AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation Paper • 2609.35530 • Published 6 days ago • 17
Chinese-Jev: Bringing System One Model to Chinese-Language Tasks Paper • 2609.36965 • Published 5 days ago • 22
HiRAE: Hierarchical Representation Autoencoding with Residual Budgets Paper • 2609.37775 • Published 5 days ago • 21
Think Before You Score: Thinking Reward Model for Visual Generation Paper • 2609.37372 • Published 5 days ago • 97
SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation Paper • 2609.33399 • Published 7 days ago • 16
FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching Paper • 2609.35673 • Published 6 days ago • 34
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning Paper • 2609.35767 • Published 6 days ago • 48
FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders Paper • 2609.31620 • Published 9 days ago • 159
AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs Paper • 2609.31590 • Published 9 days ago • 11
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation Paper • 2609.28923 • Published 10 days ago • 10
Agent-Editing World Model: Rethinking World Modeling for LLM Agents Paper • 2609.28416 • Published 11 days ago • 43
Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models Paper • 2609.24657 • Published 13 days ago • 40
StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training Paper • 2609.26774 • Published 12 days ago • 56
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay Paper • 2609.25001 • Published 13 days ago • 131
Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network Paper • 2609.20633 • Published 17 days ago • 13
Paint-Anything: Unified Any-Color Control for Image Generation and Editing Paper • 2609.20816 • Published 17 days ago • 57