Oldest and Lowest Rated Papers
Black Skin, The Queen's Masques: Africanist Ambivalence and Feminine Author(ity) in the Masques of
BERNADETTE ANDREA
English Literary Renaissance·1999
No abstract available
No ratings yet
View paper →BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
Fei Sun, Jun Liu, Jian Wu, Changhua Pei, Xiao Lin, Wenwu Ou, Peng Jiang
arXiv·2019
Modeling users' dynamic and evolving preferences from their historical behaviors is challenging and crucial for recommendation systems. Previous methods employ sequential neural networks (e.g., Recurrent Neural Network) to encode users' historical interactions from left to right into hidden representations for making recommendations. Although these methods achieve satisfactory results, they often assume a rigidly ordered sequence which is not always practical. We argue that such left-to-right unidirectional architectures restrict the power of the historical sequence representations. For this purpose, we introduce a Bidirectional Encoder Representations from Transformers for sequential Recommendation (BERT4Rec). However, jointly conditioning on both left and right context in deep bidirectional model would make the training become trivial since each item can indirectly "see the target item". To address this problem, we train the bidirectional model using the Cloze task, predicting the masked items in the sequence by jointly conditioning on their left and right context. Comparing with predicting the next item at each position in a sequence, the Cloze task can produce more samples to train a more powerful bidirectional model. Extensive experiments on four benchmark datasets show that our model outperforms various state-of-the-art sequential models consistently.
No ratings yet
View paper →From subjects to objects: Knowledge in International Relations theory
Bentley B. Allan
European Journal of International Relations·2017·38 citations
<jats:p> There has been a resurgence of interest in the role of scientific knowledge and expertise in International Relations, but it is not clear what the theoretical value-added of this work is. This article places recent work on scientific knowledge and expertise in a longer-term perspective. The history shows that knowledge has played an important role in International Relations theory since Carr and Morgenthau, but that thinking has been trapped within a simple conceptual framework centered on tracing how knowledge shapes the beliefs and interests of international subjects. This mode of theorizing first entered International Relations via Mannheim and has been further developed by Foucauldian and practice-based approaches since the 1990s. Outlining the history of knowledge from Carr through Haas to the present makes it possible to identify the distinctive contribution of recent work: whereas International Relations has focused on how knowledge shapes subjects such as states and international organizations, recent work by Corry, Sending, and others reorients International Relations to the constitution of governance objects. On the object-centered view, knowledge plays a key role in the construction of the hybrid entities like the economy and the climate that structure the landscape of international politics. </jats:p>
No ratings yet
View paper →IMPASTO: Integrating Model-Based Planning with Learned Dynamics Models for Robotic Oil Painting Reproduction
Unknown Author
impasto-robopainting.github.io
[EDIT] One-sentence summary of your paper.
No ratings yet
View paper →FLARE: Robot Learning with Implicit World Modeling
Ruijie Zheng, Jing Wang, Scott Reed, Johan Bjorck, Yu Fang, Fengyuan Hu, Joel Jang, Kaushil Kundalia, Zongyu Lin, Loic Magne, Avnish Narayan, You Liang Tan, Guanzhi Wang, Qi Wang, Jiannan Xiang, Yinzhen Xu, Seonghyeon Ye, Jan Kautz, Furong Huang, Yuke Zhu, Linxi Fan
arXiv·2025
We introduce $\textbf{F}$uture $\textbf{LA}$tent $\textbf{RE}$presentation Alignment ($\textbf{FLARE}$), a novel framework that integrates predictive latent world modeling into robot policy learning. By aligning features from a diffusion transformer with latent embeddings of future observations, $\textbf{FLARE}$ enables a diffusion transformer policy to anticipate latent representations of future observations, allowing it to reason about long-term consequences while generating actions. Remarkably lightweight, $\textbf{FLARE}$ requires only minimal architectural modifications -- adding a few tokens to standard vision-language-action (VLA) models -- yet delivers substantial performance gains. Across two challenging multitask simulation imitation learning benchmarks spanning single-arm and humanoid tabletop manipulation, $\textbf{FLARE}$ achieves state-of-the-art performance, outperforming prior policy learning baselines by up to 26%. Moreover, $\textbf{FLARE}$ unlocks the ability to co-train with human egocentric video demonstrations without action labels, significantly boosting policy generalization to a novel object with unseen geometry with as few as a single robot demonstration. Our results establish $\textbf{FLARE}$ as a general and scalable approach for combining implicit world modeling with high-frequency robotic control.
No ratings yet
View paper →A Rake’s Progress, by Nick Pinkerton
Unknown Author
Harper's Magazine·2025
Abel Ferrara’s addiction to filmmaking
No ratings yet
View paper →Language Models are Few-Shot Learners
Brown, Tom, Mann, Benjamin, Ryder, Nick, Subbiah, Melanie, Kaplan, Jared D, Dhariwal, Prafulla, Neelakantan, Arvind, Shyam, Pranav, Sastry, Girish, Askell, Amanda, Agarwal, Sandhini, Herbert-Voss, Ariel, Krueger, Gretchen, Henighan, Tom, Child, Rewon, Ramesh, Aditya, Ziegler, Daniel, Wu, Jeffrey, Winter, Clemens, Hesse, Chris, Chen, Mark, Sigler, Eric, Litwin, Mateusz, Gray, Scott, Chess, Benjamin, Clark, Jack, Berner, Christopher, McCandlish, Sam, Radford, Alec, Sutskever, Ilya, Amodei, Dario
papers.nips.cc
No abstract available
No ratings yet
View paper →Partial multivariate transformer as a tool for cryptocurrencies time series prediction
Andrzej Tokajuk, Jarosław A. Chudziak
arXiv·2025
Forecasting cryptocurrency prices is hindered by extreme volatility and a methodological dilemma between information-scarce univariate models and noise-prone full-multivariate models. This paper investigates a partial-multivariate approach to balance this trade-off, hypothesizing that a strategic subset of features offers superior predictive power. We apply the Partial-Multivariate Transformer (PMformer) to forecast daily returns for BTCUSDT and ETHUSDT, benchmarking it against eleven classical and deep learning models. Our empirical results yield two primary contributions. First, we demonstrate that the partial-multivariate strategy achieves significant statistical accuracy, effectively balancing informative signals with noise. Second, we experiment and discuss an observable disconnect between this statistical performance and practical trading utility; lower prediction error did not consistently translate to higher financial returns in simulations. This finding challenges the reliance on traditional error metrics and highlights the need to develop evaluation criteria more aligned with real-world financial objectives.
No ratings yet
View paper →Evolution Strategies at the Hyperscale
Bidipta Sarkar, Mattie Fellows, Juan Agustin Duque, Alistair Letcher, Antonio León Villares, Anya Sims, Dylan Cope, Jarek Liesen, Lukas Seier, Theo Wolf, Uljad Berdica, Alexander David Goldie, Aaron Courville, Karin Sevegnani, Shimon Whiteson, Jakob Nicolaus Foerster
arXiv·2025
We introduce Evolution Guided General Optimization via Low-rank Learning (EGGROLL), an evolution strategies (ES) algorithm designed to scale backprop-free optimization to large population sizes for modern large neural network architectures with billions of parameters. ES is a set of powerful blackbox optimisation methods that can handle non-differentiable or noisy objectives with excellent scaling potential through parallelisation. Na{ï}ve ES becomes prohibitively expensive at scale due to the computational and memory costs associated with generating matrix perturbations $E\in\mathbb{R}^{m\times n}$ and the batched matrix multiplications needed to compute per-member forward passes. EGGROLL overcomes these bottlenecks by generating random matrices $A\in \mathbb{R}^{m\times r},\ B\in \mathbb{R}^{n\times r}$ with $r\ll \min(m,n)$ to form a low-rank matrix perturbation $A B^\top$ that are used in place of the full-rank perturbation $E$. As the overall update is an average across a population of $N$ workers, this still results in a high-rank update but with significant memory and computation savings, reducing the auxiliary storage from $mn$ to $r(m+n)$ per layer and the cost of a forward pass from $\mathcal{O}(mn)$ to $\mathcal{O}(r(m+n))$ when compared to full-rank ES. A theoretical analysis reveals our low-rank update converges to the full-rank update at a fast $\mathcal{O}\left(\frac{1}{r}\right)$ rate. Our experiments show that (1) EGGROLL does not compromise the performance of ES in tabula-rasa RL settings, despite being faster, (2) it is competitive with GRPO as a technique for improving LLM reasoning, and (3) EGGROLL enables stable pre-training of nonlinear recurrent language models that operate purely in integer datatypes.
No ratings yet
View paper →The Art of Assemblage at La Venta
Claudia Brittenham
Art History·2022
<jats:p>How might the meaning of monumental sculpture be ephemeral? At La Venta, objects from greenstone figurines to massive basalt sculptures were recycled, reworked, and moved around the landscape, their new configurations and associations creating new kinds of meaning and enabling new kinds of ritual interaction. This essay considers the assemblage, and not just the individual work, as an important category of art‐historical analysis. By considering the divergent materialities of stelae, celts, figurines, and colossal heads, as well as the role that ephemeral materials played in the construction of ritually significant assemblages, I explore the connections between monumentality, memory, and forgetting at La Venta.</jats:p>
No ratings yet
View paper →Re-Noted: 6 Ways to Use a Diary
Jillian Hess
Substack·2024
"Keeping a diary is a gift to your future self."
No ratings yet
View paper →