👁 Image Submitted by 👁 Image Wang Yanghao 13 LISA: Likelihood Score Alignment for Visual-condition Controllable Generation 👁 HKUST HKUST 5 1
👁 Image Submitted by 👁 Image pangly 4 MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training 👁 HKUST HKUST 2
👁 Image Submitted by 👁 Image Ning Lu 11 Policy and World Modeling Co-Training for Language Agents 👁 HKUST HKUST 3
👁 Image Submitted by 👁 Image JingyeChen22 9 Does Synthetic Layered Design Data Benefit Layered Design Decomposition? 👁 HKUST HKUST 10 3
👁 Image Submitted by 👁 Image Yuan 16 Rethinking the Diffusion Model from a Langevin Perspective 👁 HKUST HKUST 2
👁 Image Submitted by 👁 Image tianyu liu 9 AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing 👁 HKUST HKUST 53 2
👁 Image Submitted by 👁 Image Yihong Luo 13 TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward 👁 HKUST HKUST 107 2
👁 Image Submitted by 👁 Image Xianfeng Wu 10 Show, Don't Tell: Morphing Latent Reasoning into Image Generation 👁 HKUST HKUST 45 2
👁 Image Submitted by 👁 Image Zhitao 14 Dancing in Chains: Strategic Persuasion in Academic Rebuttal via Theory of Mind 👁 HKUST HKUST 54 3
👁 Image Submitted by 👁 Image Zipeng Wang 5 FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention 👁 HKUST HKUST 95 2
👁 Image Submitted by 👁 Image taesiri 18 GIR-Bench: Versatile Benchmark for Generating Images with Reasoning 👁 HKUST HKUST 35 3
👁 Image 1 TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided Optimization 👁 HKUST HKUST 20
