LLMoxie platform enhances AI agent performance in scientific software development through a three-tier architecture and RSE-Plugins ecosystem.

Landung Setiawan, Anant Mittal, Cordero Core et al.

EVA-Client provides a unified deployment, debugging, and data collection framework for embodied policies across multiple robot platforms, integrating various real-time inference strategies.

Heqing Yang, Yang Yi, Liyao Wang et al.

EvoPolicyGym benchmarks autonomous policy evolution; GPT-5.5 achieves top performance across 16 RL environments with limited interactions.

Zhilin Wang, Han Song, Runzhe Zhan et al.

HO-HE post-generation curation balances fidelity and diversity, reaching 95% on CIFAR-10 with 300K synthetic images.

Disheng Liu, Tuo Liang, Chaoda Song et al.

Proposed a hybrid dynamic data collection method, significantly enhancing VLA spatial generalization with a 40% success rate increase.

Jincheng Tang, Yilong Zhu, Zhengyuan Xie et al.

Proposes distribution-wise reward with subset-replace strategy for RL fine-tuning, reducing FID from 8.30 to 5.77.

Ruihang Li, Mengde Xu, Shuyang Gu et al.

Bridge-WA enhances robotic action success by predicting scene changes, achieving a 9.7% improvement on VLABench.

Yongjie Bai, Hanting Wang, Mingtong Dai et al.

LongEgoRefer benchmark challenges existing models with long-form egocentric video referring expression comprehension.

Shunya Kato, Taiki Miyanishi, Shuhei Kurita et al.

MAVEN framework enhances long-context reasoning by rewarding dynamic evidence state transitions, improving performance by 3.5% on LongBench v2.

Ya Gao, Pekka Marttinen

PWM-ArtGen uses diffusion-based joint modeling of visual dynamics and kinematic parameters, outperforming baselines with strong zero-shot generalization.

Wentao Zheng, Ancong Wu

ScopeEdit employs a dual-branch scope-aware mechanism with orthogonal low-rank geometry to control knowledge propagation in online multimodal model editing.

Siyuan Li, Youyuan Zhang, Ruitong Liu et al.

PhysMani combines a physics-principled 3D Gaussian world model with a future-aware action policy model to enhance dynamic object manipulation success rates.

Peng Yun, Shouwang Huang, Hao Li et al.

Zeus is a tuning-free foundation model for time series, using multi-scale Transformer and multi-objective masking to excel across tasks.

Yisong Fu, Zezhi Shao, Chengqing Yu et al.

SkillCoach improves agentic skill-use evaluation with self-evolving rubrics, significantly enhancing assessment quality.

Jiayin Zhu, Kelong Mao, Yudong Guo et al.

Koopman operator theory enables global linearization of complex dynamical systems using methods like EDMD.

Igor Mezić, Jorge Cortés, Karl Worthmann et al.

Study finds SDPO accelerates in-domain learning under specific conditions but struggles in cross-domain scenarios.

Meng Wang, Haohan Zhao, Wenzhuo Liu et al.

ReQuest improves long-video QA accuracy through uncertainty-driven keyframe selection.

Minkuk Kim, Suyong Yun, Young Tae Kim et al.

LASER regulates visual attention via grounding and sink suppression rewards, effectively mitigating visual forgetting in LVLMs.

Bowen Yuan, Zijian Wang, Yadan Luo et al.

ICDepth uses In-Context Conditioning and SAND-Attention for video depth estimation, achieving 6-13x data efficiency improvement.

Xuanhua He, Jiaxin Xie, Mingzhe Zheng et al.

Proposes PanoGaussian, combining panoramic trajectories and Gaussian distillation for consistent 4D scene synthesis from monocular videos, even in unseen regions.

Yuankun Yang, Yi Wei, Wenyang Zhou et al.