Found 13 document(s)
Page 1 of 1
-
In this paper, we investigate the issue of difference awareness in LLMs, defined as a model's ability to recognize and acknowledge meaningful differences between social groups in fairness decision-making. Previous studie...
-
Robot deployment generates experience that can support policy improvement, but continued reliance on expert corrective actions makes learning difficult to scale across growing fleets. We propose learning from fleet exper...
-
Diffusion Transformers (DiTs) deliver high-fidelity image and video generation, but inference requires many sequential model evaluations. Two acceleration strategies are increasingly important: model compression makes ea...
-
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of mem...
-
Can LLM agents make contributions to frontier computer science R&D? We introduce FrontierCS 2, a benchmark of 48 open-ended tasks. We take a paper and the code its authors released and delete the paper's contribution. Th...
-
Recent world action models provide visual foresight and future prediction for robot manipulation, but lack explicit mechanisms for compositional skill reuse. Agentic robotics combines code-based planning and reasoning wi...
-
HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: a compact planner requests future body-p...
-
As AI agents reshape Web search and advertising, platforms can monetize information that improves decisions. We study information pricing for sequential search among independent alternatives with nonobligatory inspection...
-
We introduce PhysLadder, a hierarchical Sim-Real benchmark for evaluating physical interaction capabilities in contact-rich manipulation. Its 16 household tasks span three cumulative levels: contact selection and geometr...
-
Single-Domain Generalized Object Detection (S-DGOD) aims to generalize from a single source domain to unseen domains under distribution shifts. Existing efforts mainly focus on simulating unseen domains or suppressing do...
-
Mangroves are hotspots of carbon sequestration in transitional zones between marine and terrestrial ecosystems. Microbially driven dark carbon fixation (DCF) is prominent in sediments, yet our understanding of the DCF pr...
-
Leveraging the models' outputs, specifically the logits, is a common approach to estimating the test accuracy of a pre-trained neural network on out-of-distribution (OOD) samples without requiring access to the correspon...
-
Nowadays, the manufacturing of electrical machines based on electrical steel laminations has been well established worldwide. Compared with the electrical steel, the soft magnetic composites (SMC) shows magnetic isotropy...