Different finetune strategy: In Figure 1, we visualize the mIoU curve of different fine-tuning strategies. It can be seen that both layer-based and convolution-based fine-tuning methods bring over-fitting problems. This result shows that traditional fine-tuning methods are not suitable for few-shot segmentation tasks. Directly fine-tuning theparameters ofbackbone infew-shot learning affects the robustness ofFSS models. Therefore, we propose anovelfine-tuning strategy,namely SVF.

Behavior is shaped by various factors operating across different timescales.

Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance compared to dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive.

We study the computational complexity of explaining preference data through Boolean attribute models (BAMs), motivated by extensive research involving attribute models and their promise in understanding preference structure and enabling more efficient decision-making processes. In a BAM, each alternative has a subset of Boolean attributes, each voter cares about a subset of attributes, and voters prefer alternatives with more of their desired attributes. In the BAM problem, we are given a preference profile and a number k, and want to know whether there is a Boolean k-attribute model explaining the profile. We establish a complexity dichotomy for the number of attributes k: BAM is linear-time solvable for $k \le 2$ but NP-complete for $k \ge 3$. The problem remains hard even when preference orders have length two. On the positive side, BAM becomes fixed-parameter tractable when parameterized by the number of alternatives m. For the special case of two voters, we provide a linear-time algorithm. We also analyze variants where partial information is given: When voter preferences over attributes are known (BAM WITH CARES) or when alternative attributes are specified (BAM WITH HAS), we show that for most parameters BAM WITH CARES is more difficult whereas BAM WITH HAS is more tractable except for being NP-hard even for one voter.

The Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance over dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive.

Effective PE is vital, particularly for enabling LMs trained on shorter contexts to generalize to significantly longer sequences during inference--a desirable capability known as context length extrapolation. Several PE methods have been proposed to facilitate context length extrapolation, including Sinusoidal embeddings (V aswani, 2017), RoPE (Su et al., 2024), ALiBi (Press et al., 2022), and even the omission Bayesian attention mechanism, hereby called BAM. 2.1 B This dependency is trivially modeled by a scalar Z when the scoring function is additive, as detailed below. If the scoring function of the attention mechanism is additive, i.e., of the form With Theorem 1, we can frame positional encoding as priors to BAM. Lemma 2. ALiBi is a special case of BAM prior where the token position distribution comprises Lemma 3. ALiBi becomes local attention as the relative length |j i| increases. See Appendix B.1, B.2, and B.3. 2.3 A PE We call this new PE method GGD-BAM.

We thank all reviewers for their valuable feedback. Below please find our response to each individual review. Significance of improvements: For VQA, with provided error bars, the improvements are statistically significant. We will add them into the paper in revision. Also in BAM, the attention weights are data dependent local variables.

Deep learning in medical imaging faces obstacles: limited data diversity, ethical issues, high acquisition costs, and the need for precise annotations. Bleeding detection and localization during surgery is especially challenging due to the scarcity of high-quality datasets that reflect real surgical scenarios. We propose orGAN, a GAN-based system for generating high-fidelity, annotated surgical images of bleeding. By leveraging small "mimicking organ" datasets, synthetic models that replicate tissue properties and bleeding, our approach reduces ethical concerns and data-collection costs. orGAN builds on StyleGAN with Relational Positional Learning to simulate bleeding events realistically and mark bleeding coordinates. A LaMa-based inpainting module then restores clean, pre-bleed visuals, enabling precise pixel-level annotations. In evaluations, a balanced dataset of orGAN and mimicking-organ images achieved 90% detection accuracy in surgical settings and up to 99% frame-level accuracy. While our development data lack diverse organ morphologies and contain intraoperative artifacts, orGAN markedly advances ethical, efficient, and cost-effective creation of realistic annotated bleeding datasets, supporting broader integration of AI in surgical practice.