[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
[ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time
High-quality and editable surfel 3D Gaussian generation through native 3D diffusion (ICLR 2025)
[ICLR 2025] Animate-X: Universal Character Image Animation with Enhanced Motion Representation
🔥[ICLR'25] LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models
[ICLR 2025 Spotlight] Official implementation for "DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes"
[ICLR 2025] VideoGrain: This repo is the official implementation of "VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing"
[ICLR 2025] Benchmarking Agentic Workflow Generation
[ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers
[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Detail-Oriented CLIP for Fine-Grained Tasks (ICLR SSI-FM 2025)
[ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs
Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).
[ICLR 2025] NeRAF jointly learns acoustic and radiance fields, enabling realistic audio-visual generation.
[ICLR 2025] Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
Official Implementation for (ICLR 2025) Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior
The official source code for "Subgraph Federated Learning for Local Generalizatioin (FedLoG)" at ICLR 2025 (Oral).
Add a description, image, and links to the iclr2025 topic page so that developers can more easily learn about it.
To associate your repository with the iclr2025 topic, visit your repo's landing page and select "manage topics."