· ai
[Paper] LiteEmbed: Adapting CLIP to Rare Classes
Large-scale vision-language models such as CLIP achieve strong zero-shot recognition but struggle with classes that are rarely seen during pretraining, includin...
-
- · ai
[Paper] Image2Garment: Simulation-ready Garment Generation from a Single Image
Estimating physically accurate, simulation-ready garments from a single image is challenging due to the absence of image-to-physics datasets and the ill-posed n...
- · ai
[Paper] Exploring Fine-Tuning for Tabular Foundation Models
Tabular Foundation Models (TFMs) have recently shown strong in-context learning capabilities on structured data, achieving zero-shot performance comparable to t...
- · ai
[Paper] Creating a Hybrid Rule and Neural Network Based Semantic Tagger using Silver Standard Data: the PyMUSAS framework for Multilingual Semantic Annotation
Word Sense Disambiguation (WSD) has been widely evaluated using the semantic frameworks of WordNet, BabelNet, and the Oxford Dictionary of English. However, for...
- · ai
[Paper] Identifying Models Behind Text-to-Image Leaderboards
Text-to-image (T2I) models are increasingly popular, producing a large share of AI-generated images online. To compare model quality, voting-based leaderboards ...
- · ai
[Paper] PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
While GUI agents have shown strong performance under explicit and completion instructions, real-world deployment requires aligning with users' more complex impl...
- · ai
[Paper] LLM for Large-Scale Optimization Model Auto-Formulation: A Lightweight Few-Shot Learning Approach
Large-scale optimization is a key backbone of modern business decision-making. However, building these models is often labor-intensive and time-consuming. We ad...
- · ai
[Paper] TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion
Taxonomies form the backbone of structured knowledge representation across diverse domains, enabling applications such as e-commerce catalogs, semantic search, ...
- · ai
[Paper] From Prompt to Protocol: Fast Charging Batteries with Large Language Models
Efficiently optimizing battery charging protocols is challenging because each evaluation is slow, costly, and non-differentiable. Many existing approaches addre...
- · ai
[Paper] Pruning as Evolution: Emergent Sparsity Through Selection Dynamics in Neural Networks
Neural networks are commonly trained in highly overparameterized regimes, yet empirical evidence consistently shows that many parameters become redundant during...
- · it
Robotics software maker Skild AI hits $14B valuation
Skild AI, which is building general-purpose robotic software, just raised a $1.4 billion funding round led by SoftBank....
- · ai
[Paper] Improving CMA-ES Convergence Speed, Efficiency, and Reliability in Noisy Robot Optimization Problems
Experimental robot optimization often requires evaluating each candidate policy for seconds to minutes. The chosen evaluation time influences optimization becau...