BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning Paper • 2603.04918 • Published 6 days ago • 54
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders Paper • 2603.06569 • Published 4 days ago • 89
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence Paper • 2603.07660 • Published 2 days ago • 65
CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing Paper • 2603.08589 • Published 1 day ago • 29
ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts Paper • 2507.20939 • Published Jul 28, 2025 • 57
Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention Paper • 2507.17745 • Published Jul 23, 2025 • 36
Pixels, Patterns, but No Poetry: To See The World like Humans Paper • 2507.16863 • Published Jul 21, 2025 • 69
Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model Paper • 2507.11465 • Published Jul 15, 2025 • 18
DesignLab: Designing Slides Through Iterative Detection and Correction Paper • 2507.17202 • Published Jul 23, 2025 • 51
AFRDA: Attentive Feature Refinement for Domain Adaptive Semantic Segmentation Paper • 2507.17957 • Published Jul 23, 2025 • 2
Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning Paper • 2507.21049 • Published Jul 28, 2025 • 41
Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models Paper • 2506.00996 • Published Jun 1, 2025 • 40
Taming LLMs by Scaling Learning Rates with Gradient Grouping Paper • 2506.01049 • Published Jun 1, 2025 • 39
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis Paper • 2505.24672 • Published May 30, 2025 • 3