Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
Academic
arXiv:2604.02644v1 Announce Type: new Abstract: We present Conditional Wasserstein Autoencoders (CWAEs), a framework for conditional simulation that exploits low-dimensional structure in both the conditioned and …
arXiv:2604.02608v1 Announce Type: new Abstract: Function vectors (FVs) -- mean-difference directions extracted from in-context learning demonstrations -- can steer large language model behavior when added …
arXiv:2604.02926v1 Announce Type: new Abstract: The article proposes a new architecture based on Multi-head attention to solve the problem of morphological tagging for the Russian …
arXiv:2604.02511v1 Announce Type: new Abstract: Public pooled single-cell perturbation atlases are valuable resources for studying transcription factor (TF) function, but downstream re-analysis can be limited …
arXiv:2604.02638v1 Announce Type: new Abstract: We propose AXELRAM, a smart SRAM macro architecture that computes attention scores directly from quantized KV cache indices without dequantization. …
arXiv:2604.02459v1 Announce Type: new Abstract: We study the geometric structure of layer updates in deep language models. Rather than analyzing what information is encoded in …
arXiv:2604.02500v1 Announce Type: new Abstract: As ongoing research explores the ability of AI agents to be insider threats and act against company interests, we showcase …
arXiv:2604.02795v1 Announce Type: new Abstract: Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction …
arXiv:2604.02361v1 Announce Type: cross Abstract: Detecting Internet routing instability is a critical yet challenging task, particularly when relying solely on endpoint active measurements. This study …
arXiv:2604.02605v1 Announce Type: new Abstract: Audio-Visual Large Language Models (AVLLMs) are emerging as unified interfaces to multimodal perception. We present the first mechanistic interpretability study …
arXiv:2604.02369v1 Announce Type: cross Abstract: Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other …
arXiv:2604.02389v1 Announce Type: cross Abstract: Audio-visual Navigation refers to an agent utilizing visual and auditory information in complex 3D environments to accomplish target localization and …