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.
“In this work, we construct and simulate an explicit circuit level implementation of a quantum Metropolis-Hastings algorithm based on the framework introduced by Claudon \emph{et al.} (arXiv:2506.11576…”
“The best existing answer is provided by Theorem 10.1 of Jordan et al., yet we show that this answer systematically underestimates the extent of quantum advantage.”
“Our findings highlight the advantages of our approach and suggest promising advancements in the field of quantum LiDAR sensing technology, providing a pathway for more accurate and sensitive measureme…”
“Blog post by Marcus Buckingham”
“To address these challenges, we propose VISOR (Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning), a unified single-agent framework.”
“Extensive experiments on ViDoSeek, SlideVQA, and MMLongBench demonstrate that VISOR achieves state-of-the-art performance”
“Extensive experiments on ViDoSeek, SlideVQA, and MMLongBench demonstrate that VISOR achieves state-of-the-art performance”
“Extensive experiments on ViDoSeek, SlideVQA, and MMLongBench demonstrate that VISOR achieves state-of-the-art performance”
“Over a range of FeMoco active spaces, SE-QPE reduces time evolution resources, with asymptotic reductions of about 33% in CX count, 25% in $T$ count, and an asymptotic depth ratio of $3/N$ for CX laye…”
“We present a two-pronged diagnostic toolkit applied to SummEval”
“This paper proposes Atropos, a predictive early-termination analysis and hotswap technique that aims to improve the cost-benefit trade-off for LLM-based agents that use self-consistency.”
“Tragedy of the commons: Hardin”
“To address this issue, we propose StableOPD, a stabilized OPD framework that combines a reference-based divergence constraint with rollout mixture distillation. These together mitigate repetition-indu…”
“We initiate the study of language generation in the limit, a model recently introduced by Kleinberg and Mullainathan [KM24], under the constraint of differential privacy.”
“We introduce DiADEM, a neural architecture that learns "how much each demographic axis matters" for predicting who will disagree and on what.”
“In this paper, inspired by the vulnerability of unfaithful intermediate reasoning trajectories, we propose \textbf{S}elf-\textbf{A}udited \textbf{Ve}rified \textbf{R}easoning (\textsc{SAVeR}), a novel…”
“We propose SOLAR (Subspace-Oriented Latent Adapter Reparameterization), a post-training compression framework that substantially reduces the communication cost (i.e., the number of parameters to trans…”
“We introduce TrACE (Trajectorical Adaptive Compute via agrEement), a training-free controller that allocates LLM calls adaptively across agent timesteps by measuring inter-rollout action agreement.”
“To address these issues, we present SkillClaw, a framework for collective skill evolution in multi-user agent ecosystems, which treats cross-user and over-time interactions as the primary signal for i…”
“To this end, we propose HyperMem, a hypergraph-based hierarchical memory architecture that explicitly models such associations using hyperedges.”
“To address this limitation, we introduce Self-Debias, a progressive framework designed to instill intrinsic self-correction capabilities.”
“We introduce GuarantRAG, a framework that explicitly decouples reasoning from evidence integration.”
“Thus we can conclude that our newly proposed unsupervised feature selection method is promising.”
“This review offers an insightful analysis of VQAs and their progression toward the fault-tolerant regime.”
“We present a hardware-aware Neural Architecture Search (NAS) approach for designing quantum feature maps that are natively executable on IBM quantum processors without transpilation overhead.”
“Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural representations and computational models of vision.”
“We propose Equivariant MeanFlow (EQUIMF), a unified SE(3)-equivariant generative framework that jointly models discrete and continuous components through synchronized MeanFlow dynamics.”
“We therefore introduce Echo Networks, a type of recurrent network that consists of the connection matrix only, with the source neurons of the synapses represented as rows, destination neurons as colum…”
“To address this, we present the shift- and stretch-invariant non-negative matrix factorization framework.”
“To address this gap, we introduce Test-Time Variational Synthesis (TTVS), a novel framework that enables LRMs to self-evolve by dynamically augmenting the training stream from unlabeled test queries.”
“Code is available at: https://github.com/czg1225/DMax”
“EgoEverything is a benchmark that explicitly considers human behavior by leveraging human attention signals, abstracted from gaze data, when generating questions. It comprises over 5,000 multiple choi…”
“We propose a new method, Multiple Embedding Replay Selection, MERS, which replaces the buffer selection module with a graph-based approach that integrates both supervised and self-supervised embedding…”
“In this paper, we introduce HistDiT, a novel latent conditional Diffusion Transformer (DiT) architecture that establishes a new benchmark for visual fidelity in virtual histological staining.”
“We propose Long-Term Embeddings (LTE) as a high-inertia contextual anchor to bridge this gap.”
“To address this, we introduce SIM1, a physics-aligned real-to-sim-to-real data engine that grounds simulation in the physical world.”
“We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin dynamics.”
“We introduce LINE, a novel, training-free iterative approach tailored for open-vocabulary concept labeling in vision models.”
“we study the applicability of Conditional Neural Processes (CNP) to the task of self-supervised multimodal action prediction in robotics.”
“To address this, we propose OVS-DINO, a novel framework that revitalizes latent edge-sensitivity of DINO through structural alignment with the Segment Anything Model (SAM).”
“First, we release MiniF2F-Hard and FIMO-Hard, expert-reannotated Hard Mode variants of two widely-used ATP benchmarks.”
“We introduce InstAP, an Instance-Aware Pre-training framework that jointly optimizes global vision-text alignment and fine-grained, instance-level contrastive alignment by grounding textual mentions t…”
“Second, to address this gap, we introduce Phantasia, a context-adaptive backdoor attack that dynamically aligns its poisoned outputs with the semantics of each input.”
“SNIP (Meidani et al., 2024), a contrastive pre-training model inspired by CLIP, advances LSO by introducing a multi-modal approach: aligning symbolic and numeric encoders in a shared latent space to l…”
“This paper reframes annotation as a measurement process and introduces a statistical framework for decomposing labeling outcomes into interpretable sources of variation: instance difficulty, annotator…”
“In this paper, we propose a Newton-Schulz-based Riemannian Gradient Scheme (NS-RGS) for orthogonal group synchronization that significantly reduces computational cost by replacing the SVD or QR step w…”
“In symmetric binary Gaussian mixtures, the criterion recovers the critical diffusion time detected by the midpoint derivative of the score and agrees with the spectral criterion of Biroli, Bonnaire, d…”
“Did you read the Ronan Farrow piece in The New Yorker about Sam Altman?”
“https://about.fb.com/news/2024/08/why-europe-should-embrace-open-source-ai-zuckerberg-ek”
“# Open Source AI is the Path Forward”
“We propose MM-WebAgent, a hierarchical agentic framework for multimodal webpage generation that coordinates AIGC-based element generation through hierarchical planning and iterative self-reflection.”
“We 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…”
“We introduce IRS (Incongruity-Resolution Supervision), a framework that decomposes humor understanding into three components”
“so 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”
“Blog post by Occupy Wall Street”
“We introduce DiscoTrace, a method to identify the rhetorical strategies that answerers use when responding to information-seeking questions.”
“In 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.”
“Hence, this paper proposes LArge Scale Small ODE (LASS)-ODE-Power, a learning framework for general-purpose time-domain prediction.”
“In 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.”
“We propose SpecGuard, a verification-aware speculative decoding framework that performs step-level verification using only model-internal signals.”
“In this work, we propose XQ-MEval, a semi-automatically built dataset covering nine translation directions, to benchmark translation metrics.”
“To 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…”
“Hence, we contribute a comprehensive dataset, \system, comprising scientific architecture images, their corresponding textual descriptions, and associated DOT code representations.”
“Moving beyond this, we propose \textit{IE-as-Cache}, a framework that repurposes IE as a cognitive cache to enhance agentic reasoning.”
“We 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…”
“In 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…”
“This 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…”
“In this paper, we recast LLM unlearning as an asymmetric two-task problem: retention is the primary objective and forgetting is an auxiliary.”
“We 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…”
“We 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…”
“To address these issues, we propose Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge (CURaTE).”
“We introduce MedImageEdu, a benchmark for multi-turn, evidence-grounded radiology patient education. Each case provides a radiology report with report text and case images.”
“In 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)”
“fails the topological gap protocol (TGP) (Pikulin et al., arXiv:2103.12217”
“So the TLDR is that these two papers drastically reduced the potential resources required to run an algorithm, what is called Shor's algorithm.”
“In this work, we propose Clinical Uncertainty Risk Alignment (CURA), a framework that aligns clinical LM-based risk estimates and uncertainty with both individual error likelihoods and cohort-level am…”
“In this work, we propose a novel framework for efficient model aggregation called the early-stopped aggregation (ESA)”
“We propose Generative Augmented Inference (GAI), a general framework that incorporates AI-generated outputs as informative features for estimating models of human-labeled outcomes.”
“To reconnect these approaches, this state-of-the-art survey provides a structured perspective that maps existing XAI techniques onto the various stages of surrogate modeling workflows for design and e…”
“Our method, which is called Batched Robust iHMM (BR-iHMM), balances adaptivity and robustness with two additional tunable parameters. Across limit order book data, hourly electricity demand, and a syn…”
“M. Aghaee et al., Phys. Rev. B 107, 245424 (2023)”
“To resolve this, we propose HiP-LoRA, a spectrum-aware adaptation framework. ... Experiments on Llama-3.1-8B demonstrate that under matched budgets, HiP-LoRA drastically reduces pretraining degradatio…”
“Our results are in striking contradiction with the model of J. L. Tallon and J. G. Storey [Phys. Rev. B 107, 054507 (2023)]”
“Dickerson, Esmaeili, Morgenstern and Zhang (2023) denote the combination of these two constraints as doubly constrained fair clustering. They present algorithms whose guarantees depend on the best kno…”
“To address this, we introduce RoMem, a drop-in temporal knowledge graph module for structured memory systems, applicable to agentic memory and beyond.”
“This paper reports an unexpected finding: in a deterministic hyperdimensional computing (HDC) architecture based on Galois-field algebra”
“Two recent manuscripts [arXiv:2502.19560, arXiv:2503.08944] engage with the topological gap protocol and its use in Phys. Rev. B 107, 245423 (2023) and Subsection S4.3 of the Supplementary Information…”
“Two recent manuscripts [arXiv:2502.19560, arXiv:2503.08944] engage with the topological gap protocol and its use in Phys. Rev. B 107, 245423 (2023) and Subsection S4.3 of the Supplementary Information…”
“We uphold the conclusions of Phys. Rev. B 107, 245423 (2023) and Nature 638, 651-655 (2025).”
“We uphold the conclusions of Phys. Rev. B 107, 245423 (2023) and Nature 638, 651-655 (2025).”
“Relax supports R3 (Rollout Routing Replay)~\[1\] for MoE models with only 1.9\% overhead”
“Here we introduce \textbf{Contrastive Reasoning Path Synthesis (CRPS)}, a framework that transforms supervision extraction...”
“We propose using k-sparse autoencoders [Makhzani and Frey, 2013] to directly control sparsity, simplifying tuning and improving the reconstruction-sparsity frontier.”
“I would encourage you to take a look at the research paper that will give you all of the findings they had some interesting results”
“I encourage you to look at the research supercluster enabled this team to dramatically speed up their training times”
“more details about these results can be found in our upcoming paper for the isca conference industry track later this year”
“we are publishing a blog post and paper with more details about code compose that said we are still early in our work in this space so we look forward to sharing more”
“which were proposed in [Berry and Mondragon 1987, Proc. R. Soc. A 412 53)”
“Our proposal can either be viewed as an implementation of the entropy computing paradigm presented in [Nguyen et. al. Communications Physics 1, 411, 8]”
“This guarantee also depends on the currently best algorithm for DS-fair k-center given by Jones, Nguyen and Nguyen (2020).”