arXiv:2607.00877v1 Announce Type: new Abstract: Traditional variational Kalman filtering with unknown noise statistics suffers from inconsistent process covariance estimation and slow convergence speed, limiting its practical…
arXiv:2607.01002v1 Announce Type: cross Abstract: In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting…
arXiv:2607.00334v1 Announce Type: new Abstract: Autonomous agents, whether LLM-driven software agents or robotic physical agents, face a common class of failure modes when operating without continuous…
arXiv:2607.00143v1 Announce Type: new Abstract: Online hate speech has been linked to a global rise in violence against minorities, including incidents such as mass shootings, lynchings,…
arXiv:2601.11641v3 Announce Type: replace Abstract: While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity…
arXiv:2607.00157v1 Announce Type: new Abstract: Reconstructing 4D animals from monocular videos is challenging due to large inter-species variation, complex articulations, and the lack of reliable templates.…
arXiv:2607.00162v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) reparameterizes weight updates in a fixed basis: low-rank adapters operate in the spatial domain, while a recent line…
arXiv:2607.00846v1 Announce Type: new Abstract: This paper studies whether the Metabolic Multi-Agent Optimizer (MMAO) can be credibly derived into a dynamic-optimization method without replacing its core…
arXiv:2607.00470v1 Announce Type: new Abstract: We investigate a forecasting framework based on a simple discrete-time dynamic model with coefficients varying in time. The parameters of the…
arXiv:2607.01153v1 Announce Type: cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an instruction, refused…
arXiv:2607.01218v1 Announce Type: cross Abstract: Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions.…
arXiv:2607.00139v1 Announce Type: new Abstract: The cost of human expert evaluation is a principal bottleneck to deploying language models in specialized, high-stakes domains. This is particularly…
arXiv:2603.15269v3 Announce Type: replace Abstract: The tortuosity of corneal nerve fibers are used as indication for different diseases. Current state-of-the-art methods for grading the tortuosity heavily…
arXiv:2505.03303v4 Announce Type: replace Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints. Such differences…
arXiv:2607.00152v1 Announce Type: new Abstract: Three of the most popular methods for training language models to reason look like three different tricks. They are not. All…
arXiv:2607.00761v1 Announce Type: new Abstract: Evolutionary multitasking (EMT) has shown strong capability in solving multiple optimization problems simultaneously by exploiting latent inter-task consistency, such as similarities…
arXiv:2607.00207v1 Announce Type: cross Abstract: We develop a framework for analyzing the learning dynamics of $ell_2$-adversarial training of single-index models on Gaussian mixtures in the high-dimensional…
Training language models (LMs) remains a highly human-intensive process, even as frontier language model agents become increasingly capable at software engineering and other long-horizon tasks. A…
In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they…
Vision-Language-Action (VLA) models often fail to perform the same learned tasks under environmental shifts, such as changes in camera pose and shifts to a different but…
Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typically reactive and lack explicit world…
World models can enable Model Predictive Control (MPC), but this requires dynamics prediction that is both fast enough for online use and expressive enough to represent…
Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation. However, current systems operate within constrained search…
Biomedical researchers increasingly use AI-generated analyses and reports to interpret protein-level signals, but static outputs are often insufficient for research decision-making, where users need to inspect…