forthy
发表于 2025-3-30 08:22:06
,Diffusion Models as Optimizers for Efficient Planning in Offline RL,hieve more efficient planning without sacrificing capability. To evaluate the effectiveness and efficiency of the Trajectory Diffuser, we conduct experiments on the D4RL benchmarks. The results demonstrate that our method achieves .-. faster inference speed compared to previous sequence modeling met
PATHY
发表于 2025-3-30 14:04:41
,Enhanced Sparsification via Stimulative Training,illation-guided exploration strategy. To reduce the huge capacity gap of distillation, we propose a subnet mutating expansion technique. Extensive experiments on various benchmarks indicate the effectiveness of STP. Specifically, without fine-tuning, our method consistently achieves superior perform
lesion
发表于 2025-3-30 18:33:27
How Many Are in This Image A Safety Evaluation Benchmark for Vision LLMs,) Current VLLMs struggle with OOD texts but not images, unless the visual information is limited; and 2) These VLLMs can be easily misled by deceiving vision encoders only, and their vision-language training often compromise safety protocols. We release this safety evaluation suite at ..
overwrought
发表于 2025-3-30 20:52:04
http://reply.papertrans.cn/25/2424/242329/242329_54.png
无力更进
发表于 2025-3-31 01:00:29
,Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGBocal geometric clues and the coarse-level visual priors to capture intricate details. Additionally, we propose a surface-aware efficient reconstruction strategy that sparsely performs SDF query based on the hand-object semantic priors. Experiments on two challenging hand-object datasets show that ou
羞辱
发表于 2025-3-31 06:43:28
http://reply.papertrans.cn/25/2424/242329/242329_56.png
HEPA-filter
发表于 2025-3-31 11:25:44
,Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective, reduce computation cost rather than fully fine-tuning all the parameters. In addition, multi-level circle loss is proposed to align the original and augmented data pairs, which assigns different penalties for positive and negative pairs. On the Recipe1M dataset, our DAR outperforms all existing met
SNEER
发表于 2025-3-31 13:35:47
PapMOT: Exploring Adversarial Patch Attack Against Multiple Object Tracking,de the temporal consistency of tracking results across video frames, resulting in more aggressive attacks. We further develop new evaluation metrics to assess the robustness of MOT against such attacks. Extensive evaluations on multiple datasets demonstrate that our PapMOT can successfully attack va
发酵
发表于 2025-3-31 17:38:30
,HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models,etrained diffusion models to scale image generation resolutions even to . at . the inference speed of previous methods. Extensive experiments demonstrate that our approach can address object duplication and heavy computation issues, achieving state-of-the-art performance on higher-resolution image s
不幸的人
发表于 2025-3-31 23:25:06
,Syn-to-Real Domain Adaptation for Point Cloud Completion via Part-Based Approach,ule, which operates in a part-wise manner to produce complete point clouds. Within PAC, we devise a novel part-aware transformer to learn relationships between parts and utilize this information to infer missing parts in incomplete point clouds. Extensive experiments demonstrate that our part-based