Proposes HAF-VT, a multimodal hierarchical attention model, boosting cross-domain sequential recommendation by 3-5% on key metrics.

Wangyu Wu, Zhenhong Chen, Siqi Song et al.

Twin-Co framework combines multi-turn dialogue and internal optimization, boosting image-text alignment with CLIP score reaching 0.338.

Jianhui Wang, Yangfan He, Yan Zhong et al.

CheXWorld employs a self-supervised world model with multi-task learning, capturing local structures, global layouts, and domain shifts, achieving state-of-the-art results on 8 benchmarks.

Yang Yue, Yulin Wang, Chenxin Tao et al.

PerceptionLM employs multi-stage training with 2.8M human-annotated video QA and spatio-temporal captions, advancing transparent vision-language modeling.

Jang Hyun Cho, Andrea Madotto, Effrosyni Mavroudi et al.

Proposes Uni-Inv and Uni-Edit for accurate inversion and region-aware editing in flow models, achieving low error rates and natural edits.

Guanlong Jiao, Biqing Huang, Kuan-Chieh Wang et al.

Proposes ForgetMe dataset and Entangled metric for selective forgetting in diffusion models, using prompt-layered editing and training-free local feature removal.

Zhenyu Yu, Mohd Yamani Inda Idris, Pei Wang

PartField uses contrastive learning for 3D part features, achieving 85% accuracy and 20x speedup on ShapeNetPart.

Minghua Liu, Mikaela Angelina Uy, Donglai Xiang et al.

GUI-R1 employs rule-based reinforcement fine-tuning with only 3K samples, outperforming SOTA on multi-platform GUI tasks.

Run Luo, Lu Wang, Wanwei He et al.

SegEarth-R1 leverages large language models for geospatial pixel reasoning, achieving 70.75% cIoU on EarthReason, outperforming prior methods.

Kaiyu Li, Zepeng Xin, Li Pang et al.

GigaTok scales visual tokenizers to 3 billion parameters using semantic regularization, resolving the reconstruction-generation trade-off and achieving state-of-the-art results.

Tianwei Xiong, Jun Hao Liew, Zilong Huang et al.

KARMMA framework achieves robust egocentric action recognition under missing modalities, reducing computational resources by 50%.

Maria Santos-Villafranca, Dustin Carrión-Ojeda, Alejandro Perez-Yus et al.

Proposes MM-IFEngine to generate large-scale, diverse multimodal instruction data, boosting instruction-following performance by +12.3% on MM-IFEval.

Shengyuan Ding, Shenxi Wu, Xiangyu Zhao et al.

Proposes Perception-R1 framework using GRPO for visual perception policy learning, achieving 31.9% AP on COCO detection.

En Yu, Kangheng Lin, Liang Zhao et al.

VLM-R1 enhances vision-language models using GRPO algorithm, outperforming SFT.

Haozhan Shen, Peng Liu, Jingcheng Li et al.

Objaverse++ annotates 10,000 3D models with quality scores, improving image-to-3D generation performance by 15% over baseline.

Chendi Lin, Heshan Liu, Qunshu Lin et al.

VideoChat-R1 enhances spatio-temporal perception via reinforcement fine-tuning, significantly improving video reasoning.

Xinhao Li, Ziang Yan, Desen Meng et al.

PosterMaker framework leverages TextRenderNet and SceneGenNet, achieving over 90% text rendering accuracy in high-quality product poster generation.

Yifan Gao, Zihang Lin, Chuanbin Liu et al.

D2USt3R enhances 3D reconstruction in dynamic scenes using Static-Dynamic Aligned Pointmaps, significantly improving accuracy.

Jisang Han, Honggyu An, Jaewoo Jung et al.

S4M enhances semi-supervised instance segmentation with SAM, achieving state-of-the-art performance.

Heeji Yoon, Heeseong Shin, Eunbeen Hong et al.

Prior2Former integrates evidential learning with mask transformers for assumption-free open-world panoptic segmentation.

Sebastian Schmidt, Julius Körner, Dominik Fuchsgruber et al.