arxivJul 24
arXiv:2607.20799v1 Announce Type: new Abstract: Scalar metrics are often used to evaluate clusterings against known classes, but they can obscure a fundamental trade-off: clusterings should be informative about class labels while avoiding unnecessary fragmentation. Here we describe normalized scores
arxivJul 2
arXiv:2607.00233v1 Announce Type: new Abstract: How do two agents invent a shared language from scratch? In a Lewis signaling game, a sender and receiver must coordinate on a code using only their interaction history. We study five memory architectures across varying channel configurations with LLM
arxivJun 24
arXiv:2606.22406v2 Announce Type: replace Abstract: Attention mechanisms have demonstrated remarkable empirical success in identifying relevant information from large collections of tokens, yet the theoretical principles underlying this behavior remain poorly understood. We study a stylized softmax-
arxivMay 29
arXiv:2605.29900v1 Announce Type: new Abstract: Contrastive learning is effective for aligning paired views or modalities, but alignment beyond two modalities remains non-trivial and comparatively underexplored. Pairwise CLIP-style losses decompose multi-modal alignment into independent two-way comp
arxivMay 1
arXiv:2508.05469v3 Announce Type: replace Abstract: We evaluate artificial intelligence (AI) systems without ground truth by exploiting a link between strategic gaming and information loss. Building on established information theory, we analyze which mechanisms resist adversarial manipulation. This
arxivApr 21bullish
arXiv:2604.15356v1 Announce Type: cross Abstract: Recent work on KV cache quantization, culminating in TurboQuant, has approached the Shannon entropy limit for per-vector compression of transformer key-value caches. We observe that this limit applies to a strictly weaker problem than the one that ac
arxivApr 3
arXiv:2604.02255v1 Announce Type: cross Abstract: In this paper, we consider a multi-armed bandit (MAB) instance and study how to identify the best arm when arm commands are conveyed from a central learner to a distributed agent over a discrete memoryless channel (DMC). Depending on the agent capabi