arXiv:2602.07090v1 Announce Type: new Abstract: Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform sensitivity across embedding dimensions, leading to excessive noise and degraded utility. We propose SPARSE, a user-centric framework for concept-specific privacy protection in text embeddings. SPARSE combines (1) differentiable mask learning to identify privacy-sensitive dimensions for user-defined concepts, and (2) the Mahalanobis mechanism that […]

Ver mais

arXiv:2512.05251v2 Announce Type: replace Abstract: Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterative steps to produce high-quality samples, leading to high computational costs. We introduce one-step diffusion samplers which learn a step-conditioned ODE so that one large step reproduces the trajectory of many small ones via a state-space consistency loss. We further show that standard ELBO estimates in diffusion samplers degrade in the […]

Ver mais

arXiv:2603.10053v1 Announce Type: new Abstract: The Pickup and Delivery Problem (PDP) is a fundamental and challenging variant of the Vehicle Routing Problem, characterized by tightly coupled pickup–delivery pairs, precedence constraints, and spatial layouts that often exhibit clustering. Existing deep reinforcement learning (DRL) approaches either model all nodes on a flat graph, relying on implicit learning to enforce constraints, or achieve strong performance through inference-time collaborative search at the cost of substantial latency. In this paper, we propose emph{CAADRL} […]

Ver mais

Victoria, Seychelles, February 16, 2026 MEXC, the world’s fastest-growing digital asset exchange and a pioneer of true zero-fee trading, released its February Proof of Reserve report, confirming that all major assets maintained reserve ratios above 100%. BTC reserve coverage rose to 267%, demonstrating the platform’s continued commitment to transparency and user asset protection. The February report shows reserve ratios of 267% for BTC, 112% for ETH, 117% for USDT, and 124% for USDC. MEXC wallet assets total 12,003.98 […]

Ver mais

In many applications, evaluating the effectiveness of different alternatives comes with varying costs or resource usage. Motivated by such heterogeneity, we study the Best Arm Identification with Resource Constraints (BAIwRC) problem, where an agent seeks to identify the best alternative (aka arm) in the presence of resource constraints. Each arm pull consumes one or more types of limited resources. We make two key contributions. First, we propose the Successive Halving with Resource Rationing (SH-RR) algorithm, which integrates resource-aware […]

Ver mais

arXiv:2603.02413v1 Announce Type: new Abstract: Safe highway autonomy for heavy trucks remains an open and unsolved challenge: due to long braking distances, scene understanding of hundreds of meters is required for anticipatory planning and to allow safe braking margins. However, existing driving datasets primarily cover urban scenes, with perception effectively limited to short ranges of only up to 100 meters. To address this gap, we introduce TruckDrive, a highway-scale multimodal driving dataset, captured with a sensor suite purpose-built […]

Ver mais

What if future AIs achieved enlightenment before world domination? Shanahan suggests a truly advanced AI might transcend the human ego, dropping our obsession with the “self.” Instead of triggering a runaway intelligence explosion, such a being could attain satori: a Zen-like peace that halts the singularity in its tracks.

Ver mais

Monitoring is a critical part of running reliable software, yet many teams only discover outages after users complaints starts rolling in. Imagine you get a Slack message at 2 AM, telling you that your APIs are down for over an hour and nobody noticed until customers started complaining. A monitoring service solves this problem by letting you and your team proactively respond to incidents, before problems escalate. In this tutorial, I will be taking you through the steps […]

Ver mais