The quality is adequate; the authors show familiarity with, and build on ideas from, the relevant literature. The experimental setup (image classification and NMT) is also relevant. The work is very clear and well written. The proposed method could provide a significant reduction in training time for practitioners and researchers, but, in my opinion, needs some additional empirical validation. The bounded second moment and variance assumptions, together, are quite strong.

While I feel that the new random baselines significantly strengthen the paper's results on CIFAR-100, random baselines are not provided for CIFAR-10, SVHN, or ImageNet. I've updated my score from a 6 to an 7, based on the random baselines for CIFAR-100 and the authors' promise to clarify their evaluation measure in the final submission. However, Cubuk et al.'s original algorithm is extremely resource-intensive. The main contribution of this paper is an algorithm that can operate on the same search space and come up with data augmentation schemes orders of magnitude more efficiently. The most closely related work I'm aware of is Population Based Augmentation (ICML 2019), which tries to solve the same problem in a different way.

Precise and real-time estimation of the robotic arm's position on the patient's side is essential for the success of remote robotic surgery in Tactile Internet (TI) environments. This paper presents a prediction model based on the Transformer-based Informer framework for accurate and efficient position estimation. Additionally, it combines a Four-State Hidden Markov Model (4-State HMM) to simulate realistic packet loss scenarios. The proposed approach addresses challenges such as network delays, jitter, and packet loss to ensure reliable and precise operation in remote surgical applications. The method integrates the optimization problem into the Informer model by embedding constraints such as energy efficiency, smoothness, and robustness into its training process using a differentiable optimization layer. The Informer framework uses features such as ProbSparse attention, attention distilling, and a generative-style decoder to focus on position-critical features while maintaining a low computational complexity of O(L log L). The method is evaluated using the JIGSAWS dataset, achieving a prediction accuracy of over 90 percent under various network scenarios. A comparison with models such as TCN, RNN, and LSTM demonstrates the Informer framework's superior performance in handling position prediction and meeting real-time requirements, making it suitable for Tactile Internet-enabled robotic surgery.

Yuki Mitsufuji is a Lead Research Scientist at Sony AI. Yuki and his team presented two papers at the recent Conference on Neural Information Processing Systems (NeurIPS 2024). These works tackle different aspects of image generation and are entitled: GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping and PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher . We caught up with Yuki to find out more about this research. The problem we aimed to solve is called single-shot novel view synthesis, which is where you have one image and want to create another image of the same scene from a different camera angle. There has been a lot of work in this space, but a major challenge remains: when an image angle changes substantially, the image quality degrades significantly.

There was a ton of discussion about this paper between reviewers and area chairs, multiple reviewers improved their view of the paper based on the author response, and I read through the paper in detail myself. I was still conflicted after reading it, but I am leaning towards recommending acceptance. However, I *implore* the authors to carefully consider the issues brought up by R2 and R3 as well as the issues that I bring up below. I believe that every single one of the issues brought up can be fixed, and will be extremely-disappointed if these issues are not addressed in the final version (it would make me regret recommending acceptance, and probably be more-harsh on empirical papers in the future, especially by the same authors). Some specific comments from my read-through of the paper: - I agree with the authors that optimization is a mix of theory and empirical work, and it is completely ok for works to be purely empirical if the experiments are done well.

Originality: Although VAEs using a stick-breaking construction with Kumaraswamy distributions has been considered before (Nalisnick, Smyth, STICK-BREAKING VARIATIONAL AUTOENCODERS, 2017), the idea to use such a construction and extend it by mixing over the orderings to obtain a density more similar to a Dirichlet is new and interesting. Related work is adequately cited. Quality: The paper seems technically sound and claims are largely supported. Although Theorem 1 is a standard result, reiterating it is likely useful for the subsequent exposition. Experimental results show that the method outperforms some baselines, however, I feel that some additional experiments would be useful (see details below in Section 5. Improvements).

This study uses the Palestinian Oral History Archive (POHA) to investigate how Palestinian refugee groups in Lebanon sustain a cohesive collective memory of the Nakba through shared narratives. Grounded in Halbwachs' theory of group memory, we employ statistical analysis of pairwise similarity of narratives, focusing on the influence of shared gender and location. We use textual representation and semantic embeddings of narratives to represent the interviews themselves. Our analysis demonstrates that shared origin is a powerful determinant of narrative similarity across thematic keywords, landmarks, and significant figures, as well as in semantic embeddings of the narratives. Meanwhile, shared residence fosters cohesion, with its impact significantly amplified when paired with shared origin. Additionally, women's narratives exhibit heightened thematic cohesion, particularly in recounting experiences of the British occupation, underscoring the gendered dimensions of memory formation. This research deepens the understanding of collective memory in diasporic settings, emphasizing the critical role of oral histories in safeguarding Palestinian identity and resisting erasure.

Ten video games have received nominations for the 36th Annual GLAAD Media Awards. This program celebrates media works that feature "fair, accurate and inclusive representations of the lesbian, gay, bisexual, transgender and queer (LGBTQ) community and the issues that affect their lives." There are nominees for television, film, music, theater, journalism and comics as well as video games. One of the 2024 nominees for outstanding video game is the re-release of Paper Mario: The Thousand Year Door for the Nintendo Switch. The original Japanese version of the GameCube title included a minor character named Vivian who was transgender. The game contained dialogue about her challenges being misgendered and her journey to understanding her own identity.

EDIT: After reading the author's rebuttal, I changed my assessment of the paper to an accept. The paper is well written and it does a good job at explaining the intuition behind the proposed algorithm. I appreciated the inclusion of the small dimensional toy example as it illustrates in a simple and clear manner the adaptability property of the algorithm. My main concern with the proposed algorithm is that, in my opinion, it is most suitable for small dimensional problems only. The provided examples further justify my impression given that posterior distribution to sample from is of reduced dimension. Consequently, I'm having a hard time justifying the interest of the ML community with respect to the proposed sampling algorithm considering its perceived limited scope.

However, even after reading the rebuttal, I feel that it is a bit premature to publish the research at this point in time. In the rebuttal, the authors acknowledge that their method is not the first universal monotonic approximator and clarify that their language regarding the "cap on expressiveness" of alternative monotonic approximators refers to the non-asymptotic case, i.e., a finite number of neurons/hidden units. They write "we believe that the constraints on the positiveness of the weights and on the class of possible activation functions are unnecessarily restraining the hypothesis space in the non-asymptotic case". However, this is an assertion for which they have not supplied any kind of proof, and I find it highly debatable. Any method, whether it is their UMNN or the Huang approach or lattices or max/min networks, has some cap on expressiveness in the non-asymptotic case.