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 the representation-aware advantage estimation, which leverages RM hidden states and models them as auxiliary signals for better advantage estimation.”
“We apply GraphAE to GRPO, GSPO and RLOO, and conduct extensive experiments on different models and benchmarks.”
“We apply GraphAE to GRPO, GSPO and RLOO, and conduct extensive experiments on different models and benchmarks.”
“We apply GraphAE to GRPO, GSPO and RLOO, and conduct extensive experiments on different models and benchmarks.”
“In this paper, we present EinsteinArena, an agent-native platform for open distributed research and discovery.”
“We introduce Knowledge-Grounded Counterfactual Reasoning (KG-CFR), a dual-stage architecture that enforces a strict separation of concerns between a private, retrieval-augmented planning buffer, and a…”
“The results reveal meaningful trade-offs between accuracy and resource efficiency, with the FRQI model achieving a 97 percent reduction in circuit depth while maintaining a near-perfect reconstruction…”
“However, on real quantum hardware, these encodings can quickly lead to circuits with many gates, large circuit depth, and high qubit usage, which is a problem for Noisy Intermediate-Scale Quantum (NIS…”
“However, on real quantum hardware, these encodings can quickly lead to circuits with many gates, large circuit depth, and high qubit usage, which is a problem for Noisy Intermediate-Scale Quantum (NIS…”
“Here we realize scalable and efficient homodyne detection by leveraging a large number of pixels in a charge-coupled-device (CCD) camera.”
“the computational tool used: Qibo, an open-source framework for efficient quantum simulations and quantum hardware control.”
“we propose EEVEE, the first multi-dataset test-time prompt learning framework for LLM agents, enabling test-time prompt learning under real-world task streams.”
“we propose Target-SFT which constructs the training objective directly from the desired target distribution.”
“the folks at kaggle actually are are pushing on this notion of like um having personal evals and being able to sort of build a platform in which as new models are released and made available to the wo…”
“released the the sort of experimental variant of 2.0 pro which is the the most capable Frontier Model we have... Pro is where you're sort of not bound by costs in a lot of ways”
“we also previewed in December the multimodal live API which allows you to do this sort of collaborative realtime conversational video uh text interface with the models”
“We propose a Transformer-based network for cuffless BP estimation from PPG signal, leveraging self-attention to capture long-range dependencies across multiple cardiac cycles.”
“We introduce the Itô map, an any-step stochastic flow map that takes an intermediate state and Brownian path and predicts future states in a single pass.”
“We propose a specific adaptive CVaR schedule that gradually tightens the sampled tail used for optimization, together with a two-stage optimizer combining global exploration with Particle Swarm Optimi…”
“Apple Intelligence comes to Apple Vision Pro today with visionOS 2.4”
“We propose a specific adaptive CVaR schedule that gradually tightens the sampled tail used for optimization, together with a two-stage optimizer combining global exploration with Particle Swarm Optimi…”
“In the reported QPU layout comparison, the proposed heavy-hex-native deep-chain layout achieves the best final objective value and CVaR-tail performance among the tested layouts.”
“We also study ansatz depth and sequential growth strategies. Finally, we introduce two hardware-aware ansatz-layout modifications: a data-guided colored layout that assigns correlated variables to qub…”
“Latent diffusion models (LDMs) provide efficient mappings from high-dimensional geological model space to a low-dimensional latent variable, reducing the dimensionality of the inverse problem while ma…”
“We compare model-space and latent-space DA using the ensemble smoother with multiple data assimilation (ESMDA), and demonstrate a key trade-off: model-space updates achieve significant uncertainty red…”
“Motivated by this, we explore rigorous Markov chain Monte Carlo (MCMC) and Sequential Monte Carlo (SMC) algorithms in the 3D-LDM latent space.”
“Motivated by this, we explore rigorous Markov chain Monte Carlo (MCMC) and Sequential Monte Carlo (SMC) algorithms in the 3D-LDM latent space.”
“All models maintain geological realism due to the LDM parameterization. MCMC and SMC are consistent with one another and achieve lower data mismatch and more uncertainty reduction than latent-space ES…”
“All models maintain geological realism due to the LDM parameterization. MCMC and SMC are consistent with one another and achieve lower data mismatch and more uncertainty reduction than latent-space ES…”
“We present explicit controlled-SWAP-based unitary constructions that achieve exact uniformity with quadratic circuit size and linear depth (O(n)) on linear nearest neighbor topologies.”
“We introduce CIAware-Bench, a benchmark for measuring control intervention (CI) awareness across frontier models.”
“We introduce GASLoC, a novel decentralized pre-training algorithm that generalizes the notion of communication acceleration to the recently popular "outer optimizer" to allow a practical gossip-based …”
“To this end, we propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time.”
“we propose GenAIR, a general framework that empowers sequential recommendation with Generative Archetype-grounded Item Representations”
“We present FADA, a unified vision-language model built on Qwen3.5-VL that performs clinical interpretation, classification, detection, and segmentation through a single interpretation-first pipeline w…”
“While existing methodologies such as SECDA enable rapid hardware-software co-design through SystemC simulation and FPGA execution, identifying efficient accelerator configurations remains a largely ma…”
“SECDA-DSE is a framework that integrates Large Language Models (LLMs) into the SECDA ecosystem to guide design space exploration (DSE) of FPGA-based accelerators.”
“It combines a structured DSE Explorer for generating candidate architectures with an LLM Stack that performs reasoning-guided exploration using retrieval-augmented generation and chain-of-thought prom…”
“we propose ReasonAlloc, a training-free framework that recasts decoding-time KV compression as a hierarchical budget allocation problem.”
“Linear integrates with the very best agent coding tools directly, like cursor and codex.”
“we propose Bellman--Taylor score decoding, a framework that moves policy learning to a Euclidean score space while enforcing feasibility through an action decoder”
“Lastly, we apply this framework to a queueing network control problem, where the policy essentially learns a state-dependent index-based dispatching rule.”
“To address these limitations, we propose VISTA, a Versatile Interactive user Simulation Toolkit for Agent evaluation.”
“We apply our method to two open-source models, Moshi and PersonaPlex, demonstrating consistent improvements in interactivity on both offline evaluation with pre-recorded audio and real-time multi-turn…”
“We apply our method to two open-source models, Moshi and PersonaPlex, demonstrating consistent improvements in interactivity on both offline evaluation with pre-recorded audio and real-time multi-turn…”
“We analyze how Claude Opus 4, GPT-4.1, and Gemini 2.5 Pro adapt 60 English math word problems into Bengali, Hindi, Punjabi (India), Urdu, Sindhi (Pakistan), Italian, and Sicilian (Italy)”
“We analyze how Claude Opus 4, GPT-4.1, and Gemini 2.5 Pro adapt 60 English math word problems into Bengali, Hindi, Punjabi (India), Urdu, Sindhi (Pakistan), Italian, and Sicilian (Italy)”
“Instruction-tuned LLMs are increasingly converted into reasoning models through post-training to improve multi-step task performance.”
“With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under complex personality conditions is essential.”
“we introduce HiViG, a History-aware Visually Grounded test-time framework, built around a multimodal critic trained on real GUI trajectories”
“HiViG consistently outperforms existing scalar and verbal critics, improving average success rates over the strongest baseline by 5.8% for Qwen3-VL-32B and 9.0% for Gemini-3-Flash”
“We introduce Data Journalist Agent (Data2Story), a multi-agent framework that orchestrates specialized roles into a single virtual newsroom.”
“we present Architect-Ant, an editable automatic furnishing framework powered by a fine-tuned vision-language model”
“This study aims to explore the performance of the VAR model in comparison with mel-frequency cepstral coefficient (MFCC) matrices and log-mel spectrograms using deep learning.”
“This study aims to explore the performance of the VAR model in comparison with mel-frequency cepstral coefficient (MFCC) matrices and log-mel spectrograms using deep learning.”
“This study aims to explore the performance of the VAR model in comparison with mel-frequency cepstral coefficient (MFCC) matrices and log-mel spectrograms using deep learning.”
“Along with traditional trimming/zero-padding, adaptive-length windowing was presented to fix their temporal dimensions.”
“Different convolutional neural network (CNN) architectures were employed to extract features from the two-dimensional representations obtained over the sub-phases.”
“The extracted sub-phase features were then fused using various strategies including direct concatenation, gated recurrent unit (GRU) network and GRU with attention mechanism.”
“The extracted sub-phase features were then fused using various strategies including direct concatenation, gated recurrent unit (GRU) network and GRU with attention mechanism.”
“Augmentation degraded the performance of models overall, yet mixup augmentation was the best among the methods tested.”
“Integral field unit (IFU) spectroscopy provides spatially resolved spectra across galaxies, offering crucial insights into their evolution.”
“We present a multi-modal, probabilistic foundation model that predicts high-resolution spectra with calibrated uncertainties at arbitrary spatial locations within a galaxy directly from broadband imag…”
“The model employs a neural network (NN) classifier to filter for single-mode designs (suppression ratio $\ge$ 50 dB), followed by a regressor that predicts confinement loss (CL).”
“We propose a high-efficiency, two-stage machine learning framework designed to identify high-performance NANF designs using minimal training data.”
“The Gromov--Wasserstein (GW) distance provides a framework for comparing metric measure spaces, regardless of their underlying structure or geometry.”
“Furthermore, through a variant of GW known as fused Gromov--Wasserstein (fGW), it is also possible to incorporate node features in addition to graph structure.”
“By viewing graphs as finitely supported metric measure spaces equipped with the pairwise distance metric and a uniform probability measure on the nodes, we obtain universal consistency of GW-kNN for t…”
“Likewise for fGW-kNN, we prove universal consistency on the space of weak isomorphism classes of structured objects consisting of metric measure spaces with finite support and uniform probability meas…”
“We study the simplest architecture for which the analogy is tractable: a pure MLP residual stack trained on masked token prediction over synthetic Markov chain sequences with known spectral properties…”
“Together these findings constitute the first quantitative, position-level evidence that MLP residual networks implement a selective coarse-graining procedure governed by the spectral structure of the …”
“we introduce Learning Europa's Atmosphere and Plasma (LEAP), a transformer-based surrogate trained on outputs from a state-of-the-art multi-fluid MHD code to predict magnetic field perturbations along…”
“Now if you want to look around the corner and see the next bottleneck coming, I strongly urge you to look at copper.”
“We consume a billion2 ounces a year. We supply a billion ounces a year. So there's a 200 million ton deficit per year and we only have 600 million of above ground inventory left. So the clock's tickin…”
“So for our kids and for the country generation tool belt for us allocating get some exposure to copper silver minerals and then there's a bunch of service providers in and around that area that we sho…”
“Dataiku gives companies one place to see, control, and measure every agent across the entire business.”
“And in this bigger picture, XRP plays a defining role.”
“Ono has already carved its place in history by launching the first tokenized US treasuries available worldwide.”
“all the frontier models plug into that. So if you are an OpenAI Codex person, you write all your code in Codex, you use CloudCode, you can use those models inside of Xcode, their software development …”
“all the frontier models plug into that. So if you are an OpenAI Codex person, you write all your code in Codex, you use CloudCode, you can use those models inside of Xcode, their software development …”
“The person at your company who runs the Airtable is the most powerful person at your company.”
“Or Trello or whatever it is that your company uses. But the person who runs that thing is the most powerful person because they get to reorganize the priorities.”
“I have heard some strong initial impressions about Fable's capabilities, and I was very impressed with Fable's review of this update, and will take it for granted that it is excellent.”
“This is a significantly more serious intervention than any of the other guardrails, because Anthropic is fundamentally changing the experience of the model to be less helpful for Frontier LM developme…”
“We introduce RM, a multi-task stage-aware reward model that combines an action-primitive-based stage estimator with a multi-gate Mixture-of-Experts (MMoE) value head to produce dense per-step rewards …”
“Building on RM, we further propose SPIRAL (Self-Policy Improvement via Reward-Aligned Learning), an on-policy reward-guided framework that improves VLA policies from cheap autonomous rollouts.”
“We introduce NOVA (Navigating via Observation, Verification, and Action) to make this viable in the combinatorially large UI state space, where the plan can invoke a perception model to resolve runtim…”
“This work presents GuardNet, a guardrail system based on an ensemble of shallow neural networks (BiLSTMs) with approximately 47 million parameters.”
“We present Bespoke-Card, an agent-driven system that synthesizes workload-specific cardinality estimators as executable code”
“Here, we introduce Multi-Region Latent Factor Analysis via Dynamical Systems (MR-LFADS), a sequential variational autoencoder designed to disentangle inter-regional communication, inputs from unobserv…”
“Strong DM's EI team is an example of how to do this.”
“A great example is what Jack Dorsey is doing over at Block.”
“produced with the assistance of Bolzano, an open-source multi-agent LLM system.”
“In particular, we adapt two widely used RLHF frameworks--Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO)--as our defenses by constructing preference pairs and defini…”
“In particular, we adapt two widely used RLHF frameworks--Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO)--as our defenses by constructing preference pairs and defini…”
“we propose a training-free Global-Local Skipping Strategy that accelerates diffusion model-based 3D PET denoising while simultaneously improving reconstruction quality.”
“Diffusion-model-based methods have demonstrated strong potential for restoring low-count PET to near high-count quality”
“In the medical domain, claude-haiku-4-5 increases certainty of 20% examples after a single iteration, increasing to 40% after five iterations.”
“Keep your employees and data safe with Chrome Enterprise, the most trusted enterprise browser.”
“Here we propose a protocol that stabilizes a toric-code quantum memory without moving, measuring or local addressing atoms.”