JointDiT employs diffusion transformers for RGB-depth joint modeling, enabling high-fidelity joint generation and accurate depth estimation.

Kwon Byung-Ki, Qi Dai, Lee Hyoseok et al.

This survey analyzes how physics simulators influence robotic navigation and manipulation, focusing on physical properties affecting sim-to-real transfer.

Lik Hang Kenny Wong, Xueyang Kang, Kaixin Bai et al.

Common3D employs self-supervised learning to build category-agnostic 3D deformable models from videos, improving pose and correspondence estimation.

Leonhard Sommer, Olaf Dünkel, Christian Theobalt et al.

LongFuncEval measures long context models' function call effectiveness, with 7%-85% performance drop.

Kiran Kate, Tejaswini Pedapati, Kinjal Basu et al.

ImaginateAR combines scene understanding, 3D generation, and LLMs for speech-driven outdoor AR authoring, achieving 30% faster 3D generation.

Jaewook Lee, Filippo Aleotti, Diego Mazala et al.

Reinforcement learning enhances reasoning in multimodal large language models using value-model-free and value-model-based methods.

Guanghao Zhou, Panjia Qiu, Cen Chen et al.

CMT: Boundary-representation-based multimodal cascade MAR, improves coverage by 10.68%, supports complex CAD generation.

Jianyu Wu, Yizhou Wang, Xiangyu Yue et al.

OGPIT method optimizes high-variance stochastic functions using Gaussian processes and trust-region framework, enhancing efficiency.

Mickael Binois, Jeffrey Larson

Combining physics-based models with neural networks, this study encodes cardiac geometric variability into surrogate models predicting activation maps with an average MSE of 0.0034.

Elena Martinez, Beatrice Moscoloni, Matteo Salvador et al.

CarbonCall dynamically selects tools and adjusts model precision based on real-time carbon intensity, reducing emissions by up to 52% while maintaining performance.

Varatheepan Paramanayakam, Andreas Karatzas, Iraklis Anagnostopoulos et al.

DRO: Doppler-aware direct radar odometry using SE(2) optimization and Doppler velocity constraints, achieving 0.18% relative translation error.

Cedric Le Gentil, Leonardo Brizi, Daniil Lisus et al.

AutoNuggetizer automatically extracts atomic facts from LLM responses, correlating strongly with human preferences (p<1e-24).

Sahel Sharifymoghaddam, Shivani Upadhyay, Nandan Thakur et al.

RepText employs a copying mechanism within a diffusion framework to accurately replicate multilingual visual text without understanding, achieving 85.4% accuracy on ICDAR.

Haofan Wang, Yujia Xu, Yimeng Li et al.

ARTEMIS couples autoregression and MoE to reach 87.0 PDMS and 83.1 EPDMS on NAVSIM.

Renju Feng, Ning Xi, Duanfeng Chu et al.

DISCO combines hypernetworks with neural ODEs for multi-physics prediction, learning evolution operators from short trajectories with high accuracy.

Rudy Morel, Jiequn Han, Edouard Oyallon

BrowseComp-ZH benchmarks Chinese LLM web browsing with 289 multi-hop questions; most models score below 20%, best is 42.9%.

Peilin Zhou, Bruce Leon, Xiang Ying et al.

Proposes a framework modeling oversight as a capability-mismatch game using Elo scores, validated on multiple oversight scenarios, deriving scaling laws for success probabilities.

Joshua Engels, David D. Baek, Subhash Kantamneni et al.

Sky-Drive combines CARLA, RPC, digital twins, and bidirectional human-AI mentoring; the paper reports no quantitative performance gains.

Zilin Huang, Zihao Sheng, Zhengyang Wan et al.

The 4th Monocular Depth Estimation Challenge improved 3D F-Score to 23.05% using affine-invariant predictions.

Anton Obukhov, Matteo Poggi, Fabio Tosi et al.

StarPO and StarPO-S expose the Echo Trap in multi-turn agent RL; uncertainty filtering extends FrozenLake-PPO stability from 100 to 140 steps.

Zihan Wang, Kangrui Wang, Qineng Wang et al.