In this work, we conduct an extensive empirical study of several deep reinforcement learning algorithms on two challenging combinatorial optimization problems: the job-shop and flexible job-shop scheduling problems, both fundamental challenges with multiple industrial applications. Broadly, deep reinforcement learning algorithms fall into two categories: policy-gradient and value-based. While value-based algorithms have achieved notable success in domains such as the Arcade Learning Environment, the combinatorial optimization community has predominantly favored policy-gradient algorithms, often overlooking the potential of value-based alternatives. From our results, value-based algorithms demonstrated a lower variance and a more stable convergence profile compared to policy-gradient ones. Moreover, they achieved superior cross-size and cross-distribution generalization, that is, effectively solving instances that are substantially larger or structurally distinct from those seen during training. Finally, our analysis also suggests that the relative performance of each category of algorithms may be dependent on structural properties of the problem, such as problem flexibility and instance size. Overall, our findings challenge the prevailing assumption that policy-gradient algorithms are inherently superior for combinatorial optimization. We show instead that value-based algorithms can match or even surpass the performance of policy-gradient algorithms, suggesting that they deserve greater attention from the combinatorial optimization community. Our code is openly available at: https://github.com/AJ-Correa/Unraveling-the-Rainbow

This paper explores the design of a propaganda detection tool using Large Language Models (LLMs). Acknowledging the inherent biases in AI models, especially in political contexts, we investigate how these biases might be leveraged to enhance critical think ing in news consumption. Countering the typical view of AI biases as detrimental, our research proposes strategies of user choice and personalization in response to a user's political stance, applying psychological concepts of confirmation bias and cogniti ve dissonance.

Long-context video understanding in multimodal large language models (MLLMs) faces a critical challenge: balancing computational efficiency with the retention of fine-grained spatio-temporal patterns. Existing approaches (e.g., sparse sampling, dense sampling with low resolution, and token compression) suffer from significant information loss in temporal dynamics, spatial details, or subtle interactions, particularly in videos with complex motion or varying resolutions. To address this, we propose $\mathbf{Mavors}$, a novel framework that introduces $\mathbf{M}$ulti-gr$\mathbf{a}$nularity $\mathbf{v}$ide$\mathbf{o}$ $\mathbf{r}$epre$\mathbf{s}$entation for holistic long-video modeling. Specifically, Mavors directly encodes raw video content into latent representations through two core components: 1) an Intra-chunk Vision Encoder (IVE) that preserves high-resolution spatial features via 3D convolutions and Vision Transformers, and 2) an Inter-chunk Feature Aggregator (IFA) that establishes temporal coherence across chunks using transformer-based dependency modeling with chunk-level rotary position encodings. Moreover, the framework unifies image and video understanding by treating images as single-frame videos via sub-image decomposition. Experiments across diverse benchmarks demonstrate Mavors' superiority in maintaining both spatial fidelity and temporal continuity, significantly outperforming existing methods in tasks requiring fine-grained spatio-temporal reasoning.

From protein supplements and electrolytes to greens powders and energy drinks, these are the discounted picks worth snagging. The wellness industry is a wild marketplace. You can't trust the marketing alone, and FDA regulation on protein powder deals is quite limited. It pays to be cautious. So for this year's Black Friday, we sifted through the markdowns, cross-checked claims, verified third-party tests, and sampled the supplements so you don't have to.

From protein supplements and electrolytes to greens powders and energy drinks, these are the discounted picks worth snagging. The wellness industry is a wild marketplace. You can't trust the marketing alone, and FDA regulation is quite limited. It pays to be cautious. So for this year's Black Friday, we sifted through the markdowns, cross-checked claims, verified third-party tests, and sampled the supplements so you don't have to.

We recruited participants through two online platforms, CloudResearch and Bovitz, targeting US residents over 18 years old who self-identified as either Republican or Democrat and were active users of X (SM section S1.1). Qualified individuals were invited to complete a screening task, which included installing a browser extension that analyzed their X feed. To ensure the interventions could have a meaningful impact on participants' feeds, only those with at least 5% of posts related to politics or social issues were invited to participate. Figure S1 summarizes the recruitment funnel, including the number of individuals at each stage of the process. Participants were not instructed to use X in any particular way, but they received daily reminders if they had not used the platform that day.

At a recent conference on mathematics in the age of automated proofs, mathematician and Fields Medalist Akshay Venkatesh presented “How do we talk to our students about AI?'' He quoted an email he'd received from a young student who asked, “Do you believe that mathematics is worth being studied in a world in which a machine can answer everything for you? What do you believe would be the 'job’ of a mathematician in this world?” Venkatesh framed AI as an opportunity to correct what he called an “essential gap that has opened between the practice of mathematics and our values.” Mathematician William Thurston has explained these values by writing, “mathematics is not about numbers, equations, computations, or algorithms: it is about understanding.” But Venkatesh argued that the record on this is terrible, lamenting that “for a typical paper or talk, very few of us understand it.” He is not alone in thinking that something is wrong with the current state of mathematics research.

Post-Double-Lasso is becoming the most popular method for estimating linear regression models with many covariates when the purpose is to obtain an accurate estimate of a parameter of interest, such as an average treatment effect. However, this method can suffer from substantial omitted variable bias in finite sample. We propose a new method called Post-Double-Autometrics, which is based on Autometrics, and show that this method outperforms Post-Double-Lasso.

We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whether training on easier or harder data leads to better results, and whether those gains come on easier or harder test data. We address this question by conducting a systematic evaluation of LLMs' generalization across models, datasets, and fine-grained groups of example difficulty. We rank examples in six datasets using the outputs of thousands of different LLMs and Item Response Theory (IRT), a well-established difficulty metric in educational testing. Unlike prior work, our difficulty ratings are therefore determined solely by the abilities of many different LLMs, excluding human opinions of difficulty. With a more objective, larger-scale, and finer-grained analysis, we show that cross-difficulty generalization is often limited; training on either easy or hard data cannot achieve consistent improvements across the full range of difficulties. These results show the importance of having a range of difficulties in both training and evaluation data for LLMs, and that taking shortcuts with respect to difficulty is risky.

Large Language Models (LLMs) often exhibit inconsistent behavior when answering paraphrased questions, suggesting a reliance on surface-level patterns rather than true semantic understanding. To address this limitation, we introduce RoParQ, a benchmark specifically constructed to evaluate cross-paraphrase consistency in closed-book multiple-choice QA. This benchmark is derived from standard datasets by generating paraphrases via proprietary models and selectively retaining examples that elicit inconsistent confidence from a judge model. We further propose XParaCon, a novel evaluation metric that quantifies a model's robustness by measuring the standard deviation of accuracies across question variants. Additionally, we implement a reasoning-based, paraphrase-aware Supervised Fine-Tuning (SFT) strategy designed to align models toward semantic invariance. Our experiments demonstrate that this targeted alignment significantly enhances robustness. Notably, fine-tuned lightweight models achieved consistency levels comparable to much larger pre-trained models. These results highlight the efficacy of our approach in mitigating superficial memorization and fostering more robust, reliable LLMs.