Quality follows upgrading
Academic
arXiv:2603.16985v1 Announce Type: new Abstract: Transformer-based models have been widely adopted for time-series forecasting due to their high representational capacity and architectural flexibility. However, many …
arXiv:2603.17019v1 Announce Type: new Abstract: A central question in the LLM debate is whether transformers can infer rules absent from training, or whether apparent generalisation …
arXiv:2603.17044v1 Announce Type: new Abstract: Unified multimodal models share a language model backbone for both understanding and generating images. Can DPO align both capabilities simultaneously? …
arXiv:2603.17048v1 Announce Type: new Abstract: Modern neural networks achieve strong performance but remain difficult to interpret in high-dimensional visual domains. Counterfactual explanations (CFEs) provide a …
arXiv:2603.17052v1 Announce Type: new Abstract: Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is …
arXiv:2603.17074v1 Announce Type: new Abstract: We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven …
arXiv:2603.17075v1 Announce Type: new Abstract: Motivated by auto-proof generation and Valiant's VP vs. VNP conjecture, we study the problem of discovering efficient arithmetic circuits to …
arXiv:2603.17109v1 Announce Type: new Abstract: Decoding brain activity into natural language is a major challenge in AI with important applications in assistive communication, neurotechnology, and …
arXiv:2603.17126v1 Announce Type: new Abstract: Many wireless vision applications, such as autonomous driving, require preservation of global structural information rather than only per-pixel fidelity. However, …
arXiv:2603.17139v1 Announce Type: new Abstract: Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we propose a sequential learning-and-optimization …
arXiv:2603.17145v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known …
arXiv:2603.17148v1 Announce Type: new Abstract: Personalized fall detection models can significantly improve accuracy by adapting to individual motion patterns, yet their effectiveness is often limited …
