Model Detail
Lance
▲ 31.3%Lance is a multimodal model with 3B parameters released by bytedance-research. The model is registered under the any-to-any pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
Lance ships with 3B parameters. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Downloads of Lance have moved +31.3% over the past 24 hours. That is a slight downtrend, consistent with normal cooling as newer models compete for the same workloads. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
Lance is best fit for mixed text-and-image reasoning tasks such as document understanding. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Addressing Imbalance in Multi-Label Data via Label-Specific Distance-based Oversampling
arXiv:2606.05927v1 Announce Type: new Abstract: The complex imbalanced label distribution poses a crucial challenge to multi-label classification, as most classifiers are biased towards the majority class and high-frequent labels. Oversampling is an efficient and flexible solution that augments inst
Next-Generation Parallel Decoder for LPDR: Architectural Optimization and Class-Balanced GAN-Augmentation
arXiv:2606.05785v1 Announce Type: cross Abstract: Real-Time License Plate Detection and Recognition (LPDR) forms the backbone of modern smart cities. Although the YOLOV5-PDLPR model substantially improved system efficiency through a parallel decoder approach, its performance is still affected by spa
Revisiting Prototype Rehearsal for Exemplar-Free Continual Learning: Manifold-Aware Boundary Sampling with Adaptive Class-Balanced Loss
arXiv:2606.05695v1 Announce Type: new Abstract: Exemplar-free class-incremental learning (EFCIL) aims to acquire new classes over time without storing raw data. Historically, prototype rehearsal, which samples around stored class prototypes and mixes them with current-task data, has been a popular s
Uncovering Extreme Event Mechanisms for Prediction and Control with Sensitivity-Balanced Projections
arXiv:2606.05618v1 Announce Type: cross Abstract: Extreme events -- such as earthquakes and coronal mass ejections -- are common in many chaotic dynamical systems, yet are difficult to characterize and predict due to the subtle instability mechanisms that drive them. In this work, we develop an inte
Class-Dependent Hybrid Data Augmentation for Multiclass Migraine Classification under Severe Class Imbalance
arXiv:2605.23453v2 Announce Type: replace Abstract: We conducted a reproducibility-oriented re-evaluation of prior migraine classification studies, correcting for data leakage and metric bias. We then introduced (i) a clinically motivated aggregation of two hemiplegic subtypes following ICHD-3 {\S}1
Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game
arXiv:2606.04978v1 Announce Type: new Abstract: LLMs can appear cautious in risk decision-making tasks, yet cautious-looking outputs do not necessarily indicate alignment with human decision-making mechanisms. We investigate this distinction using the St. Petersburg game as a controlled testbed, a c
