arXiv:2603.20991v1 Announce Type: cross Abstract: A single matrix out of 468 in GPT-2 Small can increase perplexity by 20,000x when…
arXiv:2603.21108v1 Announce Type: cross Abstract: Molecular property prediction constitutes a cornerstone of drug discovery and materials science, necessitating models capable…
arXiv:2603.20729v1 Announce Type: cross Abstract: Acoustic borehole images provide high-resolution borehole-wall structure, but large-scale interpretation remains difficult because dense expert…
arXiv:2603.20897v1 Announce Type: cross Abstract: The strong and continuous increase of AI-based services leads to the steady proliferation of AI…
arXiv:2603.20449v1 Announce Type: cross Abstract: Tool-augmented Large Language Models (TaLLMs) extend LLMs with the ability to invoke external tools, enabling…
arXiv:2603.20246v1 Announce Type: cross Abstract: Speech brain–computer interfaces require decoders that translate intracortical activity into linguistic output while remaining robust…
arXiv:2603.20266v1 Announce Type: cross Abstract: Despite the rapid advancements in Artificial Intelligence (AI), Stochastic Differential Equations (SDEs) remain the gold-standard…
arXiv:2603.20204v1 Announce Type: cross Abstract: Understanding how interdisciplinary research teams converge on shared knowledge is a persistent challenge. This paper…
arXiv:2603.20223v1 Announce Type: cross Abstract: Immediate feedback is a foundational requirement of effective AI-mediated learning, yet the energy and latency…
arXiv:2603.21708v1 Announce Type: new Abstract: Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in…
