Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2608. 02391v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive.
arXiv:2608. 02487v1 Announce Type: cross Abstract: Recently, rectified flow has emerged as a fundamental framework for large-scale image generation, powering state-of-the-art systems such as FLUX.
arXiv:2505. 20894v2 Announce Type: replace Abstract: Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to segment labeled datasets.
arXiv:2509. 09195v2 Announce Type: replace Abstract: Current evaluation metrics for deep learning weather models create a "Statistical Similarity Trap", rewarding blurry predictions while missing rare, high-impact events.
arXiv:2509. 26405v2 Announce Type: replace Abstract: We introduce InVirtuoGen, a discrete flow generative model for fragmented SMILES for de novo and fragment-constrained generation, and target-property/lead optimization of small molecules.
arXiv:2602. 02288v3 Announce Type: replace Abstract: Current time-series forecasting models are primarily based on transformer-style neural networks.
arXiv:2604. 09922v2 Announce Type: replace Abstract: Subsurface stratigraphy contains important spatio-temporal information about accumulation, deformation, and layer formation in polar ice sheets.
arXiv:2605. 02942v2 Announce Type: replace Abstract: Fairness studies of medical imaging AI often explain subgroup performance gaps through under-representation in the training data.
arXiv:2606. 21994v2 Announce Type: replace Abstract: On-policy distillation (OPD) improves reasoning models by applying dense teacher supervision on student-sampled trajectories.
arXiv:2507. 21449v2 Announce Type: replace-cross Abstract: Degeneracy is an inherent feature of the loss landscape of neural networks, but it is not well understood how stochastic gradient MCMC (SGMCMC) algorithms interact with this degeneracy.
arXiv:2509. 13374v2 Announce Type: replace-cross Abstract: We develop and audit a history-aware financial path generator based on Denoising Levy Probabilistic Models (DLPMs) for conditional equity-index path generation.
arXiv:2602. 13847v5 Announce Type: replace-cross Abstract: A central challenge across science and engineering is to build data-driven reduced-order models of turbulent dynamical systems that reproduce stationary statistics, predict responses to external perturbations, and remain practical for real-world applications.
arXiv:2603. 11804v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce.
arXiv:2605. 14883v2 Announce Type: replace-cross Abstract: Mild traumatic brain injury (mTBI) is a prevalent condition that remains difficult to diagnose in its early stages.
arXiv:2605. 15720v2 Announce Type: replace-cross Abstract: Medical referring image segmentation (MRIS) predicts lesion masks from medical images and natural-language referring expressions, but acquiring paired pixel-level annotations and referring texts is costly.
arXiv:2607. 17082v2 Announce Type: replace-cross Abstract: Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results.
arXiv:2608. 00152v1 Announce Type: new Abstract: Predicting the magnitude of a CRISPRi perturbation's transcriptomic effect on held-out target genes is an important open problem in single-cell biology.
arXiv:2608. 00316v1 Announce Type: new Abstract: Bayesian optimization (BO) has become the standard tool for sample-efficient optimization and owes its efficiency to uncertainty-aware search driven by generic statistical priors.
arXiv:2608. 00106v1 Announce Type: new Abstract: Agentic systems must decide not only what answer to produce, but which reasoning and execution operations should precede it.
arXiv:2608. 00220v1 Announce Type: new Abstract: We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sample and reinforce.