arXiv:2509.07295v4 Announce Type: replace-cross
Abstract: Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training…
arXiv:2606.07552v2 Announce Type: replace-cross
Abstract: Large language models exhibit a risk-averse “turtle” bias as strategic agents. We show that injecting a symbolic reasoning framework as a…
arXiv:2602.18131v2 Announce Type: replace
Abstract: Temporal Predictive Coding provides a layer-local, parallelisable mechanism for learning in recurrent systems, making it an attractive candidate…
arXiv:2601.23147v2 Announce Type: replace-cross
Abstract: The integrity of time in distributed Internet of Things (IoT) devices is crucial for reliable operation in energy cyber-physical systems,…
arXiv:2606.22902v2 Announce Type: replace
Abstract: Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct…
arXiv:2510.01299v3 Announce Type: replace-cross
Abstract: We present domain-adapted large language model agents designed to support Cherenkov Telescope Array operation and data analysis. The agents…
arXiv:2604.21991v2 Announce Type: replace
Abstract: Multi-task optimization is a powerful approach for solving a large number of tasks in parallel. However, existing algorithms face distinct…
arXiv:2510.00866v4 Announce Type: replace
Abstract: Large-scale models are pretrained on massive web-crawled datasets containing documents of mixed quality, making data filtering essential. A…
arXiv:2602.06020v3 Announce Type: replace
Abstract: How do protein structure prediction models fold proteins? We investigate this question through causal interventions on the folding trunks of…
arXiv:2412.08147v2 Announce Type: replace-cross
Abstract: Pareto fronts are useful to find good task-mixing strategies for multitask finetuning, but they are also costly to compute. To reduce costs,…