iclr2025 topic

[ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs

zjysteven

[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

buaacyw

[ECCV`24&ICLR`25] CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians

Linketic

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

nunchaku-tech

High-quality and editable surfel 3D Gaussian generation through native 3D diffusion (ICLR 2025)

NIRVANALAN

Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).

paulgavrikov

Official code repo of ICLR'25 paper: MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations

amai-gsu

[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

miccunifi

[ICLR 2025] Benchmarking Agentic Workflow Generation

zjunlp

[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

zjunlp