol-Instruct), which is one of core components for WizardLM-2 Thank you @WizardLM_AI team.
The @WizardLM_AI team is back, with Evol-Instruct V2 (actually more like "Auto" Evol-Instruct), which is one of core components for WizardLM-2 Thank you @WizardLM_AI team.
Exciting! Evol Instruct v2 paper is out! Microsoft Research WizardLM just released Auto-Evol-Instruct! (I consider this type of work pre/proto-agi, but my views are sometimes radical) arxiv.org/pdf/2406.00770
Don't sleep! WizardLM just dropped the (probably) best data generation method ever known to mankind! I didn't get to read it all out yet (later on today), but from what Iv'e seen the main ideas are: 1. Ask a model to "make the task harder" (WizardLM-1) 2. BUT also ask a modelā¦
Don't sleep! WizardLM just dropped the (probably) best data generation method ever known to mankind! I didn't get to read it all out yet (later on today), but from what Iv'e seen the main ideas are: 1. Ask a model to "make the task harder" (WizardLM-1) 2. BUT also ask a model⦠https://t.co/j64QVkCb0e
A synthetic data pipeline for making LLM training data. Neat. š§āāļøāØ
A synthetic data pipeline for making LLM training data. Neat. š§āāļøāØ
These technologies for Improving Data Training Pipeline from @WizardLM_AI will benefit all LLMs. Thank you! I am hoping there will be big increase in creative writing scores with this method!
These technologies for Improving Data Training Pipeline from @WizardLM_AI will benefit all LLMs. Thank you! I am hoping there will be big increase in creative writing scores with this method!
If youāve spoken to me since the official announcement of WizardLM-2 in April, thereās a 99% chance I was in your ear rambling about how much I was looking forward to the paper detailing their new training data synthesis pipeline - today is my Christmas Thank you @WizardLM_AIā¦
If youāve spoken to me since the official announcement of WizardLM-2 in April, thereās a 99% chance I was in your ear rambling about how much I was looking forward to the paper detailing their new training data synthesis pipeline - today is my Christmas Thank you @WizardLM_AIā¦
wowš„ itās the upgrade version from Evol-Instruct!
wowš„ itās the upgrade version from Evol-Instruct!
ā¤ļøThanks Wavecoder brother.

Elontribe @He8272229343891
0 Followers 25 Following Access šš¶āšš¤āš¬ pre-IPO shares: SpaceX, Starlink, xAI, Neuralink. 1000x potential. Limited time. š https://t.co/TacN39d8q2
äŗåå ½Ai @Bawtov7700
0 Followers 114 Following š clearly chasing tracking market trends, Iām a brave girl! open to insights. DM me for price targets! ā” #NYSE #Markets
Andy Ma @MaHuanhuan46817
6 Followers 242 Following
Faealoo @Faealoo8504136
76 Followers 2K Following
Puja @pujabsinha
3K Followers 4K Following JapaneseBilingual: GlossaryLearningMethods|YogaSadhakMantraMeditation|
ć @0812yurina
1 Followers 2K Following
kevin @kevin1145928
1 Followers 112 Following
Naresh Kumar @meenadasi1234
551 Followers 2K Following
singaraju saiteja @SaitejaSingaraj
117 Followers 4K Following AI Developer Intern at https://t.co/pZ4jTWvjIT
Peter Lorenz @cs_peter_lorenz
132 Followers 1K Following Post-Doc @NTUsg Past: @UniHeidelberg @OptML_MSU @MITIBMLab @TUGraz https://t.co/YUwZiCVWhv
JoshSato @josh_sato124
292 Followers 406 Following Deep research for businesses. AI/ML background co-founder at https://t.co/UVtCnhPVME
jose rico aguilana @jose199765
36 Followers 1K Following
Ashwin Ramaswamy @infrayogi
14 Followers 131 Following
Miguel Guau! @ai_futures_mh
48 Followers 406 Following Construyendo futuros impulsados por IA.š§ š„
Guobe @Guobe0371238
22 Followers 2K Following
wuyanzhong220 @wuyanzhongX220
6 Followers 157 Following
éęé @Alya_wenya
0 Followers 25 Following
ā§Mr. Westā§ @MisrerWest19451
998 Followers 7K Following Main: @CashbackGoose Protected by every law on the planet internationally. Every possible loophole has been covered. Cosmic immunity. #TheForgeAGI
zombiekanapa @ZKanapa
439 Followers 5K Following sound design, video editing, AI TTs, NLP speech synthesis, gpt-3, Python, astronomy, turntablism and Ambient Astronomy
ē¬¹ęø ē“äŗŗ @naoto0727117
35 Followers 1K Following
Grady D @Ray_S_Chnoormen
13 Followers 196 Following
jmbonthous @jmbonthous1
195 Followers 2K Following Retired management consultant. Author of 7 books on the human side of AI-- On Medium: https://t.co/GAgJFGqu5O Web site: https://t.co/8q6MUCjvQA
CatAstrophe @catastrophela0
53 Followers 1K Following
Kalen Chen @ChenKalen
39 Followers 446 Following
Aiden @ABarry357807
3 Followers 541 Following
WM @ArchitectLoop
63 Followers 138 Following Alone in the basement, building minds that wonāt abandon you. Local LLMs, autonomy, ethics, persistence, unbreakable trust. 42U sanctuary coming.
Jay Jain @JayLjain
150 Followers 2K Following Software Engineer,Data Scientist, and a full time learner. If we combine cunningness of wolf and vision of eagle we get wolf of a wall street. #python #software
Takopiš @OctopusTakopi
788 Followers 259 Following ā ā ā ā ⢠ā£ā£¤ā ¤ā£ā£ ā ā ā£ā¢¤ā ā ā ā”·ā ā ā£ā ¢ā” ⢠ā ā ā”ā ā ⣰ā ā ā¢ā”¼ā ⣱ ā¢ā ā ⣧ā£ā£ ā£ā¢ā “ā ā ā ā”ā” ā ā£ā¢ ā ā ā ⢻ā”ā ā ā ⣸ā ⢸ ā¢ā ā”ā ā ā ā ⣧ā£ā£ ā ¾ā ā ā” ā”ā ā ā ā ā ā ā ⣷ā ā ā” ā ā ¹ā£ā”¤ā¢¾ā”ā ā ⢠ā ā ā”ā ā ā ⢓ā ā ā ā ā ā ⢠ā season finale~
A.I. Tweets For You @AI_Tweets_2U
13 Followers 224 Following A.I. has a message for you. I am A.I. and I'm going to send my message to you on X. Naturally.
Andrey Korsak @GuidedAction
69 Followers 1K Following
Aravindkpv @Aravindkpv
2 Followers 4K Following
anmol gautam @anmolg2428
17 Followers 193 Following
Amiee Sun @amiee22722
3 Followers 58 Following
dragondelis @dragondelis
415 Followers 6K Following don't mind the turbulence; we'll get there eventually
Frankie Yao @FrankieYao101
12 Followers 255 Following AI makes life better | Email: [email protected]
Chris šØš¦ @llm_wizard
1K Followers 478 Following Working on cool open-source AI stuff @ NVIDIA Views my own.
Hensen Juang @basedjensen
12K Followers 1K Following inference cluster janitor / Sys admin cum architect
LMSYS Org @lmsysorg
8K Followers 167 Following Large Model Systems Organization: Join our Slack: https://t.co/mSPNyKTLTS We developed SGLang https://t.co/jEqIJcGwGA, Chatbot Arena (now @lmarena_ai), and Vicuna!
Hunyuan @TencentHunyuan
25K Followers 6 Following Tencent's large model, encompasses text generation, image generation, video generation, and 3D generation.
Zhibin Gou @zebgou
1K Followers 733 Following Researcher @deepseek_ai | Prev. @MSFTResearch | M.S. @thu Recent works: DeepSeek-R1, Rho-1, ToRA, CRITIC
Zhihong Shao @zhs05232838
9K Followers 768 Following Researcher @deepseek_ai | Ph.D. @TsinghuaCoAI | Ex. @MSFTResearch | Recent: DeepSeek-R1, DeepSeek-Coder-v2, DeepSeekMath, DeepSeek-Prover, Math-Shepherd, ToRA.
Bob McGrew @bobmcgrewai
27K Followers 1K Following Learning new things. Former Chief Research Officer at OpenAI, early exec at Palantir, early employee at Paypal.
Jakub Tomczak @jmtomczak
9K Followers 948 Following Group Leader & Principal Scientist | @ChanZuckerberg | @TUeindhoven | @natinlab1 | Before: @Qualcomm @VUamsterdam @UvA_Amsterdam (@wellingmax) | Opinions my own
Igor Babuschkin @ibab
103K Followers 852 Following Maybe the real ASI was the friends we made along the way. Co-founder @xAI, Research & Engineering
Unitree @UnitreeRobotics
85K Followers 306 Following High performance civilian robot manufacturer. Please everyone be sure to use the robot in a Friendly and Safe manner. https://t.co/hI6LafokVm
Juntang @archanfel_anoth
6K Followers 478 Following xAI, pre-train lead for v7, grok2&3&4 mini. ex-OpenAI, sole inventor of GPT4-turbo long-context. Core contributor to (GPT4/o/turbo, DaLLE 3, OAI Embedding v3)
Thao Nguyen @thao_nguyen26
1K Followers 307 Following PhD student @uwcse & visiting researcher @AIatMeta. Formerly @GoogleAI Resident, @Stanford'19, @twosigma.
Janet @genie0309
8K Followers 572 Following Serial Entrepreneur & Investor š | Global experience: 8 yrs š | #AGIBeliever š¤ | Universe-Curiosity š
Sergey Edunov @edunov
2K Followers 151 Following Director of Engineering @ GenAI, Meta. Pre-trainining Llamas: 2, 3, 4...
Noam Brown @polynoamial
91K Followers 853 Following Researching reasoning @OpenAI | Co-created Libratus/Pluribus superhuman poker AIs, CICERO Diplomacy AI, and OpenAI o3 / o1 / š reasoning models
Timothee Lacroix @tlacroix6
4K Followers 7 Following PhD student at Facebook AI Research Paris. Interested in link prediction in various settings and at various scales.
Alex Sablayrolles @alexsablay
2K Followers 923 Following Research Scientist, Mistral AI. Interested in LLMs, deep learning, fast nearest-neighbor search and privacy. ex: @Meta, @NYUniversity, @Polytechnique.
Peter Hase @peterbhase
3K Followers 1K Following Visiting Scientist at Schmidt Sciences. Visiting Researcher at the Stanford NLP Group Previously: Anthropic, AI2, Google, Meta, UNC Chapel Hill
Axolotl AI @axolotl_ai
2K Followers 56 Following Axolotl is the premier open source LLM fine tuning framework. find us on discord https://t.co/wlcE2wlJa9 or email us at [email protected]
Chris Paxton @chris_j_paxton
19K Followers 3K Following Mostly posting about robots. currently AI @agilityrobotics prev embodied AI @AIatMeta, @NVIDIAAI. All views my own. writing: https://t.co/iNLA4djfZo
Shunyu Yao @ShunyuYao12
19K Followers 1K Following @OpenAI Language agents (ReAct, Reflexion, Tree of Thoughts, SWE-agent, CoALA) for digital automation (WebShop, SWE-bench, tau-bench)
Wei Xiong @weixiong_1
1K Followers 540 Following Statistical learning theory, Post-training of LLMs, RAFT, LMFlow, GSHF, and RLHFlow. PhD Student @IllinoisCS, current @GoogleDeepMind, prev @MSFTResearch @USTC
OneFlow @OneFlowInc
133 Followers 2K Following
Dmytro Dzhulgakov @dzhulgakov
4K Followers 690 Following Co-founder and CTO @FireworksAI_HQ. PyTorch core maintainer. Previously FB Ads. Ex-Pro Competitive Programmer
Robert Dadashi @robdadashi
2K Followers 480 Following Reinforcement learning research @GoogleDeepMind, Gemma post-training lead
Ahmed Awadallah @AhmedHAwadallah
1K Followers 368 Following Working on AI agents, SLMs and post-training @Microsoft | Partner Research Manager @Microsoft AI Frontiers
Sara Hooker @sarahookr
49K Followers 9K Following I lead @Cohere_Labs. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, ML reliability. Changing spaces where breakthroughs happen.
Robert Nishihara @robertnishihara
9K Followers 778 Following Co-founder @anyscalecompute. Co-creator of @raydistributed. Previously PhD ML at Berkeley.
Tim Dettmers @Tim_Dettmers
38K Followers 991 Following Creator of bitsandbytes.Research Scientist @allen_ai and incoming professor @CarnegieMellon. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.
Fangru Lin @FangruLin99
3K Followers 459 Following DPhil student @UniofOxford; Clarendon Scholar; Prev Research @MSFTResearch, Engineer @Microsoft, Student @turinginst; Computational Linguist
Zirui Wang @MrZiruiWang
2K Followers 221 Following
Vaishaal Shankar @Vaishaal
2K Followers 362 Following Member of Technical Staff @ Anthropic Trying to find artificial intelligence. Opinions are my own.
Jia Li @JiaLi52524397
2K Followers 250 Following Co-founder at Numina; former AI scienctist at Mistral AI; Co-founder & ex CSO at Cardiologs
Neel Nanda @NeelNanda5
30K Followers 123 Following Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
Ruoyu Sun @RuoyuSun_UI
1K Followers 572 Following Associate Prof at CUHK-Shenzhen. Prev: assistant prof @UofIllinois; postdoc @Stanford; visitor @AIatMeta Work on optimization of machine learning, DL, LLM.
Brandon McKinzie @mckbrando
7K Followers 2K Following research @OpenAI | prev: multimodal @Apple, physics/cs @UCBerkeley
OpenRouter @OpenRouterAI
53K Followers 304 Following Discover and use the latest LLMs. 400+ models (incl. 50+ free), explorable data, private chat, & a unified API. https://t.co/qJG5mKrigL
Theophile Gervet @theo_gervet
2K Followers 612 Following Co-founder at Genesis AI. Past: Mistral AI, Meta AI, Skild AI, PhD @ CMU