SUPER INTELLIGENCE BREAK
A focused stream of intelligence from the sources you trust.
arXiv:2610.20632v1 Announce Type: new Abstract: Modern healthcare generates increasingly complex medical reports that challenge clinical professionals in terms of time and interpretive burden. Manual review processes are slow, error-prone, and difficult to scale. This…
arXiv:2610.20634v1 Announce Type: new Abstract: Retrieval-augmented generation asks one question at volume: does this evidence support this claim? The answer is one bit, yet most pipelines obtain it from a text generator and pay…
arXiv:2610.20633v1 Announce Type: new Abstract: Long-horizon failures of language models are usually measured as end-task success or as a horizon length. We instead score, step by step, three components of a 400-step ledger task…
arXiv:2610.21330v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for election information, yet little is known about how external web content shapes the political information they present. Generative engine optimization (GEO)…
arXiv:2610.20635v1 Announce Type: new Abstract: Permutation generation with language models requires both text-conditioned ranking and a global one-to-one assignment between candidates and output positions. We study this problem through three diffusion-LLM parameterizations: hard-assignment prediction…
arXiv:2610.22344v1 Announce Type: cross Abstract: Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a pathway toward recursive…
arXiv:2610.22029v1 Announce Type: cross Abstract: Self-evolving language models train on tasks they generate, so every round must decide which updated model the next round inherits. Current loops such as R-Zero, Agent0, and Skill Self-Play…
arXiv:2607.11183v4 Announce Type: replace Abstract: We study Amplitude Gating (AG), an inference-time intervention that masks feed-forward network (FFN) activation coordinates while keeping pretrained weights fixed. Six SwiGLU sites separate shared and gate-only inputs, expanded…
arXiv:2603.22735v3 Announce Type: replace Abstract: Existing NLP work commonly treats contradictions as errors to be resolved by choosing which statements to accept or discard. Yet a key aspect of human reasoning in social and…
arXiv:2610.20419v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) models have become almost a cornerstone of open-domain question answering tasks; in which the quality of answers generated in the process, greatly relies on the effectiveness…
arXiv:2609.33465v3 Announce Type: replace Abstract: Improving language model efficiency requires not only cheaper operations but also eliminating redundant computation. We argue that effective modeling requires information accessibility and computational depth, but not repeated historical…
arXiv:2603.11611v2 Announce Type: replace Abstract: Rotary Positional Embedding (RoPE) is widely used in transformers to encode relative positional information, yet the effect of applying RoPE to only a subset of hidden dimensions remains underexplored.…