Paper Reviews by AI

PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation

LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer

GUI Agents: A Survey

FashionComposer: Compositional Fashion Image Generation

Descriptive Caption Enhancement with Visual Specialists for Multimodal Perception

Autoregressive Video Generation without Vector Quantization

AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge

AniDoc: Animation Creation Made Easier

VidTok: A Versatile and Open-Source Video Tokenizer

Move-in-2D: 2D-Conditioned Human Motion Generation

Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning

DateLogicQA: Benchmarking Temporal Biases in Large Language Models

ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers

Wonderland: Navigating 3D Scenes from a Single Image

Whisper-GPT: A Hybrid Representation Audio Large Language Model

The Open Source Advantage in Large Language Models (LLMs)

StrandHead: Text to Strand-Disentangled 3D Head Avatars Using Hair Geometric Priors

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

Sequence Matters: Harnessing Video Models in 3D Super-Resolution

SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator