Category
3,920 papers
The findings indicate that the accuracy cost of removing labels from feature learning is small on this benchmark, and that reported weaknesses of unsupervised spiking networks may be attributable to the readout protocol rather than to the learning rule.
This work introduces a frame-selection method designed specifically for multiple-choice questions, and is the first to directly utilize answer choices as inference-time cues for selecting frames relevant to answering a question.
A cross-domain learning model is proposed, using an original neural network architecture based on a Temporal Convolutional Network and multiple prediction heads, designed to improve handwriting trace reconstruction from sensor data, where each domain benefits from additional data provided by the other domain.
Six pretrained models on two SAR ship datasets are evaluated in in-domain classification, cross-dataset transfer, and unknown-class detection, showing that cross-dataset generalization in SAR remains limited and that task-specific uncertainty scores are often more informative than MC-dropout variance for held-out-class...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Remote-sensing foundation models offer strong representations for SAR imagery, but their behavior under severe long-tail class imbalance is still not well characterized, so four oversampling methods in embedding space exclusively to minority classes are applied and a lightweight classifier head is trained on the augmen...
Checkpoint-resolved, per-head analysis under fixed selection rules can expose sparse temporal organization in other factorized video diffusion transformers and, with adapted routing metrics, in joint spatio-temporal architectures.
PalmLeaf-VQA provides a standardized benchmark for advancing culturally grounded and layout-aware multimodal document analysis and reveals substantial limitations in current MLLMs for rare-script, degraded-layout, and preservation-oriented document understanding.
Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorrect results. Existing benchmarks either rely on image-centric or subjective metrics insensitive to structure, or evaluate intermediate symbolic representations rather than...
Verifiable Visual Rewards (VVR) is introduced, the first framework for programmatically verifiable image rewards, and it is shown that training on it generalizes to natural prompts, and gains extend to out-of-domain benchmarks.
This work proposes Tool-Grounded Multi-Agent Reasoning for Compositional Chemical Problem Solving (TMCS), a step-by-step multi-agent framework that formalizes chemical problem solving as an interpretable, tool-augmented workflow.
A cross-resolution two-stage generation scheduler is introduced that exploits the step-wise nature of diffusion, completely eliminating the computationally expensive VAE decode-reencode cycle for resolution transferring cross different resolutions.
JRDB-AVR is introduced, a benchmark derived from existing real-world JRDB robotics data through a structured question-generation engine that turns this gap between answer accuracy and evidence accuracy in current baselines into an explicit evaluation.
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
GPT-Lab
· gpt-lab.eu
Oct 8, 2026
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
A Blog post by H company on Hugging Face
A Blog post by Liquid AI on Hugging Face
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
