Proposed FPTE framework improves grasp success by planning multiple targets and evaluating post-planning success.

Martin Matak, Mohanraj Devendran Shanthi, Karl Van Wyk et al.

Statistical techniques enhance reliability, control behavior, quantify uncertainty, and guide experiments in generative AI, ensuring safer and more trustworthy outputs.

Edgar Dobriban

Paper2Agent transforms research papers into AI agents, enhancing interactivity and reliability of scientific outputs.

Jiacheng Miao, Joe R. Davis, Yaohui Zhang et al.

RAFFLES uses iterative reasoning to detect faults in LLM systems, achieving 50% accuracy improvement on Who&When dataset.

Chenyang Zhu, Spencer Hong, Jingyu Wu et al.

Grasp-MPC uses a learned value function inside MPPI control, reaching 67.2% simulated and 74.4% overall real-world grasp success.

Jun Yamada, Adithyavairavan Murali, Ajay Mandlekar et al.

Survey of industrial recommender systems highlighting challenges in data scale and real-time requirements.

Kuan Zou, Aixin Sun

Large Language Models enable natural language-driven optimization frameworks, enhancing 6G wireless network management.

Bisheng Wei, Ruihong Jiang, Ruichen Zhang et al.

A Bayesian two-distance AFT model captures Titan GPU failure times via physical and logical spatial random effects.

Jared M. Clark, Jie Min, Yueyao Wang et al.

FlowSeek integrates depth foundation models and motion bases for low-resource, high-accuracy optical flow estimation, outperforming SOTA by 10-15%.

Matteo Poggi, Fabio Tosi

COGITAO framework studies compositionality and generalization in vision with 28 transformations, generating millions of unique tasks.

Yassine Taoudi-Benchekroun, Klim Troyan, Pascal Sager et al.

This study analyzes failure modes in multi-agent debate, revealing models tend to conform and reinforce errors, causing performance decline.

Andrea Wynn, Harsh Satija, Gillian Hadfield

Proposes MM-ITF, a transformer-based multimodal model, achieving 90% accuracy in monocular RGB-based pointing target estimation.

Luca Müller, Hassan Ali, Philipp Allgeuer et al.

Derived fundamental bounds linking confidence and efficiency in transductive conformal prediction, showing exponential growth of prediction sets governed by conditional entropy.

Arash Behboodi, Alvaro H. C. Correia, Fabio Valerio Massoli et al.

This study reveals data uncertainty as a key factor in tabular deep learning, proposing uncertainty-aware feature embeddings for robustness.

Nikolay Kartashev, Ivan Rubachev, Artem Babenko

Proposes MDT-dist, a few-step flow distillation method reducing sampling from 25 to 1-2 steps, enabling real-time 3D generation.

Zanwei Zhou, Taoran Yi, Jiemin Fang et al.

Integrating Transformer and deep reinforcement learning for rapid earthquake disaster crew dispatch, significantly reducing restoration time.

Farshad Amani, Faezeh Ardali, Amin Kargarian

Integrates classical assignment with Gromov-Wasserstein (GW) distances, proposing multi-initialization GW_MultiInit for large-scale quadratic assignment problems (QAP).

Iman Seyedi, Antonio Candelieri, Enza Messina et al.

OneCAT is a decoder-only autoregressive model for unified multimodal understanding, generation, and editing, eliminating external encoders for efficiency.

Han Li, Xinyu Peng, Yaoming Wang et al.

AEnt method improves LLM-RL performance via adaptive entropy control, excelling in math reasoning tasks.

Han Shen

OneSearch: First industrial end-to-end generative framework for e-commerce search, boosting CTR by 1.67% and reducing operational costs by 75.40%.

Ben Chen, Xian Guo, Siyuan Wang et al.