arXiv:2603.03387v1 Announce Type: new Abstract: Clustering is a fundamental approach to understanding data patterns, wherein the intuitive Euclidean distance space is commonly adopted. However, this is not the case for implicit cluster distributions reflected by qualitative attribute values, e.g., the nominal values of attributes like symptoms, marital status, etc. This paper, therefore, discovered a tree-like distance structure to flexibly represent the local order relationship among intra-attribute qualitative values. That is, treating a value as the vertex of the […]

Ver mais

arXiv:2602.15847v1 Announce Type: new Abstract: Personality steering in large language models (LLMs) commonly relies on injecting trait-specific steering vectors, implicitly assuming that personality traits can be controlled independently. In this work, we examine whether this assumption holds by analysing the geometric relationships between Big Five personality steering directions. We study steering vectors extracted from two model families (LLaMA-3-8B and Mistral-8B) and apply a range of geometric conditioning schemes, from unconstrained directions to soft and hard orthonormalisation. Our results […]

Ver mais

arXiv:2603.07005v1 Announce Type: cross Abstract: A matching platform is a system that matches different types of participants, such as companies and job-seekers. In such a platform, merely maximizing the number of matches can result in matches being concentrated on highly popular participants, which may increase dissatisfaction among other participants, such as companies, and ultimately lead to their churn, reducing the platform’s profit opportunities. To address this issue, we propose a novel online learning problem, Combinatorial Allocation Bandits (CAB), […]

Ver mais

Inspired by Karpathy’s MicroGPT, I wanted to build the equivalent for text diffusion — a minimal implementation that shows the core algorithm without the complexity. Autoregressive models generate left to right. Diffusion generates all tokens at once by iteratively unmasking from noise: _ _ _ _ _ _ → _ o r _ a → n o r i a Three implementations included: – train_minimal.py (143 lines, pure NumPy) — bare minimum – train_pure.py (292 lines, pure NumPy) […]

Ver mais

Our latest image generation model offers advanced world knowledge, production-ready specs, subject consistency and more, all at Flash speed.

Ver mais

arXiv:2603.10047v1 Announce Type: new Abstract: Hallucinations in large language models (LLMs) are outputs that are syntactically coherent but factually incorrect or contextually inconsistent. They are persistent obstacles in high-stakes industrial settings such as engineering design, enterprise resource planning, and IoT telemetry platforms. We present and compare five prompt engineering strategies intended to reduce the variance of model outputs and move toward repeatable, grounded results without modifying model weights or creating complex validation models. These methods include: (M1) Iterative […]

Ver mais

arXiv:2601.04205v1 Announce Type: new Abstract: Unlike autoregressive language models, diffusion language models (DLMs) generate text by iteratively denoising all token positions in parallel. At each timestep, the remasking strategy of a DLM selects low-priority tokens to defer their decoding, thereby improving both efficiency and output quality. However, mainstream remasking strategies rely on a single global confidence threshold, overlooking the temporal and spatial dynamics of individual tokens. Motivated by the redundant iterations and constrained parallelism introduced by fixed-threshold remasking, […]

Ver mais