Many operations run on a budget that must rarely run out, such as a wear allowance. A wrapper keeps the remaining budget in the state, subtracts a barrier that grows as the budget shrinks and clips the combined reward from below at -m, and a standard policy-gradient learner trains unchanged. The clip level m is a price...
Pekka Malo, Lauri Viitasaari, Antti Suominen et al.· 0 citations
Hate speech detectors must separate hateful posts from the far more common offensive but non-hateful ones, and two popular ideas for doing so are hierarchical (coarse-to-fine) classification and sentiment features. We revisit our earlier transformer-based framework, which combines both ideas, and test each component in...
She Works, He Works is an interdisciplinary project that combines feminist visual theory, AI critique, and artistic practice to examine gender representation in AI-generated imagery. By juxtaposing text-to-image outputs of male and female construction workers, it reveals how societal biases manifest in generative AI sy...
Language Models (LMs) have demonstrated exceptional performance across various Natural Language Processing (NLP) tasks. Despite these advancements, LMs can inherit and amplify societal biases related to sensitive attributes such as gender and race, limiting their adoption in real-world applications. Therefore, fairness...
Zhipeng Yin, Zichong Wang, Avash Palikhe et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
DyRA is introduced, a dynamic resolution adjustment network providing an image-specific scale factor for existing detectors providing an image-specific scale factor for existing detectors utilizing specially designed loss functions, namely ParetoScaleLoss and BalanceLoss.
Daeun Seo, Hoeseok Yang, Hyungshin Kim· 3 citations· ⚡1
Normative and algorithmic theories of neural computation are integrated to present a mathematical framework for inferring canonical distributed computations from large-scale neural activity patterns and recover the latent variables, their neural representation and dynamics, and canonical message functions that govern t...
Rajkumar Vasudeva Raju, Zhe Li, Scott W. Linderman et al.· arXiv.org· 2 citations
This study suggests that machine-checked specifications in Lean can replace empirical evaluation in open-ended algorithm discovery and is the first example of an automated pipeline that designs efficient black-box optimisation algorithms with machine-checked runtime bounds in Lean.
FNO-MoE is introduced, a Fourier neural operator with a mixture of experts that predicts the full near-explicit chemical state over 30 minutes in a single call and guides its own training, using the disagreement among its experts to select the most informative box-model simulations.
Zhi-Song Liu, W. Peng, Ammar Kheder et al.· 0 citations
Zero-shot detection of machine-generated text is vital for mitigating the risks of large language models (LLMs) misuse. While the state-of-the-art dual-model detectors and resampling-based detectors outperform single-model statistical detectors on unprompted continuations, they suffer a catastrophic breakdown on instru...
Xinpeng Wang, Bruce Rushing, Zhizhen Chen et al.· 0 citations
Agents end many steps in a typed decision over a set of candidates: which screen element to click, which product to pick. System One models answer in one forward pass, and Jeva showed that four properties the setting demands - a "none of the above" probability, invariance to candidate order, scalability in the number o...
Coding agents are moving from handling one request at a time to serving as persistent assistants to which users hand a stream of work: a build, a data-processing job and a bug fix may all be pending on the same machine at once. Such an agent must decide when to take on new tasks, how to delegate and overlap them, and h...
Erle Zhu, Genrui Zhang, Keyang Hu et al.· 0 citations
Analogical reasoning is widely considered a fundamental component of human intelligence. Few benchmarks are designed to explicitly test far analogical reasoning - reasoning between domains that are superficially dissimilar yet share deep relational or structural similarities. In this work, we introduce an analogical re...
