📄 Papers×1 mentions
Secfeddnn
“Frameworks, such as DFGL-LZTA, SecFedDNN and COSIER were assessed.”
paper: Decentralized Mechanisms Bolster IoT Edge Security via Privacy, Resilience, and Adaptive Threat Response — 2026-04-21
What the smart people are recommending. 7867 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.
“Frameworks, such as DFGL-LZTA, SecFedDNN and COSIER were assessed.”
“Frameworks, such as DFGL-LZTA, SecFedDNN and COSIER were assessed.”
“To address these limitations, we propose ROAM (Region-graph OptimAl-transport Mixture-of-experts), a spatially aware MoE-MIL aggregator that routes region tokens to expert poolers via capacity-constra…”
“To tackle this challenge, we propose SL-FAC, a communication-efficient SL framework comprising two key components: adaptive frequency decomposition (AFD) and frequency-based quantization compression (…”
“We develop a theoretical framework for $NNGP$ and $GPnn$ regression. Under mild regularity assumptions, we derive almost sure pointwise limits for three key predictive criteria: mean squared error ($M…”
“Project page: https://scene-the-ella.github.io/meol/”
“An excellent post explaining the importance of Ethereum having a dynamically available consensus, that both provides economic finality and ensures chain progress even under conditions where economic f…”
“The Role of Immigration in the Fall of the Roman Empire”
“# Interface choice for your visionOS app _Blog post by VisionOS_”
“Let's talk about your newest essay on uh the age of intelligence”
“# Immersive space coordinate system”
“We present Broken Quantum, the first comprehensive formal security audit of the open-source quantum computing simulator ecosystem.”
“# FTAI Could Be Violating U.S. Sanctions Against Iran (FTAI US) _Blog post by Muddy Waters_”
“MW is Short e.l.f. Beauty, Inc. (ELF US)”
“My colleague Stephanie Palazzolo has some exclusive reporting around Fiji's CIMO's decision at OpenAI to buy TBPN. According to Steph's reporting, Fiji had the idea earlier this year as she was trying…”
“The second piece I want to highlight, we have some new data out from an exclusive survey that we ran at the Information with our subscribers. A majority think that conditions for tech companies will w…”
“# Eurofins Scientific Part II: Nothing but Net (ERF.FP)”
“MW is Short FTAI Aviation Ltd. (FTAI US)”
“First, we release MiniF2F-Hard and FIMO-Hard, expert-reannotated Hard Mode variants of two widely-used ATP benchmarks.”
“This paper introduces the Informational Buildup Framework (IBF), an alternative substrate for continual learning, based on the premise that information is the achievement of structural alignment rathe…”
“With DINO-QPM we make the level of interpretability of QPM available as an adapter while exceeding the accuracy of DINOv2 linear probe. Evaluated through an introduced Plausibility metric and other in…”
“In this paper, we propose T-STAR(Tree-structured Self-Taught Agent Rectification), a framework that recovers the latent correlated reward structure across seemingly independent trajectories.”
“To address this gap, we introduce TraceSafe-Bench, the first comprehensive benchmark specifically designed to assess mid-trajectory safety.”
“We introduce MoRight, a unified framework that addresses both limitations through disentangled motion modeling.”
“This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing …”
“We initiate the study of differentially private (DP) language identification and generation in the agnostic statistical setting, establishing algorithms and matching lower bounds that precisely quanti…”
“To address this, we propose Mixed-Initiative Context, which reconceptualizes the context formed across multi-turn interactions as an explicit, structured, and manipulable interactive object.”
“To address these challenges, we propose STRIDE-ED, a STRategy-grounded, Interpretable, and DEep reasoning framework that models Empathetic Dialogue through structured, strategy-conditioned reasoning.”
“Code and models are released on our project page: https://m80hz.github.io/kite/”
“We term this the Logic Monopoly -- the agent society's unchecked monopoly over the entire logic chain from planning through execution to evaluation. We propose the Separation of Power (SoP) model, a c…”
“The paper introduces, ClickGuard: a trustworthy adaptive fusion framework for clickbait detection.”
“In this paper, we address this tradeoff by proposing ReDAct (Reason-Defer-Act).”
“We introduce SalesLLM, a bilingual (ZH/EN) benchmark derived from realistic applications covering Financial Services and Consumer Goods, built from 30,074 scripted configurations and 1,805 curated mul…”
“We present the first systematic characterization of LoS bias, distinguishing negative and positive forms, and introduce the human-annotated dataset LOBSTER (Language-Of-study Bias in ScienTific pEer R…”
“To test external validity, the agent replicated two published studies on the CLMET corpus (40 million tokens) - Claridge (2025) and De Smet (2013) - with close quantitative agreement.”
“To test external validity, the agent replicated two published studies on the CLMET corpus (40 million tokens) - Claridge (2025) and De Smet (2013) - with close quantitative agreement.”
“To address this limitation, we introduce Flow Motion Policy, an open-loop, end-to-end neural motion planner for robotic manipulators that leverages the stochastic generative formulation of flow matchi…”
“In this paper, we propose Counterfactual Averaging for Fair Predictions (CAFP), a model-agnostic post-processing method that mitigates unfair influence from protected attributes without retraining or …”
“There's another Super popular paper that you author call koala cognitive architectures for language agents”
“We introduces EmoMAS, a Bayesian multi-agent framework that transforms emotional decision-making from reactive to strategic.”
“We propose Conformal Margin Risk Minimization (CMRM), a plug-and-play envelope framework that improves any classification loss under label noise by adding a single quantile-calibrated regularization t…”
“In this work, we introduce In-Place Test-Time Training (In-Place TTT), a framework that seamlessly endows LLMs with Test-Time Training ability.”
“For squared loss, especially, we develop Unlearning Least Squares (ULS) and establish its minimax optimality for estimating the model parameter of remaining data when only the pre-trained estimator, f…”
“This paper provides a controlled benchmark of embedding choices for graph classification, comparing classical baselines with quantum-oriented node representations under a unified pipeline.”
“This suggests that iTAG-generated data can serve as a practical surrogate for scalable benchmarking of text-based causal discovery algorithms.”
“We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an instruction-tuned AR model to predict multiple tokens per forward pass.”
“In this paper, we propose HingeMem, a boundary-guided long-term memory that operationalizes event segmentation theory to build an interpretable indexing interface via boundary-triggered hyperedges ove…”
“We present Fast-dVLM, a block-diffusion-based VLM that enables KV-cache-compatible parallel decoding and speculative block decoding for inference acceleration. ... Extensive experiments across 11 mult…”
“This paper presents the first large-scale comparative study of bias in skin-toned emoji representations across two distinct model classes.”
“We propose DIVI, a data-informed variational clustering framework that combines global feature gating with split-based adaptive structure growth. DIVI uses informative prior initialization to stabiliz…”
“In this work, we propose the Bi-Lipschitz Autoencoder (BLAE), which introduces two key innovations: (1) an injective regularization scheme based on a separation criterion to eliminate pathological loc…”
“Motivated by the complementary strengths of generative and discriminative classifiers, we propose Generative Cross-Entropy (GCE), which maximizes $p(x|y)$ and is equivalent to cross-entropy augmented …”
“This answers a recent open question of Girish (arXiv:2510.06385) on the power of commuting quantum computations.”
“To address these limitations, we propose a novel Chain-of-Thought framework based on Reversible Hierarchical Markov Chain, termed Cognitive Loop of Thought (CLoT), and a backward reasoning dataset CLo…”
“Telgarsky-Vattani note a typical improvement of 5% -- 10%.”
“We present SemEval-2026 Task 9, a shared task on online polarization detection, covering 22 languages and comprising over 110K annotated instances.”
“Under general assumptions on the target distribution $p^★$, we establish a sharp Lipschitz regularity theory for flow-matching vector fields and diffusion-model scores, with optimal dependence on time…”
“To address this, we introduce the individual-heterogeneous sub-Gaussian mixture model, a flexible framework that assigns each observation its own heterogeneity parameter, thereby explicitly capturing …”
“We propose blind-spot mass B_n(tau), a deployment metric estimating the total probability mass assigned to states whose empirical support falls below a threshold tau. B_n(tau) is computed using Good-T…”
“We introduce Machine-Learning-Assisted Generalized Entropy Calibration (MEC), a cross-fitted, calibration-weighted variant of PPI.”
“Prediction-powered inference (PPI) leverages a machine-learning predictor trained on a small labeled sample to improve efficiency, but it can lose efficiency under model misspecification and suffer fr…”
“# If You Want to Learn, Do”
“In this paper, we propose FLOWGEM, a principled iterative method for generating a complete dataset from a dataset with values Missing at Random (MAR).”
“Predicting Properties of Molecules with Machine Learning”
“this is a famous paper by Ed far look at optimization where you can come up with circuits that will be uh potentially useful for these problems”
“# ReAct: Synergizing Reasoning and Acting in Language Models”
“# EfficientDet: Towards Scalable and Efficient Object Detection”
“# Deciphering language processing in the human brain through LLM representations”
“# Image-Text Pre-training with Contrastive Captioners _Blog post by Google Brain_”
“# Self-Supervised Learning Advances Medical Image Analysis”
“https://mustafa-suleyman.ai/your-ai-companion”
“A more personal AI for all”
“# Containment for AI - how to adapt a Cold War strategy to a new threat _Blog post by Mustafa Suleyman_”
“To address this issue, we propose QuIKS, an instant key supply scheme based on adaptive buffering, offering the dominant advantage of near-zero key supply latency while consuming ultra-low key resourc…”
“We have shown in a previous work arxiv:2411.09256 that types are represented by boolean functions called type functions, and that each such function is characterized by a related structure poset.”
“We derive the volume-law coefficient of the entanglement entropy by generalizing the mean-field approach from [Phys. Rev. Lett. 119, 220603 (2017)]”
“which agrees with previous analytical and numerical results from [Phys. Rev. B 110, 235154 (2024)]”
“We use this to show that $(\mathsf{BPP}^{\mathsf{IQP}})^O \not\subseteq \mathsf{PH}^O$ relative to an oracle $O$, strengthening the result of Raz and Tal (STOC 2019).”
“This paper introduces Reinforcement Learning System-Theoretic Process Analysis (RL-STPA), a framework that adapts conventional STPA's systematic hazard analysis to address RL's unique challenges throu…”
“This paper presents Prism, the first symbolic superoptimizer for tensor programs. The key idea is sGraph, a symbolic, hierarchical representation that compactly encodes large classes of tensor program…”
“To tackle this challenge, this paper introduces Interrogative Uncertainty Quantification (IUQ), a novel framework that leverages inter-sample consistency and intra-sample faithfulness to quantify the …”
“Based on this insight, we propose LongAct, a strategy that shifts from uniform to saliency-guided sparse updates. By selectively updating only the weights associated with these significant activations…”
“Flow matching retains the generation quality of diffusion models while enabling substantially faster inference, making it a compelling paradigm for generative modeling.”
“To address these challenges, we propose a mixture-of-experts flow matching (MoE-FM) framework, which captures complex global transport geometries in latent space by decomposing them into locally speci…”
“Building on MoE-FM, we develop a non-autoregressive (NAR) language modeling approach, named YAN, instantiated with both Transformer and Mamba architectures.”
“This work in total represents compelling evidence that adopting QEC primitives on current-generation devices can deliver substantial net benefits.”
“I always find mysteries interesting and, you know, we'll see whether it was an enjoyable read. Like, I really do enjoy like the the forensic linguistics because I wonder if my footprint is just so eas…”
“This makes AdaCubic an attractive option for researchers and practitioners alike.”
“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”
“It has become clear that Hartigan's algorithm (1975) gives better results in almost all cases”
“Before we start on quantum”