arXiv:2608.07476v1 Announce Type: new Abstract: We develop a formal framework for constructing canonical interpretations from plural structure theories. A structure theory is a triple T =…
arXiv:2608.07480v1 Announce Type: new Abstract: Active inference has emerged as a principled framework for modeling adaptive behavior by balancing goal-directed action with uncertainty reduction. It has…
arXiv:2608.07524v1 Announce Type: new Abstract: Training deep learning models on variable long sequences poses significant computational challenges. Existing methods force a difficult trade-off between efficiency and…
arXiv:2608.07530v1 Announce Type: new Abstract: SHACL is a core technology for validating the conformance of RDF knowledge graphs (KGs). Yet, authoring SHACL shapes requires technical expertise…
arXiv:2608.07528v1 Announce Type: new Abstract: Linear probes detect corrupted context in language models with near-perfect accuracy, yet this does not translate into reliable failure prediction. The…
arXiv:2403.09752v4 Announce Type: replace-cross Abstract: The Internet of Medical Things transcends traditional medical boundaries, enabling a transition from reactive treatment to proactive prevention. This innovative method…
arXiv:2608.07532v1 Announce Type: new Abstract: Modern agentic AI systems combine multiple large language model agents with heterogeneous skills, yet most architectures either fix communication in advance…
arXiv:2606.16462v2 Announce Type: replace-cross Abstract: Cross-subject EEG decoding promises more training data, but it also exposes neural networks to strong inter-subject distribution shifts. We study whether…
arXiv:2602.07697v3 Announce Type: replace-cross Abstract: Predictive coding (PC) is a biologically plausible alternative to standard backpropagation (BP) that minimises an energy function with respect to network…
arXiv:2608.09251v1 Announce Type: cross Abstract: Large language model-based multi-agent systems have recently shown strong potential for complex, long-horizon tasks. However, existing methods mainly rely on coarse…
arXiv:2608.08994v1 Announce Type: cross Abstract: Retrieving relevant evidence from noisy web data is challenging, particularly in sensitive domains containing incomplete reports, heterogeneous language, and irrelevant content.…
arXiv:2608.09873v1 Announce Type: cross Abstract: We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated examples…
arXiv:2608.09532v1 Announce Type: cross Abstract: Enterprises increasingly seek to query data lakes using natural language via AI-driven tools like semantic operators or deep research agents. However,…
Article URL: https://whatever.scalzi.com/2026/08/10/why-my-father-is-wrong-a-defense-of-guitar-hero/ Comments URL: https://news.ycombinator.com/item?id=49253176 Points: 16 # Comments: 2
I wanted to find out whether a huge text-only MoE could be given basic vision without retraining the language model itself. The short answer is yes.…
A few things right off the bat: it reasons very efficiently. Like Grok 4.5 levels of efficient thinking it quantizes very well. My first few tests…
Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized around two…
As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under serious scrutiny:…
We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.2 billion activated per token. Each sparse MoE layer contains 384…
We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated examples spanning 60 subjects across four…
Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges. First, trajectory-indexed utilities grow with the interaction history, thereby dispersing limited feedback over an…
On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insufficient probability to other plausible continuations. Teacher entropy alone does…
TL;DRMachine unlearning is a proposed technique for removing harmful knowledge from AI models. However, recent work has shown that most current unlearning methods are not robust…
“Diversification internationally," Canadian Prime Minister Mark Carney remarks, “is not just economic prudence — it is the material foundation for honest foreign policy.” Carney’s address to…