Generative Models

LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding ICCV 2025 LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditions ICCV 2025 LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos ICML 2025 Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond ACL 2025 Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation AAAI 2025 Linear combinations of latents in generative models: subspaces and beyond ICLR 2025 LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields CVPR 2025 Little Martians: From Desert Clay to Generative Agents NeurIPS 2025 Live Music Models NeurIPS 2025 LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement ACL 2025 LLM-Based Multi-Agent Systems are Scalable Graph Generative Models ACL 2025 LLMs Behind the Scenes: Enabling Narrative Scene Illustration EMNLP 2025 LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs ICCV 2025 LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data ICML 2025 Local Conditional Controlling for Text-to-Image Diffusion Models AAAI 2025 Locality Sensitive Avatars From Video ICLR 2025 LOHRec: Leveraging Order and Hierarchy in Generative Sequential Recommendation EMNLP 2025 Long-Form Speech Generation with Spoken Language Models ICML 2025 Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection ICLR 2025 LookAlike: Consistent Distractor Generation in Math MCQs ACL 2025 LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping CVPR 2025 Low-Light Image Enhancement via Generative Perceptual Priors AAAI 2025 LPCG: A Self-conditional Architecture for Labeled Point Cloud Generation AAAI 2025 LUMIA: A Handheld Vision-to-Music System for Real-Time, Embodied Composition NeurIPS 2025 Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment CVPR 2025