VLMs meet UDA: Boosting Transferability of Open Vocabulary Segmentation with Unsupervised Domain Adaptationby Roberto Alcover-Couso,…
Phi-4 Technical Reportby Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar,…
Exploring Large Language Models on Cross-Cultural Values in Connection with Training Methodologyby Minsang Kim, Seungjun…
GASP: Gaussian Avatars with Synthetic Priorsby Jack Saunders, Charlie Hewitt, Yanan Jian, Marek Kowalski, Tadas…
I See, Therefore I Do: Estimating Causal Effects for Image Treatmentsby Abhinav Thorat, Ravi Kolla,…
BhashaVerse : Translation Ecosystem for Indian Subcontinent Languagesby Vandan Mujadia, Dipti Misra SharmaFirst submitted to…
VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrievalby…
ToxiLab: How Well Do Open-Source LLMs Generate Synthetic Toxicity Data?by Zheng Hui, Zhaoxiao Guo, Hang…
LLM for Barcodes: Generating Diverse Synthetic Data for Identity Documentsby Hitesh Laxmichand Patel, Amit Agarwal,…
MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth Estimationby Ansh Shah, K Madhava KrishnaFirst…