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.

RayFronts fuses dense voxel mapping with multi-directional semantic ray frontiers, boosting real-time open-set scene understanding and exploration efficiency.

Omar Alama, Avigyan Bhattacharya, Haoyang He et al.

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

Xinhao Li, Ziang Yan, Desen Meng et al.

Introduces GraspClutter6D, a large-scale real-world dataset with 736K 6D object poses and 9.3 billion grasp annotations across 1000 cluttered scenes, significantly improving grasping in complex environments.

Seunghyeok Back, Joosoon Lee, Kangmin Kim et al.

ASI method boosts agent task success by 23.5% and improves efficiency by 10.7-15.3% through programmatic skills.

Zora Zhiruo Wang, Apurva Gandhi, Graham Neubig et al.

Proposes domain-conditioned scene graphs for state grounding, achieving over 85% accuracy and 90% task success, outperforming LMM-based methods.

Jonas Herzog, Jiangpin Liu, Yue Wang

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.

ASHiTA combines LLM and 3D scene graphs to automatically analyze hierarchical tasks grounded in environment.

Yun Chang, Leonor Fermoselle, Duy Ta 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.

GTBO algorithm identifies active dimensions to enhance high-dimensional Bayesian optimization performance.

Erik Hellsten, Carl Hvarfner, Leonard Papenmeier et al.

Introduces Meta-Continual Learning of Neural Fields (MCL-NF), significantly improving learning speed and reconstruction quality.

Seungyoon Woo, Junhyeog Yun, Gunhee Kim

AdaRFT uses adaptive curriculum learning to halve training time and boost reasoning accuracy in large language models.

Taiwei Shi, Yiyang Wu, Linxin Song et al.

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

Heeji Yoon, Heeseong Shin, Eunbeen Hong et al.

SmolVLM employs architectural and tokenization innovations to create resource-efficient multimodal models with under 1GB GPU memory, outperforming much larger models.

Andrés Marafioti, Orr Zohar, Miquel Farré et al.

NoveltyBench evaluates language models' diversity; 20 models mostly underperform human baseline, larger models show less diversity, highlighting mode collapse issues.

Yiming Zhang, Harshita Diddee, Susan Holm et al.

Proposes LARM framework with multimodal LLM fine-tuning, embedding alignment, and semantic coding to improve live-streaming recommendation.

Yueyang Liu, Jiangxia Cao, Shen Wang et al.

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

Sebastian Schmidt, Julius Körner, Dominik Fuchsgruber et al.