Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and previous stages, allowing new-task supervision to induce geometric distortion. We observe that the most pronounced drift tends to concentrate in vulnerable neighborhoods near the old-new semantic interface, where shared visual patterns are easily re-explained by new textual semantics. To address this under an exemplar-free constraint, we propose Semantic […]

Ver mais

arXiv:2604.13069v1 Announce Type: new Abstract: Artificial intelligence (AI) control protocols assume that trusted large language model (LLM) monitors reliably assess proposed actions across all deployment contexts. This paper tests that assumption in the geographic dimension. We audit Claude Opus 4.6-the monitor specified in Apart Research’s AI Control Hackathon Track 3 benchmark-for systematic gaps in its factual knowledge of the global AI landscape. We develop the AI Control Knowledge Framework (ACKF), a six-dimension thematic scheme, and operationalise it with […]

Ver mais

arXiv:2601.04272v1 Announce Type: new Abstract: The paper introduces a basic logic of knowledge and abduction by extending Levesque logic of only-knowing with an abduction modal operator defined via the combination of basic epistemic concepts. The upshot is an alternative approach to abduction that employs a modal vocabulary and explores the relation between abductive reasoning and epistemic states of only knowing. Furthermore, by incorporating a preferential relation into modal frames, we provide a non-monotonic extension of our basic framework […]

Ver mais

In the dynamic world of software engineering, where technical mastery meets strategic business impact, exceptional professionals distinguish themselves through transformative solutions while nurturing engineering talent. Rishabh Agarwal’s eight-year journey across retail, financial services, consulting, and entertainment sectors exemplifies how curiosity-driven learning, combined with relentless performance optimization, creates compounding organizational value. The Foundation: From Hardware Fascination to Software Innovation Rishabh’s engineering journey began with an unexpected pivot. Initially drawn to computer engineering and fascinated by physical system architecture, he […]

Ver mais

arXiv:2604.02504v1 Announce Type: new Abstract: Electric utilities must make massive capital investments in the coming years to respond to explosive growth in demand, aging assets and rising threats from extreme weather. Utilities today already have rigorous frameworks for capital planning, and there are opportunities to extend this capability to solve multi-objective optimization problems in the face of uncertainty. This work presents a four-part framework that 1) incorporates extreme weather as a source of uncertainty, 2) leverages a digital […]

Ver mais

arXiv:2602.06065v2 Announce Type: replace Abstract: Understanding how the structure of language can be learned from sentences alone is a central question in both cognitive science and machine learning. Studies of the internal representations of Large Language Models (LLMs) support their ability to parse text when predicting the next word, while representing semantic notions independently of surface form. Yet, which data statistics make these feats possible, and how much data is required, remain largely unknown. Probabilistic context-free grammars (PCFGs) […]

Ver mais

arXiv:2601.02609v1 Announce Type: cross Abstract: Large language model fine-tuning is bottlenecked by memory: a 7B parameter model requires 84GB–14GB for weights, 14GB for gradients, and 56GB for FP32 optimizer states–exceeding even A100-40GB capacity. We present Chronicals, an open-source training framework achieving 3.51x speedup over Unsloth through four synergistic optimizations: (1) fused Triton kernels eliminating 75% of memory traffic via RMSNorm (7x), SwiGLU (5x), and QK-RoPE (2.3x) fusion; (2) Cut Cross-Entropy reducing logit memory from 5GB to 135MB through […]

Ver mais

arXiv:2603.03378v2 Announce Type: new Abstract: Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe action execution under permission-governed environments, and the inability of closed systems to improve from failures. We present AOI (Autonomous Operations Intelligence), a trainable multi-agent framework formulating automated operations as a structured trajectory learning problem under security constraints. Our approach integrates three key […]

Ver mais