6 papers
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
Chenyang Wang, Weizhong Wang, Yinuo Ren +2
iffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific obj…
UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs
Lifan Jiang, Tianrun Wu, Yuhang Pei +3
The evaluation of visual editing models remains fragmented across methods and modalities. Existing benchmarks are often tailored to specific paradigms, making fair cross-paradigm c…
Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning
Chun-Peng Chang, Chen-Yu Wang, Holger Caesar +1
A reliable driving assistant should provide consistent responses based on temporally grounded reasoning derived from observed information. In this work, we investigate whether Visi…
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen +7
Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal…
OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
Bingnan Li, Chen-Yu Wang, Haiyang Xu +7
Despite steady progress in layout-to-image generation, current methods still struggle with layouts containing significant overlap between bounding boxes. We identify two primary ch…
Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation
Chun-Peng Chang, Chen-Yu Wang, Julian Schmidt +2
Recent advancements in video generation have substantially improved visual quality and temporal coherence, making these models increasingly appealing for applications such as auton…