Found 42,749 document(s)
Page 53 of 2850
-
Policy Central is a deployed system that helps police departments find relationships between sections of their written policy: whether two sections conflict, are redundant, are merely similar, or are different. We descri...
-
Stance classifiers make errors that can be costly to identify under limited human-review budgets. Prioritizing potentially incorrect predictions remains challenging, particularly across heterogeneous base models. We intr...
-
Robots deployed in human-centered environments need maps that support both geometric navigation and open-vocabulary semantic queries beyond a fixed label set. A key challenge is enriching such maps with semantic informat...
-
Quantization-aware training (QAT) aims to recover reasoning capabilities in low-bit large language models (LLMs). Existing recipes typically supervise the quantized student with the original full-precision model on fixed...
-
Magneto-mechanical resonators (MMRs) are a recently introduced sensor technology for tracking and sensing applications that enables effective miniaturization down to the millimeter regime. However, estimating sensor para...
-
Correct transcription does not establish that a word depended on its local audio. We introduce the Acoustic Evidence Contribution (AEC), a word-level counterfactual measure of acoustic grounding. It is obtained from the ...
-
In implicit neural representations (INRs), 3D signals are encoded directly in network weights, making stable weight-space operations essential. However, permutation symmetry causes independently trained yet functionally ...
-
Automated optical inspection of precision components with tiny surface defects remains challenging when different regions of the same component exhibit different defect characteristics and, therefore, different acceptanc...
-
Ferroelectric oxides, characterized by an electrical polarization that is switchable with an electric field, are an appealing class of materials for energy-efficient computing, electronics, and photonics. In thin films, ...
-
Preference optimization can improve every ranking metric while building a hidden, shared representation shift that the relative loss barely sees, one that can eventually destroy generation. We trace this failure to the c...
-
Text-to-image generation models do not explicitly receive the syntactic structure of the prompt, i.e., which word modifies which and where each phrase attaches. Consequently, they often struggle to bind attributes to the...
-
Among existing embedding compression approaches, low-rank factorization provides a simple and mathematically principled solution by approximating the embedding matrix with a reduced-rank decomposition. However, its pract...
-
While agentic reinforcement learning (RL) has emerged as a promising paradigm for training small language models (SLMs), existing frameworks are predominantly tool-centric and struggle with data-centric environments. Spe...
-
Visual grounding (VG) in visual question answering (VQA) is a fundamental capability of Vision-Language Models (VLMs), enabling the detection of the most relevant region in an image to answer the question. This reflects ...
-
The Open Compute Project's microscaling (MX) family includes MXFP4, which stores 32 four-bit elements with a shared power-of-two scale. When lowering a dot-product reduction, a compiler can apply these scales before the ...