SUPER INTELLIGENCE BREAK
A focused stream of intelligence from the sources you trust.
arXiv:2610.22448v1 Announce Type: new Abstract: Enhancing the agentic capabilities of Large Language Models (LLMs) to tackle complex software engineering (SWE) and general terminal-usage problems is a pressing challenge. Current state-of-the-art LLMs often go through…
arXiv:2610.22439v1 Announce Type: new Abstract: Catastrophic forgetting remains a challenge in supervised continual learning, as adapting to new tasks causes representation drift and loss of previously learned information. This raises the question of which…
arXiv:2608.30976v2 Announce Type: replace Abstract: Practical time-series forecasting requires domain knowledge, constraints, plausibility checks, and human intervention. We present CastClaw, an interactive forecasting system centered on an autonomous forecasting loop and supported by a…
arXiv:2610.22438v1 Announce Type: new Abstract: Studies of what fine-tuning does to a language model often summarise the weight update $Delta W$ by its rank. We compare the rank measures used for this against the…
arXiv:2605.07772v2 Announce Type: replace Abstract: Transformers perform inference by iteratively transforming token representations across layers. This layerwise computation has been studied empirically, and recent mean-field theories of Transformer dynamics explain how attention can drive…
arXiv:2610.22381v1 Announce Type: new Abstract: When a fact becomes harder to elicit from a language model, has the model lost it, or has it merely become less accessible? Parameter-updating test-time continual learning agents are…
arXiv:2610.22430v1 Announce Type: new Abstract: Accurate prediction of multivariate time series requires models that simultaneously capture variable-specific dynamics and cross-variable interactions. In this work, a Correlation-Guided and Dynamics-Trained Clustered Echo State Network (CGDT-CESN) is…
arXiv:2610.22433v1 Announce Type: new Abstract: Flexible job-shop scheduling becomes resource-coupled when a scarce vehicle fleet moves jobs between stations, because the schedule sets the transport waits. BOLT (bound-oriented learning for transport-coupled scheduling) builds a…
arXiv:2610.22436v1 Announce Type: new Abstract: The signal generation capabilities of a novel data augmentation framework are examined in aerospace structures. First, the framework learns class-conditional temporal and spectral characteristics of the measured structural responses.…
arXiv:2610.22435v1 Announce Type: new Abstract: Distributed Transformer inference across co-located edge devices is fundamentally communication-bound, as exchanging activations between sequence-parallel partitions dominates inference latency under commodity edge bandwidths. Existing compression schemes reduce this cost…
arXiv:2610.11362v2 Announce Type: replace Abstract: Binary diffusion models typically require many function evaluations (NFEs) to generate high-quality samples, making inference costly. Reducing NFEs without sacrificing sample quality or relying on distillation or additional training…
arXiv:2610.22437v1 Announce Type: new Abstract: Automated fundus-based diabetic retinopathy (DR) grading can substantially expand screening capacity, but source-trained models degrade sharply across different cameras, clinics, and patient populations. Existing test-time adaptation methods depend on…