Hierarchical navigation with cross-graph memory and viewpoint planning improves quadrotor image-based object localization, achieving 88% success in simulation.

Junjie Gao, Yuqi Chen, Yongzhou Pan et al.

CI-MSE improves offline validation by focusing on task-critical segments, enhancing correlation with real-world performance.

Haoxu Huang, Tongsam Zheng, Yifan Chen et al.

SABER-Math constructs an automated, fine-grained benchmark for mathematical IR using large models, ontology, and preference ranking, outperforming traditional methods.

Nikolay Georgiev, Maria Drencheva, Kseniia Ibragimova et al.

Proposes modality-specific sparse autoencoders and post-hoc alignment to address cross-modal feature heterogeneity, boosting retrieval accuracy to 85.3% on MS-COCO.

Chungpa Lee, Jihoon Kwon, Kyle Min et al.

Dual-Flow RL employs conditional flow matching to jointly model return distribution and multimodal policy, enhancing exploration and value estimation in continuous control.

Qijun Li, Zheng Fu, Qi Song et al.

Nemotron-Labs-Diffusion-Image introduces a masked discrete diffusion model with token editing and GCE, achieving 0.90 on GenEval for high-res text-to-image synthesis.

Shufan Li, Greg Heinrich, Hanrong Ye et al.

Concept-centric memory framework improves long-horizon embodied manipulation by explicit object structure, achieving 70% success on RMBench.

Mingyang Sun, Xiujian Liang, Jiude Wei et al.

GUICrafter enhances GUI agent cross-device generalization using weak supervision and massive unannotated screenshots.

Sunqi Fan, Lingshan Chen, Runqi Yin et al.

By freezing OpenVLA policy, linear probes detect failure signals under visual distribution shift, achieving AUROC of 0.972.

Dipesh Tharu Mahato, Rachel Ren

SFBench is a benchmark dataset with 197 material science claims for evaluating scientific claim feasibility.

Cash Costello, James Mayfield, Elsbeth Turcan et al.

Introduced MultiDepth-3k benchmark and Laplacian Visual Prompting (LVP) to probe depth-layer preferences; DAv2-L achieved 75.5% ML-SRA.

Xiaohao Xu, Feng Xue, Xiang Li et al.

RESOURCE2SKILL distills multimodal human resources into executable skills, improving agent performance by +11.9 points on average.

Yijia Fan, Zonglin Di, Zimo Wen et al.

CogWM tracks user BDI/E states for cognitive evaluation of conversational agents, trained on 150K samples, outperforming baselines.

Minghui Ma, Bin Guo, Hao Wang et al.

MIRROR employs Gromov–Wasserstein regularization to transfer semantic relation geometry from language to vision, boosting multimodal relational reasoning.

Hong-Han Wang, Yuntao Wang, Hu Ding

Proposed a self-supervised framework using eight phase-shift images to learn subsurface scattering representations.

Arjun Majumdar, Raphael Braun, Andreas Engelhardt et al.

TASKER algorithm improves video understanding by task-driven and scene-aware keyframe extraction, achieving a 2.0% gain on EgoSchema.

Sunqi Fan, Qingle Liu, Runqi Yin et al.

Proposes an AI risk assessment framework integrating Operational Design Domains (ODD) to define safety boundaries, improving hazard identification.

Heidy Khlaaf

Latent Genetic Algorithm (LGA) improves HfO2 ground-state recovery rate to 60-95% via latent space crossover.

Kaixin Zheng, Wanjian Yin, Hongyu Yu et al.

TacGen aligns vision and touch via contrastive learning and latent diffusion, effectively addressing tactile data scarcity and improving physical property representation.

Wanghao Ye, Aarosh Das, Sihan Chen et al.

Introduces TILR, a low-rank subspace method that identifies stable reasoning directions, improving model consistency by ~10% and reducing trajectory variance by 50%.

Arun Vignesh Malarkkan, Manan Roy Choudhury, Utkarsh Byahut et al.