AI研究论文每日精选

TEXGen: a Generative Diffusion Model for Mesh Textures

DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting

Star Attention: Efficient LLM Inference over Long Sequences

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

Pathways on the Image Manifold: Image Editing via Video Generation

MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs

Rethinking Token Reduction in MLLMs: Towards a Unified Paradigm for Training-Free Acceleration

SketchAgent: Language-Driven Sequential Sketch Generation

Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE

VLRewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models

SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis

Learning 3D Representations from Procedural 3D Programs

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

AnchorCrafter: Animate CyberAnchors Saling Your Products via Human-Object Interacting Video Generation

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

MolReFlect: Towards In-Context Fine-grained Alignments between Molecules and Texts

Controllable Human Image Generation with Personalized Multi-Garments

Visual Counter Turing Test (VCT^2): Discovering the Challenges for AI-Generated Image Detection and Introducing Visual AI Index (V_AI)