Knowledge catalogue
arXiv:2609.40148v1 Announce Type: new Abstract: Power-law learning curves are often treated as fixed properties of a model and its data, although learning-rate and batch-size schedules can change the
arXiv:2609.34212v1 Announce Type: new Abstract: Mixture-of-Depths (MoD) enables conditional computation across Transformer depth by routing only a subset of tokens through selected layers, but its ori
arXiv:2604.22753v1 Announce Type: new Abstract: Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, asse
arXiv:2610.13630v1 Announce Type: new Abstract: Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the d
arXiv:2608.28404v1 Announce Type: new Abstract: Video generation for autonomous driving cannot follow the web-scale route: driving data is expensive to collect, bound by privacy requirements, and cann
arXiv:2608.17209v1 Announce Type: cross Abstract: End-to-end vision-language-action (VLA) and world-action models offer an elegant route to general-purpose robotics, but their reliability is bounded b
arXiv:2607.03787v1 Announce Type: new Abstract: Accurately modeling biomolecular interactions is a central bottleneck in biology and therapeutic discovery. Here, we introduce Open Drug Discovery Engin
arXiv:2606.29858v1 Announce Type: new Abstract: Language model loss follows remarkably regular scaling laws over model and data size, yet it remains unclear why the aggregate loss should exhibit a pow
arXiv:2606.24253v1 Announce Type: new Abstract: Modern VLMs and VLA systems commonly adopt off-the-shelf ViTs such as SigLIP2 as visual encoders, but diverse downstream requirements in latency, tempor
arXiv:2511.04567v2 Announce Type: replace-cross Abstract: Constructing reduced models for turbulent transport is essential for accelerating profile predictions and enabling many-query tasks such as pa
arXiv:2606.00815v1 Announce Type: new Abstract: Electroencephalography (EEG) supports a variety of brain-computer interface (BCI) tasks ranging from brain-state monitoring to human-LLM interactions. E
arXiv:2605.29223v1 Announce Type: new Abstract: The parameter counts of the most widely used large language models (LLMs) are often withheld by their developers, leaving model size -- a primary refere
arXiv:2605.29387v1 Announce Type: cross Abstract: The scaling exponent alpha in neural scaling laws L(N) propto N^{-alpha} is commonly treated as a fixed constant set by architecture and data. We pres
arXiv:2605.22162v1 Announce Type: cross Abstract: Stellar spectra encode key information on the physical properties and chemical compositions of stars. Accurate stellar parameter determination is esse
arXiv:2605.13433v1 Announce Type: cross Abstract: Generative recommendation (GR) has emerged as a promising paradigm that replaces fragmented, scenario-specific architectures with unified Transformer-
arXiv:2605.09189v1 Announce Type: new Abstract: The scaling laws guiding modern model training were calibrated for a single regime: data-rich, single-epoch pretraining. The dominant such scaling law f
arXiv:2605.09887v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) operationalise the linear representation hypothesis: they reconstruct model activations as sparse linear combinations of in
arXiv:2605.08541v1 Announce Type: new Abstract: Neural scaling laws approximate a language model's loss as a power-law function of parameter count N and token count D. Following Chinchilla-style compu
arXiv:2605.06859v1 Announce Type: cross Abstract: Vision foundation models are increasingly moving beyond 2D to volumetric domains such as 3D medical imaging, where unified pretraining across differen
arXiv:2602.07238v2 Announce Type: replace-cross Abstract: Do leading LLM developers possess a proprietary ``secret sauce'', or is LLM performance driven by scaling up compute? Using training and bench
arXiv:2605.01640v1 Announce Type: cross Abstract: Training compute is increasingly outpacing the availability of high-quality data. This shifts the central challenge from optimal compute allocation to
arXiv:2506.09110v3 Announce Type: replace Abstract: Electroencephalography (EEG) provides real-time insights into brain activity and supports diverse applications in neuroscience. While EEG foundation
arXiv:2604.17581v1 Announce Type: new Abstract: How much data is enough to make a scientific discovery? As biomedical datasets scale to millions of samples and AI models grow in capacity, progress inc
arXiv:2604.09389v1 Announce Type: cross Abstract: Training Transformer language models is expensive, as performance typically improves with increasing dataset size and computational budget. Although s