What the smart people are recommending. 8874 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.
“We introduce Span, a censored-Poisson Bayesian latent-growth change-point detector that models the binary detection process, accumulates a sequential generalised-likelihood-ratio statistic for an upwa…”
“Large language models (LLMs) are increasingly used as conditional generators for structured data, relying on in-context learning (ICL) to adapt to new distributions without parameter updates.”
“relying on in-context learning (ICL) to adapt to new distributions without parameter updates.”
“Parameter-efficient fine-tuning (LoRA) overcomes these limitations but introduces measurable memorization risk and, in some cases, destabilizes structured output generation, highlighting a fundamental…”
“Overall, attention-based multimodal learning with ordinal regression represents a robust, interpretable, and scalable approach for automated AD severity staging and AI-assisted clinical decision suppo…”
“Among unimodal approaches, the T1-weighted MRI model achieved slightly higher adjacent-stage accuracy (0.963) and agreement with clinical staging (QWK 0.444) than the tabular model (QWK 0.433).”
“Among unimodal approaches, the T1-weighted MRI model achieved slightly higher adjacent-stage accuracy (0.963) and agreement with clinical staging (QWK 0.444) than the tabular model (QWK 0.433).”
“The multimodal non-ordinal baseline achieved the lowest prediction error (MAE 0.340), whereas the ordinal multimodal model achieved the highest adjacent-stage accuracy (0.970) and strongest agreement …”
“The multimodal non-ordinal baseline achieved the lowest prediction error (MAE 0.340), whereas the ordinal multimodal model achieved the highest adjacent-stage accuracy (0.970) and strongest agreement …”
“The code is available on https://github.com/Hardy158118/Diffprior.”
“We propose fine-tuning with ART (Art-based Reinforcement Training).”
“While Low-Rank Adaptation (LoRA) introduces additional weights between the LLM layers, Soft Prompting introduces additional fine-tuning-specific raw tokens to an LLM input.”
“A [Pen](https://codepen.io/jjob1391/pen/xeoWYK) by [Jeremy](https://codepen.io/jjob1391) on [CodePen](https://codepen.io).”
“In this paper, I show that OMWU converges asymptotically for smooth convex-concave saddle-point problems, with a small enough constant learning rate.”
“Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative-Weights Update (OMWU) are two very popular algorithms to solve convex/concave saddle-point problems, where OMWU is the non-Eucli…”
“Code can be found at https://github.com/fraunhofer-iais/inference-framework-creditscorecards.”
“we leverage a frozen pretrained time-series foundation model (TSFM) and combine it with a small regression head for RUL estimation from multivariate sensor streams. More specifically, we use Chronos-2…”
“the implementation is publicly available at https://github.com/MBamdad/HAMNO”
“the implementation is publicly available at https://github.com/MBamdad/HAMNO”
“We introduce STRAND (Survival Topological Representation ANalysis of Diagrams), which treats (collections of) PDs as survival data”
“Code is available at https://github.com/robizso/slt-datagen.”
“Our code is available at https://github.com/Heinz217/GraspLLM.”
“we present a data-driven framework AI4Land, for generating high-resolution historical reconstructions and future projections of key land surface variables”
“AI4Land was developed and trained on MareNostrum5, demonstrating how GPU-accelerated HPC infrastructure enables global-scale climate AI pipelines.”
“The final product is a suite of open-source emulators designed for real-time coupling with digital twin platforms, such as those developed under the Destination Earth initiative.”
“We propose a continual learning (CL) method, which can overcome these challenges and continually learn from different tasks. Our method consists of three main parts: our AGF model, Taskfusion augmenta…”
“gcloud beta logging sinks create $1-to-gcs storage.googleapis.com/$PROJECT_NAME-logs-$1 --log-filter="$filter" --project=$PROJECT_NAME”
“To improve stability, we introduce Taskfusion augmentation, combining boundary-aware interpolation within tasks to refine the model anomaly boundaries and cross-task mixing to transfer anomaly structu…”
“Apple Intelligence now features Image Playground, Genmoji, and more”
“bq mk --dataset $PROJECT_NAME:logs_$1”
“To handle class imbalance and memory constraints, we employ tabular dataset distillation to store compact synthetic replay samples, which are jointly used with augmented data in an outlier exposure ob…”
“If you haven't read the GDP eval paper from open AI, it is an interesting paper.”
“These experts are instantiated as a strong text baseline Gemini3-Flash, a fine-tuned Qwen3-VL, and an external knowledge base, respectively, working collaboratively to enhance VQA performance.”
“this study proposes a novel "generation-evaluation-optimization" closed-loop framework for automated concrete barrier design using the multi-agent orchestration capabilities of AutoGen”
“The source code for the proposed multi-agent design framework is available at the project GitHub repository: https://github.com/MXY820/barrier-design”
“Codes are available at https://github.com/eeee-sys/MODF-SIR”
“the dataset for training router is available at https://huggingface.co/datasets/Harry-1234/IntentRouterTrain”
“We introduce StatefulDiscovery, a discovery framework that externalizes investigation state and uses it to coordinate frontier selection, evidence acquisition, and claim adjudication.”
“We introduce DuoBench, an extensible benchmarking framework for bimanual manipulation policies on the FR3 Duo platform.”
“we propose a facial recognition framework that addresses non-frontal pose variations by integrating lightweight generative adversarial network (GAN)-based pose frontalisation with memristor-based neur…”
“Memristor-based neuromorphic systems have emerged as a compelling approach for edge AI applications, combining biologically inspired processing with efficient and scalable computation.”
“The code can be accessed at https://github.com/atif-hassan/RCAP-dynamic-dataset-pruning”
“In this paper, we present InDex, a novel, data-efficient adaptation framework rooted in cross-morphology semantic inheritance.”
“Code is available at https://github.com/RSC-Toolkit/Lung-SRAD.”
“we propose a new optimal transport-based RL strategy, OT-GRPO, which is a minimal-matching variant of group relative policy optimization tailored to pairwise verifiers.”
“Start your search today! View John's Featured Listings.”
“The complete agent design code and prompts are open-sourced and can be accessed at: https://github.com/SimAgentDev/Ansys-LSPP-AgentKit”
“interfacing specialized agents with two widely used commercial FE softwares, i.e., ANSYS and LS-PrePost”
“interfacing specialized agents with two widely used commercial FE softwares, i.e., ANSYS and LS-PrePost”
“Easily teach your dog to ring the Mighty Paw Smart Bell to communicate potty time. It's the premier solution to all of your dog potty training problems. As a bonus all of your friends and family will …”
“Our framework, titled QLung, introduces a no-reference audio quality margin derived from spectral entropy and root-mean-square energy, which adaptively scales angular margins based on recording qualit…”
“We present WorldReasoner, an evaluation framework for temporally valid event forecasting.”
“We propose a spectral-based, unsupervised representation learning framework to derive low-dimensional embeddings for clinical concepts and patients in rare disease cohorts from electronic health recor…”
“We describe PolyILR, a canonical orthonormal decomposition of the Aitchison tangent space aligned with any tree topology.”
“This paper writes that practice down as a methodology, Agents All the Way Down: two preconditions crossed once and kept, then three practices repeated for the agent's life.”
“We propose CRUMB (Clustered Retrieval Using Minimised-MMD Batching), a three-stage inference wrapper that (i) clusters the test queries, (ii) selects a small, distributionally matched training subset …”
“Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, and predictions for t…”
“Time series analysis is a fundamental component of machine learning, especially in astrophysics and cosmology where temporal data abound.”
“We propose q-PDGD, a quantized stochastic primal-dual method, and analyze it under relaxed global geometry.”
“We give a Lean 4 mechanization of the structural core (telescoping, the finite-audit bound, finite Gibbs, and the entropy floor)”
“This paper introduces a novel tactile sensor for in-hand manipulation with slip-aware control that integrates velocity, force/torque, and pressure map sensing into a single device with a deformable co…”
“We present ALIGNBEAM, a training-free method that lifts this restriction by translating anchor logits into the target model's vocabulary token-by-token at each decoding step”
“Our results indicate that Fourier features let policies leverage geometric details more effectively than Cartesian features, showing their potential as a general-purpose tool for point cloud-based imi…”
“we present Bebop, a systematic study of MTP in LLM post-training, and offer practical recipes to integrate MTP into large-scale RL pipelines”
“These results indicate that progressive magnitude-based pruning provides an effective single-cycle approach for neural network sparsification under the evaluated settings.”
“To fill this gap, we introduce the Standard Interpretable Model (SIM), a general theory grounded in Lagrangian mechanics that enables the deductive design of interpretable methods.”
“Recent work in ML applies genetic algorithms at inference time to iteratively improve solutions to optimization problems.”
“System prompts that are not well approximated by steering vectors are not subliminally learned.”
“Designed as a plug-and-play solution, CCKS integrates seamlessly with existing DTDE algorithms.”
“In Decentralized Training and Decentralized Execution (DTDE) for cooperative Multi-Agent Reinforcement Learning (MARL), action-advising-based knowledge sharing promotes interpretable and scalable coop…”
“In this paper, we introduce a novel framework that enables real-time generation of LLM-based user interest personas for a large-scale commercial video recommendation platform.”
“Existing approaches take polar positions: a "free-for-all" model based on fair use and a "strong intellectual property rights" model. We show that both fail: Free-for-all does not compensate creators,…”
“We further propose a market design with a data intermediary internalizing cross-creator externalities and subsidizing innovative contributions, thereby restoring efficiency.”
“In-Context Operator Networks (ICON) addresses this issue by prompting the model with numerical context so that the model learns specific operators from prompts and adapt to different operators without…”
“we introduce Chain of Operators (CHOP), a framework that harness a frozen ICON to OOD operator tasks without updating its parameters.”
“We quantize Ideogram 4.0 - a 9.3B flow-matching diffusion transformer (DiT), shipped as two separate-weight copies of a single-stream 34-layer backbone for classifier-free guidance and conditioned by …”
“Our GGUF Q4_K quantization beats NF4 at equal on-disk size and is the Pareto winner on the quality-memory frontier, with paired confidence intervals excluding zero (Q8_0 is quality neutral).”
“if you don't want to miss out on this, all you need to do is to go to the restishistory.com to sign up.”
“start_str”
“Audio samples are available at our demo page: https://realfolkcode.github.io/pianokontext_demo/”
“Vision-Language-Action (VLA) models provide a natural language interface to robot control, but the mapping from language to behavior is often brittle and unintuitive”
“This study examines these questions through a gamified writing exercise where 74 participants (214 responses) replied to prompts while AI-generated word suggestions were available as they wrote.”
“Knowledge Distillation (KD) and mixup have proven effective at inducing smoothness in class boundaries”
“Knowledge Distillation (KD) and mixup have proven effective at inducing smoothness in class boundaries”
“# For Less Anxiety and More Life, Treat Your To-Do List Like a Diner Menu”
“To improve both efficiency and robustness, we introduce Context-Driven Incremental Compression (C-DIC), which treats a conversation as interleaved contextual threads and stores revisable per-thread co…”
“Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length.”
“We present Tahoe, a system that treats prompt optimization as a dynamic data management problem.”
“We release the code and dataset at huggingface.co/datasets/neginb/OpenMedReason.”
“We complement it with OpenMedReason-Bench, a held-out benchmark that allows fine-grained evaluation of LVLMs along three complementary axes of capability, including perception, medical knowledge, and …”
“In this work, we introduce ERTS, an explainability-based reliability training signal for efficient ECG classification.”
“we propose MLT-Dedup, an efficient large-scale online video deduplication framework with Multi-Level representations and spatial-Temporal matching.”
“We introduce \emph{Behavioral INR}, a self-supervised generative model that adapts implicit neural representations (INRs) from vision to behavior.”
“We propose Reroute, a training-free plug-in that replaces removal with recoverable routing.”
“including NSGA-II, NSGA-III and SMS-EMOA under the same setting of constant population size and duplicate elimination, SPEA2 is unable to cover the Pareto front of the OneTrapZeroTrap benchmark effici…”
“including NSGA-II, NSGA-III and SMS-EMOA under the same setting of constant population size and duplicate elimination, SPEA2 is unable to cover the Pareto front of the OneTrapZeroTrap benchmark effici…”
“including NSGA-II, NSGA-III and SMS-EMOA under the same setting of constant population size and duplicate elimination, SPEA2 is unable to cover the Pareto front of the OneTrapZeroTrap benchmark effici…”
“Botox, onabotulinum toxin A, prevents headaches in adults with chronic migraine before they start. It's not for those with 14 or fewer headache days a month. It prevents, on average, eight to nine hea…”
“We present projectmem, an open-source, local-first memory and judgment layer for AI coding agents.”
“Our estimator integrates PRNet-based 3D face alignment, clip-level illumination augmentation, the Residual Temporal Standardization Module, and controlled hybrid temporal-frequency supervision.”