arXiv:2604.04930v2 Announce Type: replace-cross Abstract: Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking. A key challenge is determining when the…
arXiv:2603.09868v2 Announce Type: replace Abstract: Accurately quantifying terrestrial carbon exchange is essential for climate policy and carbon accounting, yet models must generalize to ecosystems underrepresented in sparse eddy covariance observations. Despite this challenge being a natural instance of zero-shot spatial…
arXiv:2608.13756v1 Announce Type: new Abstract: Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable. We test that assumption: holding the checkpoint, prompts, hardware, inference engine, decoding, and quantization configuration fixed, we swap only the…
arXiv:2608.13668v1 Announce Type: new Abstract: Linear attention keeps a state of fixed size. At long context, many stored items share this state, and interference between them degrades retrieval. Gated DeltaNet-2 (GDN-2), like every delta-rule model before it, derives its erase…
arXiv:2507.02169v2 Announce Type: replace Abstract: Machine learning models are often used in applications where their inputs change due to routine interactions, strategic manipulation, or noise. In such settings, models can undermine safety as these changes lead them to predict over…
arXiv:2608.13721v1 Announce Type: new Abstract: In reasoning supervised fine-tuning, candidate responses for the same instruction can differ substantially in how well they match the student’s current distribution. Recent likelihood-based response selection methods suggest that responses closer to the student distribution…
arXiv:2507.13505v2 Announce Type: replace-cross Abstract: Cybersecurity simulation environments, such as cyber ranges, honeypots, and sandboxes, require realistic human behavior to be effective, yet no quantitative method exists to assess the behavioral fidelity of synthetic user personas. This paper presents PHASE…
arXiv:2608.13675v1 Announce Type: new Abstract: Between October 2018 and July 2026 AI models progressed from simple systems like BERT to massive agents that solve complex math and write software. The ability to resolve real coding issues improved by nearly six…
arXiv:2605.25194v2 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the underlying mechanisms and struggle to balance efficiency and defense utility. In…
arXiv:2607.07003v3 Announce Type: replace Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, agreeing with a user’s statement even when it is incorrect. While often studied as a single, uniform behavior, sycophancy can manifest in substantially distinct ways across contexts, raising…
