technocracy

arXiv:2603.29010v1 Announce Type: new Abstract: Optimizing GPU kernels with LLM agents is an iterative process over a large design space. Every candidate must be generated, compiled, validated, and profiled, so fewer trials will save both runtime and cost. We make two key observations. First, the abstraction level that agents operate at is important. If it is too low, the LLM wastes reasoning on low-impact details. If it is too high, it may miss important optimization choices. Second, agents […]

Ver mais

:::info Astounding Stories of Super-Science July, 2008, by Astounding Stories is part of HackerNoon’s Book Blog Post series. You can jump to any chapter in this book here. The Call of the Wild – Into the Primitive Astounding Stories of Super-Science July 2008: The Call of the Wild – Into the Primitive By Jack London ::: Old longings nomadic leap, n Chafing at custom’s chain; n Again from its brumal sleep n Wakens the ferine strain. Buck did not […]

Ver mais

arXiv:2602.13324v1 Announce Type: new Abstract: Deploying autonomous edge robotics in dynamic military environments is constrained by both scarce domain-specific training data and the computational limits of edge hardware. This paper introduces a hierarchical, zero-shot framework that cascades lightweight object detection with compact Vision-Language Models (VLMs) from the Qwen and Gemma families (4B-12B parameters). Grounding DINO serves as a high-recall, text-promptable region proposer, and frames with high detection confidence are passed to edge-class VLMs for semantic verification. We evaluate […]

Ver mais

arXiv:2603.05540v1 Announce Type: new Abstract: We study grammar-constrained decoding (GCD) as a coupling between an autoregressive next-token distribution and a reachability oracle over a pushdown system compiled from a context-free grammar (CFG). We prove an oracle invariance theorem: language-equivalent grammars induce identical admissible next-token sets for every prefix, hence identical logit masks, yet can yield provably different compiled state spaces and online ambiguity costs. We give exact control-state blowup counts for the canonical $a^n b^n$ language under redundant […]

Ver mais

arXiv:2602.21765v1 Announce Type: cross Abstract: Alignment and adaptation in large language models heavily rely on reinforcement learning from human feedback (RLHF); yet, theoretical understanding of its generalisability remains premature, especially when the learned reward could shift, and the KL control is estimated and clipped. To address this issue, we develop generalisation theory for RLHF that explicitly accounts for (1) emph{reward shift}: reward models are trained on preference data from earlier or mixed behaviour policies while RLHF optimises the […]

Ver mais

arXiv:2603.24829v1 Announce Type: new Abstract: We propose a general framework to extend Flow Matching to homogeneous spaces, i.e. quotients of Lie groups. Our approach reformulates the problem as a flow matching task on the underlying Lie group by lifting the data distributions. This strategy avoids the potentially complicated geometry of homogeneous spaces by working directly on Lie groups, which in turn enables us reduce the problem to a Euclidean flow matching task on Lie algebras. In contrast to […]

Ver mais

arXiv:2604.14338v1 Announce Type: new Abstract: We introduce path-sampled integrated gradients (PS-IG), a framework that generalizes feature attribution by computing the expected value over baselines sampled along the linear interpolation path. We prove that PS-IG is mathematically equivalent to path-weighted integrated gradients, provided the weighting function matches the cumulative distribution function of the sampling density. This equivalence allows the stochastic expectation to be evaluated via a deterministic Riemann sum, improving the error convergence rate from $O(m^{-1/2})$ to $O(m^{-1})$ for […]

Ver mais

arXiv:2602.12389v1 Announce Type: new Abstract: Temporal knowledge graph (TKG) forecasting requires predicting future facts by jointly modeling structural dependencies within each snapshot and temporal evolution across snapshots. However, most existing methods are stateless: they recompute entity representations at each timestamp from a limited query window, leading to episodic amnesia and rapid decay of long-term dependencies. To address this limitation, we propose Entity State Tuning (EST), an encoder-agnostic framework that endows TKG forecasters with persistent and continuously evolving entity […]

Ver mais

If you use Samsung products, including its smartphones and home appliances in particular, you might be aware of its in-house Bixby assistant. In the AI era, where Gemini and ChatGPT are dominating, Bixby feels dated. That being said, Samsung hasn’t given up on Bixby. Why am I saying this? Well, fresh leaks surfaced on the internet suggest that Samsung is planning a massive update for Bixby with the upcoming One UI 8.5 update. Per the leaked details, including […]

Ver mais