RoboTron-Mani integrates multimodal data fusion and 3D perception, surpassing expert models with improved generalization and task performance.

Feng Yan, Fanfan Liu, Liming Zheng et al.

Proposes an econometric framework ensuring valid prediction and estimation with LLMs, emphasizing no training leakage and validation samples.

Jens Ludwig, Sendhil Mullainathan, Ashesh Rambachan

MV-DUSt3R+ reconstructs scenes from sparse views in 2 seconds, significantly improving speed and accuracy.

Zhenggang Tang, Yuchen Fan, Dilin Wang et al.

P3-PO leverages human-prescribed semantic points and vision models to enhance robot policy generalization, achieving 43% overall improvement in real-world tasks.

Mara Levy, Siddhant Haldar, Lerrel Pinto et al.

Proactive T2I agent uses belief graphs and multi-turn questioning to improve alignment, achieving 2x VQAScore over standard methods.

Meera Hahn, Wenjun Zeng, Nithish Kannen et al.

Coconut leverages continuous latent space reasoning to outperform CoT in logical tasks like ProsQA, achieving higher accuracy and efficiency.

Shibo Hao, Sainbayar Sukhbaatar, DiJia Su et al.

Proposes Gated DeltaNet, combining gating and delta rules, significantly enhancing long-sequence task performance.

Songlin Yang, Jan Kautz, Ali Hatamizadeh

Mamba and SSMs have the same computational capabilities as Transformers, unable to solve problems beyond TC0.

Yifang Chen, Xiaoyu Li, Yingyu Liang et al.

This paper systematically reviews LLMs-as-judges, covering functionality, methodologies, applications, meta-evaluation, and limitations, highlighting innovations and challenges.

Haitao Li, Qian Dong, Junjie Chen et al.

SAME employs a state-adaptive Mixture of Experts for multi-task visual navigation, outperforming task-specific models with dynamic expert routing.

Gengze Zhou, Yicong Hong, Zun Wang et al.

UniScene unifies occupancy, video, and LiDAR generation via an occupancy-centric progressive framework.

Bohan Li, Jiazhe Guo, Hongsi Liu et al.

InternVL 2.5 achieves over 70% on MMMU by model, data, and test-time scaling, surpassing previous open-source limits.

Zhe Chen, Weiyun Wang, Yue Cao et al.

TeamCraft builds a Minecraft-based benchmark with 55,000 multimodal multi-agent tasks to evaluate generalization in complex environments.

Qian Long, Zhi Li, Ran Gong et al.

Proposes neural Riemannian PDE solver (NES) for high-dimensional geodesic distance fields, enabling real-time, global path optimization in robotics.

Yiming Li, Jiacheng Qiu, Sylvain Calinon

Proposed ADU-Bench evaluates 16 LALMs across multi-scenario, multi-skill, multi-language, and ambiguity tasks, revealing performance gaps and strengths.

Kuofeng Gao, Shu-Tao Xia, Ke Xu et al.

Integrating energy-efficient techniques and lifecycle assessment reduces LLMs' environmental impact by over 50%.

Aditi Singh, Nirmal Prakashbhai Patel, Abul Ehtesham et al.

REGENT employs retrieval-augmented transformer policies for zero-shot generalization, with 3x fewer parameters and 10x less data, outperforming SOTA in unseen environments.

Kaustubh Sridhar, Souradeep Dutta, Dinesh Jayaraman et al.

NVILA employs a 'scale-then-compress' approach, boosting high-res image and long video processing efficiency, reducing training costs by 1.9-5.1×.

Zhijian Liu, Ligeng Zhu, Baifeng Shi et al.

VisionZip selects high-information visual tokens, reduces redundancy, boosts inference speed by 8x, with performance drop under 5%.

Senqiao Yang, Yukang Chen, Zhuotao Tian et al.

Moto employs Latent Motion Tokens for unsupervised pretraining, boosting robot manipulation success rate to 61.4%.

Yi Chen, Yuying Ge, Weiliang Tang et al.