technocracy

👩🏼‍❤️‍👨🏻 Dating as a timeless human topic Dating is one of the oldest human problems we continue to try to solve with technology, probably because it sits at the intersection of hope, vulnerability, ego, and timing, and rarely follows logic. Long before apps existed, people obsessed over mixed signals, situationships (before they had a name), and spiraling into why this person, why now, and why did it suddenly go cold? Technology didn’t invent this emotional chaos; it simply […]

Ver mais

arXiv:2602.02502v1 Announce Type: new Abstract: Continual learning in natural language processing plays a crucial role in adapting to evolving data and preventing catastrophic forgetting. Despite significant progress, existing methods still face challenges, such as inefficient parameter reuse across tasks, risking catastrophic forgetting when tasks are dissimilar, and the unnecessary introduction of new parameters for each task, which hampers knowledge sharing among similar tasks. To tackle these issues, we propose a Sparse Adapter Fusion Method (SAFM), which dynamically fuses […]

Ver mais

arXiv:2507.21429v2 Announce Type: replace Abstract: Gradient descent (GD) on deep neural network loss landscapes is non-convex, yet often converges far faster in practice than classical guarantees suggest. Prior work shows that within locally quasi-convex regions (LQCRs), GD converges to stationary points at sublinear rates, leaving the commonly observed near-exponential training dynamics unexplained. We show that, under a mild local Neural Tangent Kernel (NTK) stability assumption, the loss satisfies a PL-type error bound within these regions, yielding a Locally […]

Ver mais

arXiv:2602.20193v1 Announce Type: new Abstract: Standard evaluations of backdoor attacks on text-to-image (T2I) models primarily measure trigger activation and visual fidelity. We challenge this paradigm, demonstrating that encoder-side poisoning induces persistent, trigger-free semantic corruption that fundamentally reshapes the representation manifold. We trace this vulnerability to a geometric mechanism: a Jacobian-based analysis reveals that backdoors act as low-rank, target-centered deformations that amplify local sensitivity, causing distortion to propagate coherently across semantic neighborhoods. To rigorously quantify this structural degradation, we […]

Ver mais

We have been learning quickly from how people are using Sora and taking feedback from users, rightsholders, and other interested groups. We of course spent a lot of time discussing this before launch, but now that we have a product out we can do more than just theorize. We are going to make two changes soon (and many more to come). First, we will give rightsholders more granular control over generation of characters, similar to the opt-in model […]

Ver mais

arXiv:2602.19703v1 Announce Type: cross Abstract: We propose a framework for testing the homogeneity of conditional average treatment effects (CATEs) across multiple experimental and observational studies. Our approach leverages multiple randomized trials to assess whether treatment effects vary with unobserved heterogeneity that differs across trials: if CATEs are homogeneous, this indicates the absence of interactions between treatment and unobservables in the mean effect. Comparing CATEs between experimental and observational data further allows evaluation of potential confounding: if the estimands […]

Ver mais

What web browsers do when a user requests a page is quite a remarkable journey. My goodness, the process behind the curtains reflects a diligent effort by the folks who build browsers. So far, I’ve found it very interesting to navigate through the steps taken to draw pixels on the screen. I’ll admit it—this is a surprisingly deep and fascinating area. As developers, we tend to focus heavily on performance, especially when building at scale. If we want […]

Ver mais

arXiv:2601.10930v1 Announce Type: new Abstract: A key challenge in contact-rich dexterous manipulation is the need to jointly reason over geometry, kinematic constraints, and intricate, nonsmooth contact dynamics. End-to-end visuomotor policies bypass this structure, but often require large amounts of data, transfer poorly from simulation to reality, and generalize weakly across tasks/embodiments. We address those limitations by leveraging a simple insight: dexterous manipulation is inherently hierarchical – at a high level, a robot decides where to touch (geometry) and […]

Ver mais