Archives AI News

Addressing divergent representations from causal interventions on neural networks

arXiv:2511.04638v4 Announce Type: replace-cross Abstract: A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encode. Here we ask whether such interventions create out-of-distribution (divergent) representations, and whether…

T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning

arXiv:2506.01317v2 Announce Type: replace-cross Abstract: Instruction tuning is essential for Large Language Models (LLMs) to effectively follow user instructions. To improve training efficiency and reduce data redundancy, recent works use LLM-based scoring functions, e.g., Instruction-Following Difficulty (IFD), to select high-quality…

Interpreting ResNet-based CLIP via Neuron-Attention Decomposition

arXiv:2509.19943v3 Announce Type: replace-cross Abstract: We present a novel technique for interpreting the neurons in CLIP-ResNet by decomposing their contributions to the output into individual computation paths. More specifically, we analyze all pairwise combinations of neurons and the following attention…

Will Humanity Be Rendered Obsolete by AI?

arXiv:2510.22814v3 Announce Type: replace Abstract: This article analyzes the existential risks artificial intelligence (AI) poses to humanity, tracing the trajectory from current AI to ultraintelligence. Drawing on Irving J. Good and Nick Bostrom’s theoretical work, plus recent publications (AI 2027;…

Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification

arXiv:2502.07299v3 Announce Type: replace-cross Abstract: The interactions between DNA, RNA, and proteins are fundamental to biological processes, as illustrated by the central dogma of molecular biology. Although modern biological pre-trained models have achieved great success in analyzing these macromolecules individually,…