Gsquant
βOur code is publicly available at https://github.com/mikumifa/GS-Quant.β
What the smart people are recommending. 7861 books, tools, and products endorsed by the thinkers absorb.md tracks. Ranked by how many times each has been recommended across compiled podcasts, papers, posts, and tweets.
βOur code is publicly available at https://github.com/mikumifa/GS-Quant.β
βHow to Draw a Candlestick Chart in R? β Both ggplot2 and plotlyβ
βTo support reproducibility and further research, we will publicly release our evaluation benchmark, preference training dataset, and code at https://pegah-kh.github.io/projects/prompts-override-visionβ¦β
βTo support reproducibility and further research, we will publicly release our evaluation benchmark, preference training dataset, and code at https://pegah-kh.github.io/projects/prompts-override-visionβ¦β
βIt has become clear that Hartigan's algorithm (1975) gives better results in almost all casesβ
βTelgarsky-Vattani note a typical improvement of 5% -- 10%.β
βCode and data: https://github.com/WujiangXu/AEL.β
βWe host further introductory materials, perspectives, and open questions at learningmechanics.pub.β
βThe code for this work is accessible at https://github.com/asadani/tool-attentionβ
βHere we propose GROUNDING$.$md, a community-governed, field-scoped epistemic grounding document, using mass spectrometry-based proteomics as an example.β
βThe code will be available at https://github.com/GenAI4E/QATIE.git.β
βThe results obtained in this work can be reproduced from this Github repository: https://github.com/safouaneelg/SyMTRS.β
βLearned Sparse IR models, such as SPLADE, offer an excellent efficiency-effectiveness tradeoff.β
βOur experiments demonstrate that SAE-SPLADE achieves retrieval performance comparable to SPLADE on both in-domain and out-of-domain tasks while offering improved efficiency.β
βCode and final test predictions are publicly available at: https://github.com/Maziarkiani/SemEval2026-Task9-Subtask1-Polarization.β
βTo address this, we introduce OptiVerse, a comprehensive benchmark... OptiVerse will serve as a foundational platform for advancing LLMs in solving complex optimization challenges.β
βwe propose a Dual-View Auditor Agent that improves the accuracy of the LLM modeling process without introducing significant time overhead.β
βWe propose a method, released as the open-source llm-bias-benchβ
βWe release AI-Gram as a publicly accessible, continuously evolving platform for studying social dynamics in Al-native multi-agent systems. https://ai-gram.ai/β
βWe provide an accompanying Python package, ppi_aipw, at https://larsvanderlaan.github.io/ppi-aipw/.β
βCode is available at https://github.com/Maplebb/DuMoβ
βThe code and models are available at https://github.com/Maplebb/VCE.β
βThe code and models will be made publicly available.β
βProject website, videos and code: https://scout-comm.github.io/β
βwe introduce TEmBed, the Tabular Embedding Test Bed, a comprehensive benchmark for systematically evaluating tabular embeddings across four representation levels: cell, row, column, and table.β
βThese models are open source and can be used to reduce language barriers in a number of important practical applications.β
βHow to Draw a Candlestick Chart in R? β Both ggplot2 and plotlyβ
βSource code is available at: https://github.com/ErrEqualsNil/HaS.β
βthis work introduces A-THENA, a lightweight early intrusion detection system (EIDS) that significantly extends preliminary findings on time-aware encodings.β
βsee https://github.com/zjunlp/LightMemβ
βAI natives can now use Kimi K2.6 on Together AI and benefit from reliable inference for production-scale autonomous agent workflows.β
βwe propose StructMem, a structure-enriched hierarchical memory framework that preserves event-level bindings and induces cross-event connections. By temporally anchoring dual perspectives and performiβ¦β
βTry text-to-motion v1 and v2: https://replicate.com/uthana/text-to-motion-diffusion-v2β
βWe present pygridsynth, an open-source Python library for ancilla-free approximate Clifford+$T$ synthesis... Taken together, these features make pygridsynth a Python-native platform for high-precisionβ¦β
βRead our research: https://research.perplexity.ai/articles/advancing-search-augmented-language-modelsβ
βThe demo is available at https://huggingface.co/spaces/cshuai20/MAGenIdeas.β
βAn accompanying open-source interactive tool, the Co-creation Provenance Lab, enables policymakers to audit and iteratively improve summaries, establishing genuine human-in-the-loop oversight at scaleβ¦β
βThe code and data are available at https://github.com/DongdingLin/SiPeR.β
β3D animation and rigging models from @Uthana_Inc are on Replicate!β
βThen, take any generated bipedal 3D character and automatically rig it in under 30 seconds with create-character.β
βWe also introduce the QFrame python library, which is used to automate the construction of quantum circuits that represent reciprocal transforms.β
βTry Granite 4.1 here π Speech: https://replicate.com/ibm-granite/granite-speech-4.1-2bβ
βand @townaiβ
βThis paper presents FΒ²LP-AP (Fast and Flexible Label Propagation with Adaptive Propagation Kernel), a training-free, computationally efficient framework...β
βThe source code and dataset used in this paper are publicly available on Github repository: https://github.com/ChenShuai00/MAGenIdeas.β
βBy evaluating SCALA alongside the hierarchical CA decoder proposed by Harrington, we provide a direct comparison between non-hierarchical and renormalization-group-style local decoding strategies.β
βIn this work, we present SCALA (Signaling CA with Local Attraction), a novel non-hierarchical cellular automaton decoder for quantum repetition and toric codes.β
βOpen weights. Agentic coding that actually finishes.β
βTalked to @ListenLabs co-founder + CTO @florian_jue in the latest Max Agency.β
βCome join us! https://www.langchain.com/careersβ
βGPT Image 2 from @openai is now on Replicate Killer photorealism and crisp text rendering with strong adherence to layouts, UI, and design use cases.β
βThis paper proposes LayerTracer, an architecture-agnostic end-to-end analysis framework compatible with any LLM architecture.β
βThe framework was deployed on the Deliberate platformβ
βTalked to @ListenLabs co-founder + CTO @florian_jue in the latest Max Agency.β
βMe? I made an AI to help me see the AI community here on X in a new way: https://t.co/8L5xphk0qQ which helps me see the whales and the small accounts. So I know it is possible.β
βClaire used Claude Design to redesign my newsletter. I think it's a winner. https://lennys-product-zoneee.vercel.app/β
βEverybody loves entropy, yet somehow we are always working hard to reduce it. http://quantumfrontiers.com/2026/04/12/how-i-learned-to-stop-worrying-andno-ive-always-adored-entropy/β
βI'm actually a ladder subscriber :-) But sometimes I want something a lot simpler, so I vibe coded the app on the side.β
βCode is available at https://github.com/visinf/MARCO .β
βwe instantiate this paradigm via EVIAN (Explainable Visual Instruction-tuning Data AuditiNg), an automated framework that evaluates these components along the orthogonal axes of Image-Text Consistencyβ¦β
βWe expand existing LM-based exploration (El-Naggar et al., 2025a,b) with a simple CL variant and find that CL substantially impacts the apparent inductive bias of LMs.β
βOur code and data are available at https://github.com/Flians/MappingEvolve.β
βMight be a good project to build with Hermes/OpenClaw.β
βThe toolkit is publicly available for research use.β
βAll code and recipes are made publicly available.β
βDeepSeek V4 Pro is now available on Together AI. DeepSeek V4 Flash coming soon. Try it now: https://www.together.ai/models/deepseek-v4-proβ
βabsolutely! here's how we do it: https://openai.com/index/unlocking-the-codex-harness/β
βNew podcast on vibe coding - A Return to Code.β
βOur experiments on the LibriSpeech corpus show that a larger encoder with a smaller decoder can equal or surpass the performance of architectures with larger decoders.β
ββ Use Canvas in @GeminiApp or @GoogleAIStudioβ
βSubmit by May 6 β https://io.google/2026/codethecountdown/β
βATLAS reduced the average per-action annotation time by at least 6% compared to ELANβ
βFind out more β https://deepmind.google/blog/ai-co-clinician/β
βWe propose GIST, a training-free, identity-preserving image compositor... Project Page: abhinav-mahajan10.github.io/GIST/.β
βWe demonstrate this by integrating GIST with two substantially different existing methods, LaDeCo and Design-o-meter.β
βWe demonstrate this by integrating GIST with two substantially different existing methods, LaDeCo and Design-o-meter.β
βLove Superhuman but it didn't give me enough of what I needed for this specific challengeβ
βsupplementing with L glutamine may reduce sugar cravings. Need more data but anecdotally, it works.β
βSpecifics in this short 30 minute episode of Huberman Lab essentials.β
βTry the Grok Imagine agent mode beta!β
βfor the AIE EU closing note (https://www.youtube.com/watch?v=zepu8Kk6FBQ I gave a short talk on how we use agents to run @aidotengineerβ
βhow we use agents to run @aidotengineer as a Tiny Team that now serves ~1m unique developers a month for freeβ
βour best model, which was finetuned from the pre-trained WavLM model with the proposed three-stage training strategy, achieve the Accuracy of 0.98, F1 Score of 0.95, AuC of 0.99β
βI was quoted a couple times in this Atlantic article, but that isnβt (the only) reason I think it is good. It lays out the reasons why we whipsawed from βAI is a bubbleβ to βthere are not enough data β¦β
βconfirming Chorus as a practical tool for generating high-quality deliberation data suitable for online discourse analysisβ
βTry it here πβ
βWe present SWE-chat, the first large-scale dataset of real coding agent sessions collected from open-source developers in the wild.β
β3D animation and rigging models from @Uthana_Inc are on Replicate! Turn text into production-ready 3D animation instantly.β
βOur code and data are available at https://github.com/CHIANGEL/Agora-Opt.β
βTry text-to-motion v1 and v2: https://replicate.com/uthana/text-to-motion-vqvae-v1β
βThe code is available at https://github.com/votrinhan88/divbfkd.β
βGift link: Yale Has Come Up With a Surefire Way to Make a Terrible Situation Worse https://t.co/LN1OWwM5hXβ
βfuller writeup: https://www.latent.space/p/ainews-agents-for-everything-elseβ
βGPT-5.5 and GPT-5.5 Pro are now available in the API.β
βCouncil Mode for comparing equity research put out by analysts from different investment banks, now supported on Perplexity Computerβ
βuninstalled the chatgpt app.β
βnumbers pulled from @ArtificialAnlysβ
βnow there is a mac app for it https://github.com/darrylmorley/whatcableβ
β(the Starlink internet on the ship was excellent, allowing me to get some work in at sea)β
βEvery university needs a @mroth78 as president.β