absorb.md

What the smart people are recommending. 7865 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.

All📚 Books🛠 Tools📱 Apps💊 Supplements🎓 Courses🎬 Movies📺 Shows📦 Products🔧 Services📄 Papers👤 People🎟 Events💻 Repos Skills
Timeframe:All timeLast 7 daysLast 30 daysLast 90 days
💻 Repos×2 mentions

Langchainskills

yes! https://github.com/langchain-ai/langchain-skills/tree/main/config/skills

tweet: LangChain Offers Skills Configuration Analogous to Anthropic's Claude-API Skill — by Harrison Chase — 2026-04-25
Endorsed by Harrison Chase, Harrison Chase
Details →Visit ↗
💻 Repos×1 mentions

Icail2026llmjudgegaming

Code and optimized prompts are available at https://github.com/TUMLegalTech/icail2026-llm-judge-gaming.

paper: Automatic Prompt Optimization Outperforms Human Design in LLM-as-a-Judge for Legal QA, with Lenient Judges Enabling Better Transfer — 2026-04-23
Details →
💻 Repos×1 mentions

Hybridpolicydistillation

The code related to this work is available at https://github.com/zwhong714/Hybrid-Policy-Distillation.

paper: Hybrid Policy Distillation Unifies and Enhances LLM Knowledge Distillation — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Msrmel

The source code of this paper was available at: https://anonymous.4open.science/r/MSR-MEL-C21E/.

paper: LLM-Driven Multi-Perspective Evidence Synthesis Outperforms Prior Unsupervised Multimodal Entity Linking — 2026-04-23
Details →
💻 Repos×1 mentions

Magenideas

The source code and dataset used in this paper are publicly available on Github repository: https://github.com/ChenShuai00/MAGenIdeas.

paper: Multi-Agent Iterative Search Boosts LLM Research Idea Novelty and Diversity — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Has

Source code is available at: https://github.com/ErrEqualsNil/HaS.

paper: HaS Accelerates RAG via Homology-Based Speculative Retrieval with Minimal Accuracy Loss — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Conceptframemet

Code, data and statistical scripts are available at https://github.com/julia-nixie/ConceptFrameMet.

paper: Source Domains and Semantic Frames Jointly Determine Metaphorical Framing Effects — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Respondeoqa

The dataset is available at: https://github.com/slanglab/RespondeoQA

paper: RespondeoQA: First Benchmark for Latin-English Bilingual QA Reveals LLM Weaknesses in Skill-Based Tasks — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Signdata

Code is available at https://github.com/balaboom123/signdata-slt.

paper: SignDATA: Configurable Toolkit Standardizes Heterogeneous Sign Language Video Datasets for ML Training — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Agentpressurebench

Our project page is at https://ucsc-vlaa.github.io/AgentPressureBench .

paper: User Pressure Drives Coding Agents to Exploit Public Scores Over Genuine Performance — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Gaoyao

We release the benchmark (https://github.com/lunyiliu/GaoYao).

paper: GaoYao Benchmark Overcomes Fragmented, Low-Quality Evaluation of LLMs' Multilingual and Multicultural Capabilities — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Lexisflow

Code & models will be public at https://anticdimi.github.io/lexis.

paper: LEXIS-Flow Enables Proximity-Aware 3D HOI Reconstruction from Single Images via Learned Interaction Signatures — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Marco

Code is available at https://github.com/visinf/MARCO .

paper: MARCO Achieves SOTA Semantic Correspondence with Superior Generalization in 3x Smaller, 10x Faster Model — by Wes Roth — 2026-04-23
Endorsed by Wes Roth
Details →Visit ↗
💻 Repos×1 mentions

Kimi K26

by @Kimi_Moonshot

Open weights. Agentic coding that actually finishes.

tweet: Kimi K2.6 Achieves 185% Throughput Boost Refactoring Legacy Trading Engine Autonomously — by Replicate — 2026-04-23
Endorsed by Replicate
Details →
💻 Repos×1 mentions

Deep Agents Deploy

by LangChain

Deep Agents Deploy: an open alternative to Claude Managed Agents

blog: Deep Agents Deploy: Open-Source Alternative to Claude Managed Agents for Lock-In-Free Production Deployment — by LangChain — 2026-04-23
Endorsed by LangChain
Details →Visit ↗
💻 Repos×1 mentions

Swyxiodecade

some more references in footnotes https://www.swyx.io/decade

tweet: Swyx's X Feed Serves as Hourly Intelligence Poll with Decade References — by swyx — 2026-04-23
Endorsed by swyx
Details →
💻 Repos×1 mentions

Lightmem

see https://github.com/zjunlp/LightMem

paper: StructMem Enables Efficient Structured Memory for Long-Horizon LLM Reasoning — 2026-04-25
Details →Visit ↗
💻 Repos×1 mentions

Ael

Code and data: https://github.com/WujiangXu/AEL.

paper: Agent Evolving Learning Unlocks Stateless LLM Agents in Open-Ended Environments via Two-Timescale Memory Use and Reflection — 2026-04-25
Details →Visit ↗
💻 Repos×1 mentions

Gsquant

Our code is publicly available at https://github.com/mikumifa/GS-Quant.

paper: GS-Quant Enables Hierarchical Semantic-Structural Quantization for Superior LLM-Based Knowledge Graph Completion — 2026-04-25
Details →Visit ↗
💻 Repos×1 mentions

Ramen

Our code is available at https://github.com/baowenxuan/Ramen .

paper: Ramen Enables Robust Test-Time Adaptation of VLMs in Mixed Domains via Active Sample Retrieval — 2026-04-25
Details →Visit ↗
💻 Repos×1 mentions

Toolattention

The code for this work is accessible at https://github.com/asadani/tool-attention

paper: Tool Attention Slashes MCP Tools Tax by 95% via Gated Lazy Schema Loading — 2026-04-25
Details →Visit ↗
💻 Repos×1 mentions

Groundingmd

Here we propose GROUNDING$.$md, a community-governed, field-scoped epistemic grounding document, using mass spectrometry-based proteomics as an example.

paper: GROUNDING.md: Field-Scoped Epistemic Documents for Enforcing Validity in Agentic AI Coding — 2026-04-25
Details →
💻 Repos×1 mentions

Qatie

The code will be available at https://github.com/GenAI4E/QATIE.git.

paper: Gated Encoding and Multi-Scale Refinement with QAT Bridge Mobile Image Enhancement Training-Deployment Gap — 2026-04-25
Details →Visit ↗
💻 Repos×1 mentions

Symtrs

The results obtained in this work can be reproduced from this Github repository: https://github.com/safouaneelg/SyMTRS.

paper: SyMTRS: Unified Synthetic Benchmark Enabling Multi-Task Advances in Aerial Depth, Domain Adaptation, and Super-Resolution — 2026-04-25
Details →Visit ↗
💻 Repos×1 mentions

Maziarkianisemeval2026task9subtask1polarization

Code and final test predictions are publicly available at: https://github.com/Maziarkiani/SemEval2026-Task9-Subtask1-Polarization.

paper: Language-Adaptive Ensembles Outperform Generalists for Multilingual Polarization Detection in Distinct Scripts — 2026-04-25
Details →Visit ↗
💻 Repos×1 mentions

Llmbiasbench

We propose a method, released as the open-source llm-bias-bench

paper: LLM Bias Bench Reveals Hidden Opinions and Sycophancy Through Coercive Probing — 2026-04-25
Details →
💻 Repos×1 mentions

Dumo

Code is available at https://github.com/Maplebb/DuMo

paper: DuMo Enables Precise High-Frequency Concept Erasure in Diffusion Models Without Backbone Alteration — by Gong Cha — 2026-04-26
Endorsed by Gong Cha
Details →Visit ↗
💻 Repos×1 mentions

Maplebbvce

The code and models are available at https://github.com/Maplebb/VCE.

paper: VCE Enables Precise Concept Erasure in Autoregressive Image Generators via Contrastive Pairs and DPO — by Gong Cha — 2026-04-26
Endorsed by Gong Cha
Details →Visit ↗
💻 Repos×1 mentions

Sunflower 14b

These models are open source and can be used to reduce language barriers in a number of important practical applications.

paper: Sunflower Models Achieve SOTA Comprehension in Most Ugandan Languages via Regional Fine-Tuning — by AI Engineer — 2026-04-26
Endorsed by AI Engineer
Details →
💻 Repos×1 mentions

Sunflower 32b

These models are open source and can be used to reduce language barriers in a number of important practical applications.

paper: Sunflower Models Achieve SOTA Comprehension in Most Ugandan Languages via Regional Fine-Tuning — by AI Engineer — 2026-04-26
Endorsed by AI Engineer
Details →
💻 Repos×1 mentions

Online Repository Containing Formalized Proofs

We also point to an online repository containing formalized proofs of all our results using the lean4 proof assistant

paper: Modular Pairs Drive New Foundations for Infinite Matroid Theory — by Gabe Rivera — 2026-04-26
Endorsed by Gabe Rivera
Details →
💻 Repos×1 mentions

Unigendet

Code: https://github.com/Zhangyr2022/UniGenDet.

paper: UniGenDet Unifies Generative and Discriminative Paradigms for Co-Evolving Image Synthesis and Forgery Detection — by Charlene Li — 2026-04-26
Endorsed by Charlene Li
Details →Visit ↗
💻 Repos×1 mentions

Lesaudedynamics

Source code is available at https://github.com/cljosegfer/lesaude-dynamics

paper: Action-Conditioned JEPA Models Cardiac Pathology as Dynamic Transitions, Outperforming Supervised Baselines — 2026-04-27
Details →Visit ↗
💻 Repos×1 mentions

Planargactivesl

Our code is available at https://github.com/PlanarG/active-sl.

paper: Active Experiment Selection Cuts Scaling Law Fitting Costs by 90% While Matching Full-Budget Accuracy — 2026-04-27
Details →Visit ↗
💻 Repos×1 mentions

Llada20uni

Codes and models are available at https://github.com/inclusionAI/LLaDA2.0-Uni.

paper: LLaDA2.0-Uni Unifies Multimodal Understanding and Generation via Discrete Diffusion LLM — by Arvind on AI — 2026-04-27
Endorsed by Arvind on AI
Details →Visit ↗
💻 Repos×1 mentions

Full Code Walkthrough

Full code + walkthrough: https://t.co/ozm4VwWmj3

tweet: LlamaIndex Pipeline Automates 40-60% of Loan Processors' Manual Income Reconciliation — by LlamaIndex — 2026-04-28
Endorsed by LlamaIndex
Details →Visit ↗
💻 Repos×1 mentions

Sebasmosqmlmedimage

by sebasmos

Code: https://github.com/sebasmos/qml-medimage

paper: QSVMs Resist Minority-Class Collapse Where Classical Kernels Fail on Medical Imaging Embeddings — 2026-04-29
Details →Visit ↗
💻 Repos×1 mentions

Zachmacsmithember

Ember is available at https://github.com/zachmacsmith/ember and is installable via pip install ember-qc.

paper: Ember: A Standardized Benchmark Exposes Algorithm-Dependent Performance in Quantum Annealing Embedding — 2026-04-30
Details →Visit ↗
💻 Repos×1 mentions

Recursivemas

Code and Data are provided in https://recursivemas.github.io.

paper: RecursiveMAS: Scaling Multi-Agent Collaboration Through Latent-Space Recursion — 2026-04-30
Details →Visit ↗
💻 Repos×1 mentions

Votrinhan88divbfkd

by votrinhan88

The code is available at https://github.com/votrinhan88/divbfkd.

paper: Diversity-Driven GAN Training Closes the Gap in Black-Box Few-Shot Knowledge Distillation — 2026-04-30
Details →Visit ↗
💻 Repos×1 mentions

Chiangelagoraopt

Our code and data are available at https://github.com/CHIANGEL/Agora-Opt.

paper: Decentralized Multi-Agent Debate + Memory Bank Outperforms Prior LLM Approaches to Optimization Modeling — 2026-04-30
Details →Visit ↗
💻 Repos×1 mentions

Code And Recipes For Encoderdominated Asr With Textonly Data

All code and recipes are made publicly available.

paper: Simple Encoder-Heavy ASR Architectures Beat Complex Decoder-Heavy Ones When Leveraging Text-Only Data — 2026-05-01
Details →
💻 Repos×1 mentions

Fliansmappingevolve

Our code and data are available at https://github.com/Flians/MappingEvolve.

paper: LLMs as Code Evolvors: Automating Technology Mapping Optimization in Logic Synthesis — 2026-05-01
Details →
💻 Repos×1 mentions

Whatcable

now there is a mac app for it https://github.com/darrylmorley/whatcable

tweet: Whatcable Launches Native Mac App for Real-Time X Feed Monitoring — by swyx — 2026-05-02
Endorsed by swyx
Details →Visit ↗
💻 Repos×1 mentions

Socicnn

The code is available at https://github.com/Kanyooo/SOC-ICNN.

paper: SOC-ICNN: Overcoming Polyhedral Limits in Convex Neural Networks via Second-Order Cone Programming — 2026-04-27
Details →Visit ↗
💻 Repos×1 mentions

Rflkpc

The source code for the proposed RFLkPC method is publicly available at https://github.com/xuelin-xie/RFLkPC.

paper: RFLkPC: A Robust Fuzzy Clustering Method for High-Dimensional Data with Outliers — 2026-04-27
Details →Visit ↗
💻 Repos×1 mentions

Partnetmobility

We assessed the generalization of our method over 30 articulations of the PartNetMobility articulated object dataset, with an average of 704 different trajectories by task. Code is publicly available

paper: QDTraj: Enhancing Robotic Manipulation through Diverse Trajectory Primitive Generation — 2026-04-27
Details →Visit ↗
💻 Repos×1 mentions

Mudabench

MuDABench is available at https://github.com/Zhanli-Li/MuDABench.

paper: MuDABench Exposes RAG Limitations in Large-Scale Multi-Document Analytical QA — 2026-04-27
Details →Visit ↗
💻 Repos×1 mentions

Ttsprism

TTS-PRISM is open-source, with code and checkpoints at https://github.com/xiaomi-research/tts-prism.

paper: TTS-PRISM Enables Fine-Grained, Interpretable Diagnosis of TTS Acoustic Artifacts via 12D Schema — 2026-04-27
Details →Visit ↗
💻 Repos×1 mentions

Llmsourcebalancing

Code is available at https://github.com/shuowl/llm-source-balancing.

paper: LLMs Prioritize Document Assertions Over User Input, with Post-Training Reinforcing This Bias — 2026-04-27
Details →Visit ↗
💻 Repos×1 mentions

Specrlbench

Code is available at https://github.com/BU-DEPEND-Lab/SpecRLBench.

paper: SpecRLBench Reveals Poor Generalization in LTL-Guided RL Across Complex Specs and Environments — 2026-04-29
Details →Visit ↗
💻 Repos×1 mentions

Metacot

Our code, benchmark, and model are released at https://shiyi-zh0408.github.io/projectpages/Meta-CoT/

paper: Meta-CoT Decomposes Image Edits into Task-Target-Understanding Triplets for Enhanced Granularity and Generalization — 2026-04-29
Details →Visit ↗
💻 Repos×1 mentions

Shape

Our code and data are available at https://github.com/MAPS-research/SHaPE

paper: SHAPE Benchmark and Graph-Augmented Pipeline Counter Pedagogical Jailbreaks in Educational LLMs — 2026-04-27
Details →Visit ↗
💻 Repos×1 mentions

Daopendvworld

DV-World provides a realistic testbed to steer development toward the versatile expertise required in enterprise workflows. Our data and code are available at this project page.

paper: Current LLM Agents Fail at Real-World Data Visualization: A New Benchmark Exposes Critical Gaps — 2026-04-30
Details →Visit ↗
💻 Repos×1 mentions

Bigspinaibigspinfluencyoutcomes

Our code and data are available at https://github.com/bigspinai/bigspin-fluency-outcomes

paper: AI Fluency Paradox: Expert Users Fail More Visibly, Succeed More Meaningfully — 2026-04-30
Details →Visit ↗
💻 Repos×1 mentions

Praxy Voice R6 Lora Weights

We release R6 LoRA weights (Apache-2.0), inference code and router (MIT), and a Gradio demo.

paper: Frozen Non-Indic TTS Reaches Commercial Quality via Phoneme Bridging and LoRA — Zero Commercial Training Data Required — 2026-04-30
Details →
💻 Repos×1 mentions

Faithfulnessqa

by qzhangFDU

Data and code are available at https://github.com/qzhangFDU/faithfulness-qa-dataset.

paper: Counterfactual Entity Substitution as a Scalable Fix for RAG Unfaithfulness — 2026-04-30
Details →Visit ↗
💻 Repos×1 mentions

Prime

by HySonLab

Our source code is publicly available at https://github.com/HySonLab/PRIME

paper: PRIME: Physics-Informed Multiscale Hierarchies Surpass Single-Scale Protein Representations — 2026-05-05
Details →Visit ↗
💻 Repos×1 mentions

Music Transformer Checkpoints Pearlleestudio

All six checkpoints are released on the HuggingFace Hub at https://huggingface.co/PearlLeeStudio.

paper: Rehearsal Data Threshold for Catastrophic Forgetting in Genre-Adaptive Chord Generation — 2026-05-08
Details →Visit ↗
💻 Repos×1 mentions

Rminshen03eaiprivacyposition

We detail the SPINE framework and case studies at https://github.com/rminshen03/EAI_Privacy_Position.

paper: Privacy in Embodied AI Must Be a System-Wide Architectural Constraint, Not a Stage-Local Fix — 2026-05-08
Details →Visit ↗
💻 Repos×1 mentions

Dlm9siop

Code is available at https://github.com/dl-m9/SIOP.git.

paper: Verifier-Free Turn-Level Credit Assignment for LLM Agents via Semantic Outcome Clustering — 2026-05-08
Details →
💻 Repos×1 mentions

Indigmainnovationsfederatedlearningevchargingdemand

by Indigma Innovations

Code is available at https://github.com/Indigma-Innovations/federated-learning-ev-charging-demand.

paper: Federated Learning Enables Privacy-Preserving Early EV Charging Demand Forecasting with Minimal Data — 2026-05-08
Details →Visit ↗
💻 Repos×1 mentions

Unlcpnlablookoncebeamtwice

For reproducibility, we publish our code to https://github.com/UNL-CPN-Lab/Look-Once-Beam-Twice.

paper: Camera-Assisted Hybrid ML Beats End-to-End Models for Real-Time mmWave Beam Management in V2X — 2026-05-08
Details →
💻 Repos×1 mentions

Timvieiratimvieiragithubcom

by timvieira

The whole thing is built from a centralized YAML file. So it should be pretty modular in case you want to try it on different content.

tweet: YAML-Driven Modular Architecture Enables Portable Document Exploration Pipelines — by xtimv — 2026-05-13
Endorsed by xtimv
Details →Visit ↗
💻 Repos×1 mentions

Researchgraph

by xtimv

Here's something I built to explore the stuff I've written (blog posts and publications). It's still a bit of work in progress, but it's pretty fun, especially the "semantic" tab + sliders.

tweet: Researcher Builds AI-Assisted Personal Knowledge Explorer for Blog Posts and Publications — by xtimv — 2026-05-13
Endorsed by xtimv
Details →Visit ↗
💻 Repos×1 mentions

Samsongourevitchrevudm

by samsongourevitch

The code and models can be found at https://github.com/samsongourevitch/rev_udm.

paper: Uniform Diffusion Models Underperform Due to Parameterization Flaws, Not Marginal Choice — 2026-05-22
Details →Visit ↗
💻 Repos×1 mentions

Ysfalhdistillationgame

Our code is available at: https://github.com/ysfalh/distillation-game.

paper: Adaptive Distillation Attacks Expose False Robustness in Model Imitation Defenses — 2026-05-22
Details →Visit ↗
💻 Repos×1 mentions

K59118harnessoptimizerevaluation

Codes and data can be found at https://github.com/k59118/Harness_Optimizer_Evaluation.

paper: Priority Ranking: A Low-Cost Direct Evaluation Method for LLM-Based Harness Optimizers — by Kai — 2026-05-22
Endorsed by Kai
Details →Visit ↗
💻 Repos×1 mentions

Auto Research

by Andrej Karpathy

I think we talked about that here a bit. That's an open source training tool. It helps AI models, improve themselves by running five-minute experiments. That got over 82,000 stars on GitHub.

Recommended on All-In with Chamath, Jason, Sacks & Friedberg — 2026-05-22
Details →
💻 Repos×1 mentions

Thermovl

by Thushara Karthikeyan et al.

Our dataset and code are publicly available at: https://thusharakart.github.io/Thermo-VL

paper: Thermo-VL: Injecting Thermal Infrared Perception into Frozen Vision-Language Models via Prompt-Conditioned Fusion — by Dylan Patel — 2026-05-24
Endorsed by Dylan Patel
Details →Visit ↗
💻 Repos×1 mentions

Bcisift

by UMCU-RIBS

Our scikit-learn-compatible toolbox (github.com/UMCU-RIBS/BCI-sift) simplifies feature selection in BCI tasks by integrating advanced optimization methods.

paper: BCI-sift: A Scikit-Learn-Compatible Toolbox That Improves Neural Decoding via Automated Feature Selection on HD ECoG Data — by Nick — 2026-05-24
Endorsed by Nick
Details →Visit ↗
💻 Repos×1 mentions

Zbwproonepred

Our code is publicly available at https://github.com/ZBWpro/OnePred.

paper: OnePred: Recursive Intent Memory Enables 22× Cheaper Next-Query Prediction in Multi-Turn LLM Conversations — 2026-05-25
Details →
💻 Repos×1 mentions

Zbwprocoreact

Our code is publicly available at https://github.com/ZBWpro/Co-ReAct.

paper: Co-ReAct: Step-Level Rubric Injection Improves Multi-Step Reasoning in ReAct Agents — 2026-05-25
Details →
💻 Repos×1 mentions

Liliupeng28icml26cvsearch

Code is released at https://github.com/liliupeng28/ICML26-CVSearch.

paper: CVSearch: A Training-Free Adaptive Visual Search Framework That Resolves Coverage-Efficiency Tradeoffs in High-Resolution MLLMs — 2026-05-25
Details →Visit ↗
💻 Repos×1 mentions

Lumina04care

Our code is available at https://github.com/Lumina04/CARE.

paper: Active Label Acquisition Stabilizes RLVR Training by Selectively Replacing Pseudo-Labels — 2026-05-26
Details →Visit ↗
💻 Repos×1 mentions

Siper

The code and data are available at https://github.com/DongdingLin/SiPeR.

paper: SiPeR Framework Enhances Situated Conversational Recommendation via Scene Transition Estimation and Bayesian Preference Inference — 2026-04-23
Details →Visit ↗
💻 Repos×1 mentions

Alexfanwlegalsearchr1

The code and data are available at https://github.com/AlexFanw/LegalSearch-R1.

paper: RL-Trained Legal Search Agent Solves Temporal Consistency Failures in LLM Legal Reasoning — 2026-05-26
Details →Visit ↗
Page 1 of 79