absorb.md

What the smart people are recommending. 7786 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.

AllπŸ“š BooksπŸ›  ToolsπŸ“± AppsπŸ’Š SupplementsπŸŽ“ Courses🎬 MoviesπŸ“Ί ShowsπŸ“¦ ProductsπŸ”§ ServicesπŸ“„ PapersπŸ‘€ People🎟 EventsπŸ’» Repos✨ Skills
Timeframe:All timeLast 7 daysLast 30 daysLast 90 days
πŸ›  ToolsΓ—1 mentions

Earth2

β€œEarth-2. We're at the frontier of physical AI, that is physical AI and AI physics”

youtube: Nvidia’s Full-Stack AI Strategy and the Future of Compute β€” by Jensen Huang β€” 2026-04-06
Endorsed by Jensen Huang
Details β†’
πŸ›  ToolsΓ—1 mentions

No Child Left Behind

by George W. Bush

β€œNo Child Left Behind, of course, is the George W. Bush era policy that went into effect in 2002. And if you were growing up in the United States in that time, like I was, you were you were taking test…”

Recommended on The Daily β€” 2026-04-10
Details β†’
πŸ›  ToolsΓ—1 mentions

Every Student Succeeds Act

by President Obama

β€œNo Child Left Behind is repealed and replaced with a different law, the Every Student Succeeds Act under President Obama.”

Recommended on The Daily β€” 2026-04-10
Details β†’
πŸ“Ί ShowsΓ—1 mentions

Idiot

β€œFrom Serial Productions and The New York Times, I'm M. Gessen, and this is The Idiot. Listen wherever you get your podcasts.”

Recommended on The Daily β€” 2026-04-10
Details β†’
πŸ›  ToolsΓ—1 mentions

Tinydinomaly

β€œNotably, Tiny-Dinomaly achieves the best accuracy-efficiency trade-off for edge deployment, matching full-scale localization performance at a fraction of the memory cost.”

paper: Visual Anomaly Detection for Enhanced Autonomous Driving Safety β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Radagent

β€œTo address this, we introduce RadAgent, a tool-using AI agent that generates CT reports through a stepwise and interpretable process.”

paper: RadAgent: Enhancing AI-driven Chest CT Interpretation with Explainable Reasoning β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Datasite

β€œBut Datasite can deliver deal intelligence across every stage of the investment lifecycle, powered by the best available AI models and protected by security standards dealmakers trust. [...] You can m…”

Recommended on Morning Brew Daily β€” 2026-04-10
Details β†’Visit β†—
πŸ“¦ ProductsΓ—1 mentions

Rockin Grandmas Hot Sauce

by Rockin' Grandma's Hot Sauce

β€œYou'll be able to try all four flavors of Rockin' Grandma's Hot Sauce sold on Amazon.”

Recommended on Morning Brew Daily β€” 2026-04-10
Details β†’
πŸ”§ ServicesΓ—1 mentions

Carvanacom

by Carvana

β€œCarvana believes selling your car should be refreshingly simple. Enter your license plate or VIN, get a real offer down to the penny, and schedule a pickup on your time. No surprises. Sell your car to…”

Recommended on Up First from NPR β€” 2026-04-10
Details β†’
πŸ“Ί ShowsΓ—1 mentions

This American Life

β€œThis is Ira Glass. On This American Life, we tell stories about when things change. Like for this guy, David, whose entire life took a sharp, unexpected, and very unpleasant turn.”

Recommended on Up First from NPR β€” 2026-04-10
Details β†’Visit β†—
πŸ“Ί ShowsΓ—1 mentions

Are We There Yet

β€œThat's Brendan Byrne from Central Florida Public Media. He hosts the space podcast, Are We There Yet?”

Recommended on Up First from NPR β€” 2026-04-10
Details β†’
🎟 EventsΓ—1 mentions

Help Freehammond At His Nyc Sentencing Tomorrow

by Occupy Wall Street

β€œ# Help #FreeHammond at His NYC Sentencing Tomorrow”

Details β†’Visit β†—
πŸ“Ί ShowsΓ—1 mentions

Kara Swisher Wants To Live Forever

by Kara Swisher

β€œAs you might know, my new CNN series debuted this past weekend. It's called Kara Swisher Wants to Live Forever.”

Recommended on On with Kara Swisher β€” 2026-04-13
Details β†’
πŸ”§ ServicesΓ—1 mentions

Backmarket

β€œShop now at backmarket.com.”

Recommended on On with Kara Swisher β€” 2026-04-13
Details β†’Visit β†—
πŸ“Ί ShowsΓ—1 mentions

Long Game

β€œThe episode's out now. Search for and follow The Long Game wherever you get your podcasts.”

Recommended on On with Kara Swisher β€” 2026-04-13
Details β†’
πŸ›  ToolsΓ—1 mentions

Rippling

β€œhead to rippling.com slash Kara and sign up today.”

Recommended on On with Kara Swisher β€” 2026-04-13
Details β†’Visit β†—
πŸ“š BooksΓ—1 mentions

Elite Human Capital

β€œand I'll tell you that I I'm thinking about writing a book on the concept of elite human in capital because it it's a topic that has drawn me in it is something that I keep talking about and I keep se…”

Details β†’
πŸ”§ ServicesΓ—1 mentions

Notioncomupstream Pod

β€œ>>> Want to give it a try head over to notion.com/Upstream pod that's all lowercase notion.com/Upstream pod you can try notion for free and when you use our link you're supporting our show gi…”

Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Vruinterpret

by Young-Zhen

β€œOur dataset and code will be released at https://github.com/Young-Zhen/VRU_Interpret .”

paper: LLMs and VLMs Struggle with Viewpoint Rotation in Text-Only Spatial Reasoning β€” 2026-04-17
Details β†’
πŸ“š BooksΓ—1 mentions

Conservative Futurist

β€œI just reading a a book it's called the conservative futurist and his name is James pth pacus and basically you know he he talks about sort of these cycles and you know this sort of cycles of American…”

Details β†’
πŸ“Ί ShowsΓ—1 mentions

Live Players From Turpentine

by s bua

β€œplease enjoy and check out s's podcast Live players from turpentine”

Details β†’
πŸ“„ PapersΓ—1 mentions

Mmwebagent

β€œWe propose MM-WebAgent, a hierarchical agentic framework for multimodal webpage generation that coordinates AIGC-based element generation through hierarchical planning and iterative self-reflection.”

paper: MM-WebAgent: Hierarchical Multimodal AI for Coherent Webpage Generation β€” 2026-04-17
Details β†’Visit β†—
πŸ”§ ServicesΓ—1 mentions

Adquickcom

β€œvisit adi.com today to start reaching your customers in the real world again that's adq ik.com”

Details β†’
πŸ“„ PapersΓ—1 mentions

Rejectiongated Policy Optimization Rgpo

β€œWe propose a new perspective on policy optimization: rather than reweighting all samples by their importance ratios, an optimizer should select which samples are trustworthy enough to drive a policy u…”

paper: Rejection-Gated Policy Optimization Improves RL Reliability and Performance β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Aadvark

β€œIn this paper we present a prototype of AADvark, an agentic system designed for this task.”

paper: AADvark: Advancing Agent-Aided Design for Dynamic CAD Assemblies β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Irs Incongruityresolution Supervision

β€œWe introduce IRS (Incongruity-Resolution Supervision), a framework that decomposes humor understanding into three components”

paper: Structured Reasoning Boosts AI Humor Comprehension β€” 2026-04-17
Details β†’Visit β†—
πŸ›  ToolsΓ—1 mentions

City Journal

β€œyou wrote a great post and City Journal about how Silicon Valley shift away from Democrats is not just about the election it's it's brought in that why don't you sort of give us the lay of the”

Details β†’Visit β†—
πŸ“„ PapersΓ—1 mentions

New New Control Society

by John Asconas

β€œso I have a new essay in the new Atlantis called the new new control society which is really about the how the internet is reshaping politics in our civilization”

Details β†’
πŸ“± AppsΓ—1 mentions

Babel

β€œIf learning a new languag is on your list you absolutely need to check out Babel Babel offers a range of learning tools self-study app lessons live classes and even podcasts which have always been my …”

Details β†’
πŸ“Ί ShowsΓ—1 mentions

Am Edition Of Whats News

β€œAnd here's the AM edition of What's News, the top headlines and business stories moving your world today.”

Recommended on WSJ What’s News β€” 2026-04-10
Details β†’
πŸ”§ ServicesΓ—1 mentions

Subscribewsjcomtake

β€œVisit subscribe.wsj.com slash take on the week to subscribe now.”

Recommended on WSJ What’s News β€” 2026-04-10
Details β†’Visit β†—
πŸ“„ PapersΓ—1 mentions

Our One Demand Is To End Capitalism

by Occupy Wall Street

β€œBlog post by Occupy Wall Street”

Details β†’Visit β†—
πŸ“¦ ProductsΓ—1 mentions

Orchid

β€œnor siki is the founder and CEO of orchid the company making the world's first whole genome embryo screen”

Details β†’Visit β†—
πŸ”§ ServicesΓ—1 mentions

Fundrise Innovation Fund

β€œThe fundrise Innovation fund is finally changing that it's a more than 125 million fund it holds some of the most exciting pre-ipo tech companies in the world and it's designed specifically for indivi…”

Details β†’
πŸ”§ ServicesΓ—1 mentions

Brave Ads

β€œBrave ads offers first-party targeting and it's been Cookie list since day one so you can relax while third party tracking cookies disappear from the web today millions of people turn to ad blockers t…”

Details β†’Visit β†—
πŸ”§ ServicesΓ—1 mentions

Turpentine

β€œhey everyone Eric here at turpentine we're building the First Media outlet for tech people by tech people we're the network behind the show you're listening to right now we have a slate of hit shows a…”

Details β†’Visit β†—
πŸ“¦ ProductsΓ—1 mentions

Iq Bar

β€œIQ Bar is offering our special podcast listeners 20% off all IQ Bar products... text CARA to 64000.”

Recommended on On with Kara Swisher β€” 2026-04-13
Details β†’
πŸ”§ ServicesΓ—1 mentions

Weight Loss By Hims

β€œVisit HIMSS.com slash Cara to get a personalized, affordable plan that gets you.”

Recommended on On with Kara Swisher β€” 2026-04-13
Details β†’
πŸ’Š SupplementsΓ—1 mentions

Multivitamin

β€œI started taking a multivitamin. I was 69 years old and I thought, it's not going to hurt me.”

Recommended on On with Kara Swisher β€” 2026-04-13
Details β†’
πŸ›  ToolsΓ—1 mentions

Policyguided Hybrid Simulation Pghs

β€œWe propose Policy-Guided Hybrid Simulation (PGHS), a dual-process framework that mines transferable decision policies from behavioral trajectories and uses them as a shared alignment layer. This layer…”

paper: Policy-Guided Hybrid Simulation for Merchant Business Diagnosis β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Igsearch

β€œIn this paper, we propose IG-Search, a reinforcement learning framework that introduces a step-level reward based on Information Gain (IG).”

paper: Information Gain Rewards for Enhanced Search-Augmented Reasoning in LLMs β€” 2026-04-17
Details β†’
πŸ’» ReposΓ—1 mentions

Openmobile

β€œWe release data and code at https://njucckevin.github.io/openmobile/ to bridge the data gap and facilitate broader mobile agent research.”

paper: OpenMobile: An Open-Source Framework for Mobile Agent Development β€” 2026-04-17
Details β†’Visit β†—
πŸ›  ToolsΓ—1 mentions

Provoicebench

β€œTo bridge this gap, we introduce ProVoice-Bench, the first evaluation framework specifically designed for proactive voice agents, featuring four novel tasks.”

paper: ProVoice-Bench: Evaluating Proactive Voice Agent Performance β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Sequential Relevance Memory Unit Srmu

β€œIn this work, we introduce the Sequential Relevance Memory Unit (SRMU), a domain- and cleanup-agnostic update rule for VSA-based SAMs.”

paper: SRMU: A Novel Update Rule for Robust Streaming Hyperdimensional Memories β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Hyperspace

β€œWe introduce HyperSpace, an open-source framework that decomposes VSA systems into modular operators for encoding, binding, bundling, similarity, cleanup, and regression.”

paper: HyperSpace: A Framework for Benchmarking Vector Symbolic Architectures β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Cogrid

β€œWe introduce two tools designed to reduce these barriers. The first, CoGrid, is a multi-agent grid-based simulation library with dual NumPy and JAX backends.”

paper: CoGrid and Multi-User Gymnasium: Bridging the Gap in Human-AI Multi-Agent Experimentation β€” 2026-04-17
Details β†’Visit β†—
πŸ›  ToolsΓ—1 mentions

Multiuser Gymnasium Mug

β€œThe second, Multi-User Gymnasium (MUG), translates such simulation environments directly into interactive web-based experiments.”

paper: CoGrid and Multi-User Gymnasium: Bridging the Gap in Human-AI Multi-Agent Experimentation β€” 2026-04-17
Details β†’Visit β†—
πŸ“„ PapersΓ—1 mentions

Discotrace

β€œWe introduce DiscoTrace, a method to identify the rhetorical strategies that answerers use when responding to information-seeking questions.”

paper: DiscoTrace: A Tool for Analyzing Rhetorical Strategies in QA β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Discover And Prove Dap

β€œSecond, we introduce Discover And Prove (DAP), an agentic framework that uses LLM natural-language reasoning with explicit self-reflection to discover answers”

paper: DAP Framework Masters Hard Mode ATP by Discovering Answers via LLM Reasoning Before Proving β€” 2026-04-20
Details β†’
πŸ’» ReposΓ—1 mentions

Sequential Internal Variance Representation Sivr

β€œOur code repository is available online at https://github.com/ponhvoan/internal-variance.”

paper: Sequential Internal Variance Detects LLM Hallucinations with Minimal Assumptions β€” 2026-04-20
Details β†’Visit β†—
πŸ’» ReposΓ—1 mentions

Ttl

β€œOur code is available at https://github.com/figec/TTL.”

paper: Dynamic Textual Adaptation Enables Label-Free Test-Time OOD Detection in VLMs β€” 2026-04-20
Details β†’Visit β†—
πŸ›  ToolsΓ—1 mentions

Memevobench

β€œwe introduce MemEvoBench, the first benchmark evaluating long-horizon memory safety in LLM agents against adversarial memory injection, noisy tool outputs, and biased feedback.”

paper: MemEvoBench Reveals Severe Memory-Induced Safety Drift in LLM Agents β€” 2026-04-20
Details β†’
πŸ›  ToolsΓ—1 mentions

Agentsafetybench

β€œworkflow-style tasks adapted from 20 Agent-SafetyBench environments with noisy tool returns.”

paper: MemEvoBench Reveals Severe Memory-Induced Safety Drift in LLM Agents β€” 2026-04-20
Details β†’
πŸ“„ PapersΓ—1 mentions

Ktoken Merging

β€œIn this paper, we propose K-Token Merging, a latent-space compression framework that merges each contiguous block of K token embeddings into a single embedding via a lightweight encoder.”

paper: K-Token Merging: Latent-Space Compression for LLMs β€” 2026-04-17
Details β†’
πŸ’» ReposΓ—1 mentions

Benchmark Code

β€œWe release the benchmark code as supplementary material to encourage the development of more robust scientific literature novelty metrics.”

paper: Axiomatic Benchmark Reveals Limitations and Synergies in Scientific Novelty Metrics β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Neatnc

β€œInspired by these biological principles, we developed NEATNC, a Neuro-Evolution of Augmenting Topology guided Navigation Cells. The goal of the paper is to improve NEAT algorithm performance in path p…”

paper: Bio-inspired Neural Networks for Dynamic Robot Path Planning β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Large Scale Small Ode Lassodepower

β€œHence, this paper proposes LArge Scale Small ODE (LASS)-ODE-Power, a learning framework for general-purpose time-domain prediction.”

paper: Foundation Models for Power System Dynamics β€” 2026-04-17
Details β†’
πŸ’» ReposΓ—1 mentions

Made

by Fraunhofer HHI

β€œOur work is publicly available at https://hhi.fraunhofer.de/aml-demonstrator/made-benchmark.”

paper: MADE: A Dynamic Benchmark for Medical Device Adverse Event Classification β€” 2026-04-17
Details β†’Visit β†—
πŸ“„ PapersΓ—1 mentions

Quantcodebench

β€œIn this work, we present QuantCode-Bench, a benchmark for the systematic evaluation of modern LLMs in generating strategies for the Backtrader framework from textual descriptions in English.”

paper: QuantCode-Bench: Evaluating LLMs in Algorithmic Trading Strategy Generation β€” 2026-04-17
Details β†’Visit β†—
πŸ›  ToolsΓ—1 mentions

Groth

β€œI put in a a few prompts into Groth into Open AI and Google Gemini, Anthropic Cloud.”

youtube: Cognitive Architectures Enable Truly Autonomous AI, Outperforming Chat-Centric Paradigms β€” by Robert Scoble β€” 2026-04-06
Endorsed by Robert Scoble
Details β†’
πŸ“Ί ShowsΓ—1 mentions

On Investing

β€œYou can download the latest episode and subscribe at schwab.com slash on investing or wherever you get your podcasts.”

Recommended on Morning Brew Daily β€” 2026-04-13
Details β†’
πŸ“¦ ProductsΓ—1 mentions

Kerbal Space Program

β€œthere is this space simulator game called Kerbal Space Program. It's pretty niche, honestly. It's about building and flying rockets for a species of green aliens called Kerbals. But after Artemis II l…”

Recommended on Morning Brew Daily β€” 2026-04-13
Details β†’
πŸ’» ReposΓ—1 mentions

Adam Jacobs Collection

β€œYou can just go to Adam Jacobs, just Google Adam Jacobs collection.”

Recommended on Morning Brew Daily β€” 2026-04-13
Details β†’
πŸ›  ToolsΓ—1 mentions

Backtrader

β€œIn this work, we present QuantCode-Bench, a benchmark for the systematic evaluation of modern LLMs in generating strategies for the Backtrader framework from textual descriptions in English.”

paper: QuantCode-Bench: Evaluating LLMs in Algorithmic Trading Strategy Generation β€” 2026-04-17
Details β†’Visit β†—
πŸ›  ToolsΓ—1 mentions

Dr Rtl

β€œTo address these limitations, we present Dr. RTL, an agentic framework for RTL timing optimization in a realistic evaluation environment, with continual self-improvement through reusable optimization …”

paper: Autonomous Agent Optimizes RTL Design with Self-Improving Skill Library β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Specguard

β€œWe propose SpecGuard, a verification-aware speculative decoding framework that performs step-level verification using only model-internal signals.”

paper: SpecGuard: In-Model Verification for Efficient LLM Multi-Step Reasoning β€” 2026-04-17
Details β†’Visit β†—
πŸ“„ PapersΓ—1 mentions

Xqmeval

β€œIn this work, we propose XQ-MEval, a semi-automatically built dataset covering nine translation directions, to benchmark translation metrics.”

paper: Cross-lingual Scoring Bias in Translation Metric Evaluation β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Dynafford

β€œTo address this limitation, we introduce DynAfford, a benchmark that evaluates embodied agents in dynamic environments where object affordances may change over time and are not specified in the instru…”

paper: ADAPT: Enhancing Embodied Agent Planning with Dynamic Affordance Reasoning β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

System

β€œHence, we contribute a comprehensive dataset, \system, comprising scientific architecture images, their corresponding textual descriptions, and associated DOT code representations.”

paper: Text2Arch: Bridging Natural Language and Scientific Architecture Diagrams β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Ieascache

β€œMoving beyond this, we propose \textit{IE-as-Cache}, a framework that repurposes IE as a cognitive cache to enhance agentic reasoning.”

paper: IE-as-Cache: Enhancing Agentic Reasoning with Information Extraction β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Confguide

β€œWe address this issue by introducing ConfGuide, a novel LtG approach that generates more succinct and targeted guidance. To this end, it employs conformal risk control to select a set of outcomes, ens…”

paper: ConfGuide: Conformal Guidance for Hybrid Decision Making β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Ratatool

β€œIn this work, we introduce RaTA-Tool, a novel framework for open-world multimodal tool selection.”

paper: RaTA-Tool: Retrieval-based Tool Selection for Multimodal LLMs in Open-World Settings β€” 2026-04-17
Details β†’
πŸ’» ReposΓ—1 mentions

Openskytraffic

β€œCode available at https://github.com/Weijiang-Xiong/OpenSkyTraffic”

paper: Universal GMM Output Layer Enables Probabilistic Traffic Forecasting Without Model or Training Changes β€” 2026-04-20
Details β†’Visit β†—
πŸ›  ToolsΓ—1 mentions

Omnisend

β€œThat's why I can recommend a platform called Omnisend.”

youtube: Perplexity AI's Rapid Ascent and the Future of AI-Powered Interactions β€” by Aravind Srinivas β€” 2026-04-06
Endorsed by Aravind Srinivas
Details β†’Visit β†—
πŸ“š BooksΓ—1 mentions

This Car Sucks

by Randy Pressgrove

β€œOur guest is Randy Pressgrove, the author of This Car Sucks. I love that title.”

Recommended on The WealthAbility Show with Tom Wheelwright, CPA β€” 2026-04-10
Details β†’Visit β†—
πŸ”§ ServicesΓ—1 mentions

Sidgoldscom

β€œyea! http://sidgolds.com”

tweet: Swyx Revives Broadway Solo Performance After 18-Year Hiatus β€” by swyx β€” 2026-04-13
Endorsed by swyx
Details β†’Visit β†—
πŸ›  ToolsΓ—1 mentions

Patent Citation Spectroscopy Pcs

β€œThe interactive tool is free-to-use at: www.leydesdorff.net/pcs/”

Details β†’Visit β†—
πŸ“„ PapersΓ—1 mentions

A Hybrid Approach That Combines Large Language Models Llms With Three Newly Created And Curated Vocabularies To Detect And Explain Hate Speech In English French And Greek

β€œIn this paper, we present a hybrid approach that combines Large Language Models (LLMs) with three newly created and curated vocabularies to detect and explain hate speech in English, French, and Greek…”

paper: Hybrid LLM Approach for Explainable Hate Speech Detection β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Retrievalgrounded Llm Systems

β€œRetrieval-grounded LLM systems may have value as adjunct tools for CGM review, patient education, and preconsultation preparation.”

paper: LLM Outperforms Clinicians in Diabetes Counseling β€” 2026-04-17
Details β†’
πŸ’» ReposΓ—1 mentions

Panguace

β€œThis paper rewrites our earlier draft around the system that was actually implemented and archived in the repository: a sample-level 1B to 7B cascade for the shared-8 EduBench benchmark.”

paper: Pangu-ACE: Adaptive Cascaded Experts for Educational Response Generation β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Llm Fallacy

β€œThis paper introduces the LLM fallacy, a cognitive attribution error in which individuals misinterpret LLM-assisted outputs as evidence of their own independent competence, producing a systematic dive…”

paper: The LLM Fallacy: Misattributing AI-Assisted Output to Personal Competence β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Machine Unlearning For Large Language Models Llms

β€œIn this paper, we recast LLM unlearning as an asymmetric two-task problem: retention is the primary objective and forgetting is an auxiliary.”

paper: Gradient Synthesis for LLM Unlearning Prioritizes Retention β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Racer Retrievalaugmented Contextual Rapid Speculative Decoding

β€œWe propose RACER (Retrieval-Augmented Contextual Rapid Speculative Decoding), a lightweight and training-free method that integrates retrieved exact patterns with logit-driven future cues. This unific…”

paper: RACER: Accelerating LLM Inference with Hybrid Speculative Decoding β€” 2026-04-17
Details β†’
πŸ’» ReposΓ—1 mentions

Hkr04racer

by hkr04

β€œOur source code is available at https://github.com/hkr04/RACER.”

paper: RACER: Accelerating LLM Inference with Hybrid Speculative Decoding β€” 2026-04-17
Details β†’Visit β†—
πŸ“„ PapersΓ—1 mentions

Climatecause

β€œWe introduce ClimateCause, a manually expert-annotated dataset of higher-order causal structures from science-for-policy climate reports, including implicit and nested causality. Cause-effect expressi…”

paper: ClimateCause: A Dataset for Causal Reasoning in Climate Reports β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Continual Unlearning In Real Time With Ensured Preservation Of Llm Knowledge

β€œTo address these issues, we propose Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge (CURaTE).”

paper: Real-Time Continual Unlearning in LLMs β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Medimageedu

β€œWe introduce MedImageEdu, a benchmark for multi-turn, evidence-grounded radiology patient education. Each case provides a radiology report with report text and case images.”

paper: MedImageEdu: A New Benchmark for Multi-Modal Patient Education β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Spagbias

β€œWe introduce SPAGBias - the first systematic framework to evaluate spatial gender bias in LLMs.”

paper: LLMs Exhibit Structured Spatial Gender Bias Beyond Public-Private Dichotomies β€” 2026-04-17
Details β†’
✨ SkillsΓ—1 mentions

Nest

β€œIn this paper, we introduce a new task, NEgative-conSTrained (NEST) KGQA, where each question contains at least one negative constraint, and a corresponding dataset, NestKGQA.”

paper: CUCKOO Framework for Negative-Constrained Knowledge Graph Question Answering β€” 2026-04-17
Details β†’
✨ SkillsΓ—1 mentions

Nestkgqa

β€œIn this paper, we introduce a new task, NEgative-conSTrained (NEST) KGQA, where each question contains at least one negative constraint, and a corresponding dataset, NestKGQA.”

paper: CUCKOO Framework for Negative-Constrained Knowledge Graph Question Answering β€” 2026-04-17
Details β†’
πŸ›  ToolsΓ—1 mentions

Pylf

β€œWe also design PyLF, a Python-formatted logical form, since existing logical forms are hardly suitable to express negation clearly while maintaining readability.”

paper: CUCKOO Framework for Negative-Constrained Knowledge Graph Question Answering β€” 2026-04-17
Details β†’
πŸ”§ ServicesΓ—1 mentions

M365copilotcom

β€œPisa Copilot handles the spreadsheets. Learn more at M365copilot.com slash work.”

Recommended on WSJ What’s News β€” 2026-04-10
Details β†’Visit β†—
πŸ›  ToolsΓ—1 mentions

Cuckoo

β€œTo mitigate their semantic complexity, we present a novel framework named CUCKOO, specialized to multiple-constrained questions and ensuring semantic executability.”

paper: CUCKOO Framework for Negative-Constrained Knowledge Graph Question Answering β€” 2026-04-17
Details β†’
πŸ“„ PapersΓ—1 mentions

Hess Et Al Phys Rev Lett 130 207001 2023

by Hess et al.

β€œIn this comment, we show that the model introduced in Hess et al. Phys. Rev. Lett. {\bf 130}, 207001 (2023) fails the topological gap protocol (TGP)”

Details β†’
πŸ“„ PapersΓ—1 mentions

Pikulin Et Al Arxiv210312217

by Pikulin et al.

β€œfails the topological gap protocol (TGP) (Pikulin et al., arXiv:2103.12217”

Details β†’Visit β†—
πŸ“¦ ProductsΓ—1 mentions

Spotify Wrapped

β€œWe all know you know the end of year December Spotify wrapped. Um they get 100 million shares every December of that thing.”

youtube: Distribution is the New Moat: Seven Strategies for AI-Era Growth β€” by Greg Isenberg β€” 2026-04-10
Endorsed by Greg Isenberg
Details β†’Visit β†—
πŸ”§ ServicesΓ—1 mentions

Vibes

β€œVibes is built by game industry veterans. It runs on AI-powered targeting ... Go to VYBS.co and get yourself the best loyalty platform in mobile gaming.”

Recommended on Deconstructor of Fun β€” 2026-04-13
Details β†’Visit β†—
πŸ”§ ServicesΓ—1 mentions

9to5maccomjoin

β€œYou can find an ad free version of the show at nine to five mac dot com slash join for $5 a month or $50 a year.”

Recommended on 9to5Mac Daily β€” 2026-04-10
Details β†’Visit β†—
πŸ”§ ServicesΓ—1 mentions

Project 11

β€œAlex, it's so great to have you here on the Defined podcast. Welcome. Yeah, it's amazing to be here. Thanks for having me. Project 11 is a company that does research and builds at the intersection of …”

Recommended on The Defiant - DeFi Podcast β€” 2026-04-10
Details β†’
πŸ’» ReposΓ—1 mentions

Lorec

β€œThe implementation is available at https://github.com/Git-King-Zhan/LoReC.”

paper: LoReC Enhances LLMs for Graph Tasks via Attention Redistribution, Information Re-injection, and Logit Contrast β€” 2026-04-21
Details β†’Visit β†—
← PreviousPage 38 of 78Next β†’