Proposes TTF-VLA, a training-free temporal fusion method combining pixel difference and attention, boosting robotic manipulation success by 4-8%.

Chenghao Liu, Jiachen Zhang, Chengxuan Li et al.

CHORD framework harmonizes SFT and RL via dynamic weighting, improving LLMs' performance.

Wenhao Zhang, Yuexiang Xie, Yuchang Sun et al.

Proposes a discrete-time linear causal model for latent process detection in Hawkes processes, enabling structure recovery without prior knowledge.

Songyao Jin, Biwei Huang

Introduced Conic Gromov-Wasserstein (CGW) distance for comparing unbalanced measure networks and hypernetworks, offering robustness and scalability.

Mary Chriselda Antony Oliver, Emmanuel Hartman, Tom Needham

TexVerse provides 1.6M high-resolution 3D models, addressing gaps in texture generation datasets.

Yibo Zhang, Li Zhang, Rui Ma et al.

UI-Venus achieves SOTA in UI grounding/navigation using RFT.

Zhangxuan Gu, Zhengwen Zeng, Zhenyu Xu et al.

This review unifies Memory-Augmented Transformers through three taxonomies, but reports no new dataset-level benchmark.

Parsa Omidi, Xingshuai Huang, Axel Laborieux et al.

Pass@k training leverages the Pass@k metric as reward, with analytical derivation of advantage functions, significantly enhancing large models' exploration, outperforming traditional Pass@1 training.

Zhipeng Chen, Xiaobo Qin, Youbin Wu et al.

STEP method enhances semantic fusion and precision in conversational recommendation via curriculum learning.

Zhenye Yang, Jinpeng Chen, Huan Li et al.

Πnet introduces an orthogonal projection layer for neural networks, enabling fast, reliable hard constraint satisfaction with orders-of-magnitude training speedup.

Panagiotis D. Grontas, Antonio Terpin, Efe C. Balta et al.

Enhancing Multimodal LLMs with external tools across four key dimensions.

Wenbin An, Jiahao Nie, Yaqiang Wu et al.

ProxyRL-FRS combines ProxyNCF and reinforcement learning for efficient client selection, boosting federated recommendation accuracy.

Liang Qu, Jianxin Li, Wei Yuan et al.

Employing Mistral 7B and mT5 models, this study advances Czech text summarization, establishing new benchmarks for modern and historical documents.

Václav Tran, Jakub Šmíd, Jiří Martínek et al.

Echo-4o leverages GPT-4o synthetic images to enhance image generation, achieving significant performance improvements across benchmarks.

Junyan Ye, Dongzhi Jiang, Zihao Wang et al.

Proposes Noise Hypernetwork to learn reward-biased noise modulation, reducing inference costs while maintaining quality in diffusion models.

Luca Eyring, Shyamgopal Karthik, Alexey Dosovitskiy et al.

Proposed STREAM standard enhances transparency in ChemBio model evaluation reports, developed with 23 experts.

Tegan McCaslin, Jide Alaga, Samira Nedungadi et al.

Introduces non-asymptotic convergence bounds for conditional diffusion models using Wasserstein distance, integrating pre-trained functions for precise distribution approximation.

Mengze Li

Proposed M3-Agent with entity-centric multimodal long-term memory, outperforming baselines by 6-8% on long-video QA benchmarks.

Lin Long, Yichen He, Wentao Ye et al.

CitySeg uses local-global cross-attention and hierarchical classification to achieve open-vocabulary semantic segmentation and zero-shot inference for city-scale point clouds.

Jialei Xu, Zizhuang Wei, Weikang You et al.

OpenCUA leverages cross-OS human demonstration data and reflective long Chain-of-Thought reasoning to achieve 45% success rate, setting new open-source SOTA.

Xinyuan Wang, Bowen Wang, Dunjie Lu et al.