arXiv:2509.23926v4 Announce Type: replace Abstract: Empirical evidence shows that deep vision networks often represent concepts as directions in latent space with concept information written along directional…
arXiv:2607.10248v2 Announce Type: replace-cross Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical. Each is a mental space…
arXiv:2607.18412v1 Announce Type: cross Abstract: Dynamic graph learning aims to capture evolving structural and semantic patterns in real-world systems, such as fraud detection and recommender systems.…
arXiv:2607.18866v1 Announce Type: cross Abstract: Building on the identity that expected regret equals the covariance between costs and decisions, this paper develops the complete derivative theory…
arXiv:2607.18245v1 Announce Type: new Abstract: Exact-match evaluation of agent-calling obscures qualitatively different failure modes: a model may select the right function yet hallucinate argument values, or…
arXiv:2604.08571v3 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual…
arXiv:2607.19223v1 Announce Type: cross Abstract: Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the…
arXiv:2607.18544v1 Announce Type: new Abstract: Machine olfaction for gas unmixing is an underconstrained inverse problem in which gas compositions must be inferred from low-dimensional, delayed, and…
arXiv:2509.25045v3 Announce Type: replace-cross Abstract: Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods either focus…
arXiv:2607.18289v1 Announce Type: new Abstract: Continual anomaly detection (CAD) studies how models can adapt to evolving data distributions while retaining performance on previously observed regimes. CAD…
arXiv:2607.19170v1 Announce Type: new Abstract: Functional magnetic resonance imaging (fMRI)-based visual decoding aims to recover visual information from measured brain activity, commonly by mapping fMRI responses…
arXiv:2607.16329v2 Announce Type: replace Abstract: Lipschitz continuity is a fundamental property of neural networks that characterizes their sensitivity to input perturbations. It plays a pivotal role…
arXiv:2607.18246v1 Announce Type: new Abstract: We present Phionyx, a deterministic AI runtime architecture derived from the broader Echoism interaction framework that introduces a governance-first approach to…
arXiv:2602.14469v4 Announce Type: replace Abstract: Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but answer-visible generation can justify a pre-committed answer rather than derive…
arXiv:2607.18532v1 Announce Type: new Abstract: Reasoning-specialized language models show large performance gains over base models, yet the internal changes responsible for improved multi-step reasoning remain poorly…
arXiv:2607.18510v1 Announce Type: new Abstract: Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this information loss, yet…
arXiv:2605.20803v2 Announce Type: replace Abstract: Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge. Recent advances…
arXiv:2607.18652v1 Announce Type: cross Abstract: We establish a $widetildeOmega(d^{5/4}sqrt T)$ lower bound on the minimax expected regret of stochastic bandit convex optimization of $1$-Lipschitz functions on…
arXiv:2605.03517v4 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the…
arXiv:2607.19060v1 Announce Type: cross Abstract: Fast prediction of the response of adhesive soft viscoelastic contacts represents a current challenge in soft robotics and for gripping and…
arXiv:2607.18243v1 Announce Type: new Abstract: Agentic AI is crossing trust boundaries faster than current risk models can represent. Existing approaches provide one of two partial views.…
arXiv:2606.08076v2 Announce Type: replace Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely…
arXiv:2502.19737v2 Announce Type: replace Abstract: We introduce XCOMPS in this work, a multilingual conceptual minimal pair dataset covering 17 languages. Using this dataset, we evaluate LLMs'…
arXiv:2607.18539v1 Announce Type: new Abstract: Novel view rendering of large and complex reconstructed scenes is becoming increasingly photorealistic. However, most reconstructions remain static and lack the…