In video-on-demand services, each video title is deployed as a bitrate ladder—a set of pre-encoded representations with increasing bitrate and quality. This paper introduces NILO, a Nested and Iterative Ladder Optimization method for designing bitrate ladders in video streaming services. NILO balances the tradeoffs between user Quality of Experience (QoE) and Content Delivery Network (CDN) efficiency, while meeting the operational needs of large-scale production systems. Our contributions include a multi-objective optimization framework that captures QoE and CDN efficiency during ladder construction, and a novel method that uniquely integrates standard optimization components to address this complex problem. We evaluate NILO at a large video streamer using trace-driven simulations and an A/B test in production with over one million users. Our results show that NILO achieves significant efficiency gains while maintaining QoE comparable to highly tuned production ladders. Specifically, NILO reduces storage by approximately 20% and streaming rate by about 2%, with options for greater efficiency gains at the cost of modest QoE degradation.

Drug-induced toxicity is one of the leading reasons new drugs fail clinical trials. Machine learning models that predict drug toxicity from molecular structure could help researchers prioritize less toxic drug candidates. However, current toxicity datasets are typically small and limited to a single organ system (e.g., cardio, renal, or liver). Creating these datasets often involved time-intensive expert curation by parsing drug labelling documents that can exceed 100 pages per drug. Here, we introduce UniTox, a unified dataset of 2,418 FDA-approved drugs with drug-induced toxicity summaries and ratings created by using GPT-4o to process FDA drug labels. UniTox spans eight types of toxicity: cardiotoxicity, liver toxicity, renal toxicity, pulmonary toxicity, hematological toxicity, dermatological toxicity, ototoxicity, and infertility. This is, to the best of our knowledge, the largest such systematic human in vivo database by number of drugs and toxicities, and the first covering nearly all non-combination FDA-approved medications for several of these toxicities. We recruited clinicians to validate a random sample of our GPT-4o annotated toxicities, and UniTox's toxicity ratings concord with clinician labelers 85-96\% of the time. Finally, we benchmark several machine learning models trained on UniTox to demonstrate the utility of this dataset for building molecular toxicity prediction models.

MOTIVATION: The emergence of large chemical repositories and combinatorial chemical spaces, coupled with high-throughput docking and generative AI, have greatly expanded the chemical diversity of small molecules for drug discovery. Selecting compounds for experimental validation requires filtering these molecules based on favourable druglike properties, such as Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET). RESULTS: We developed ADMET-AI, a machine learning platform that provides fast and accurate ADMET predictions both as a website and as a Python package. ADMET-AI has the highest average rank on the TDC ADMET Leaderboard, and it is currently the fastest web-based ADMET predictor, with a 45% reduction in time compared to the next fastest public ADMET web server. ADMET-AI can also be run locally with predictions for one million molecules taking just 3.1 h. AVAILABILITY AND IMPLEMENTATION: The ADMET-AI platform is freely available both as a web server at admet.ai.greenstonebio.com and as an open-source Python package for local batch prediction at github.com/swansonk14/admet_ai (also archived on Zenodo at doi.org/10.5281/zenodo.10372930). All data and models are archived on Zenodo at doi.org/10.5281/zenodo.10372418.

In HTTP Adaptive Streaming, video content is conventionally encoded by adapting its spatial resolution and quantization level to best match the prevailing network state and display characteristics. It is well known that the traditional solution, of using a fixed bitrate ladder, does not result in the highest quality of experience for the user. Hence, in this paper, we introduce a content-driven approach for estimating the bitrate ladder, based on spatio-temporal features extracted from the uncompressed content. The method implements a content-driven interpolation. It uses the extracted features to train a machine learning model to infer the curvature points of the Rate-VMAF curves in order to guide a set of initial encodings. We employ the VMAF quality metric as a means of perceptually conditioning the estimation. When compared to the generation of a reference ladder using exhaustive encoding, 76.63% the estimated ladder's Rate-VMAF points are identical to those of the reference ladder. The proposed method benefits from a significant (77.4%) reduction in the number of encodes required with only a small (1.04%) average Bj⊘ntegaard Delta Rate increase.

Selecting input features of top relevance has become a popular method for building selfexplaining models.In this work, we extend this selective rationalization approach to text matching, where the goal is to jointly select and align text pieces, such as tokens or sentences, as a justification for the downstream prediction.Our approach employs optimal transport (OT) to find a minimal cost alignment between the inputs.However, directly applying OT often produces dense and therefore uninterpretable alignments.To overcome this limitation, we introduce novel constrained variants of the OT problem that result in highly sparse alignments with controllable sparsity.Our model is end-to-end differentiable using the Sinkhorn algorithm for OT and can be trained without any alignment annotations.We evaluate our model on the Stack-Exchange, MultiNews, e-SNLI, and MultiRC datasets.Our model achieves very sparse rationale selections with high fidelity while preserving prediction accuracy compared to strong attention baseline models.† * Denotes equal contribution.† Our code is publicly available at https://github. com/asappresearch/rationale-alignment.Can I find duplicate songs with different names?I have so many duplicate songs but they have different names.Is there an application I can use to find and delete the duplicates?How to find (and delete) duplicate files?I have a largish music collection and there are some duplicates in there.Is there any way to find duplicate files.At a minimum by doing a hash and seeing if two files have the same hash.… I'm happy using the command line if that is the easiest way.

Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient training data. In this paper, we propose a surprisingly effective self-training approach for iteratively creating additional molecular targets. We first pre-train the generative model together with a simple property predictor. The property predictor is then used as a likelihood model for filtering candidate structures from the generative model. Additional targets are iteratively produced and used in the course of stochastic EM iterations to maximize the log-likelihood that the candidate structures are accepted. A simple rejection (re-weighting) sampler suffices to draw posterior samples since the generative model is already reasonable after pre-training. We demonstrate significant gains over strong baselines for both unconditional and conditional molecular design. In particular, our approach outperforms the previous state-of-the-art in conditional molecular design by over 10% in absolute gain. Finally, we show that our approach is useful in other domains as well, such as program synthesis.