PhysMoDPO optimizes humanoid motion for physical realism and task performance through preference optimization.

Yangsong Zhang, Anujith Muraleedharan, Rikhat Akizhanov et al.

Using Joint Embedding Predictive Architectures (JEPA) for learning representations in latent space significantly enhances parameter estimation accuracy.

Helen Qu, Rudy Morel, Michael McCabe et al.

Visual-ERM enhances vision-to-code tasks with fine-grained visual rewards, significantly outperforming existing models.

Ziyu Liu, Shengyuan Ding, Xinyu Fang et al.

STEVO-Bench evaluates video world models' ability to evolve state during observation interruptions, revealing limitations.

Ziqi Ma, Mengzhan Liufu, Georgia Gkioxari

NAIT framework selects efficient instruction tuning data via neuron activation patterns, enhancing LLM performance.

Xin Chen, Junchao Wu, Shu Yang et al.

QMatSuite reduces reasoning overhead by 67% and improves accuracy to 3% in AI-driven materials science.

Haonan Huang

Using CWRF, only critical weights are adjusted to enhance privacy while maintaining utility.

Xingli Fang, Jung-Eun Kim

MXNorm reuses MXFP8 block scales for efficient tensor normalization, reducing reduction size by 32x.

Callum McLean, Luke Y. Prince, Alexandre Payot et al.

Using MiniRocket and TSFresh, analyze and cluster Saturn's satellite orbital data to reveal stability and resonance structures.

Eraldo Pereira Marinho, Nelson Callegari Junior, Fabricio Aparecido Breve et al.

Developed a chatbot for maternal health in India using stage-aware triage and hybrid retrieval, achieving 86.7% emergency recall.

Smriti Jha, Vidhi Jain, Jianyu Xu et al.

DiT-IC achieves efficient image compression using a 32x downscaled diffusion transformer, offering 30x faster decoding.

Junqi Shi, Ming Lu, Xingchen Li et al.

PITMonitor detects distributional changes in probability integral transforms using a mixture e-process, providing Type I error control over an unbounded monitoring horizon.

Tristan Farran

ESG-Bench significantly reduces hallucinations in long-context ESG report analysis using task-specific Chain-of-Thought prompting strategies.

Siqi Sun, Ben Peng Wu, Mali Jin et al.

ZO-SAM integrates zero-order optimization to reduce computational costs, enhancing efficiency and robustness in sparse training.

Jie Ji, Gen Li, Kaiyuan Deng et al.

BoSS enhances deep active learning performance by integrating multiple selection strategies, excelling on large-scale datasets.

Denis Huseljic, Paul Hahn, Marek Herde et al.

Proposed a feasibility-enhanced control barrier function method, significantly reducing infeasibility and improving collision avoidance in multi-UAV scenarios.

Qishen Zhong, Junlong Wu, Jian Yang et al.

Qwen2.5-VL excels in spatial reasoning for robot motion with 71.4% zero-shot accuracy.

Wenxi Wu, Jingjing Zhang, Martim Brandão

CRYSTAL benchmark evaluates multimodal reasoning transparency using Match F1 and Ordered Match F1, revealing systematic flaws in existing models.

Wayner Barrios, SouYoung Jin

SldprtNet is a large-scale multimodal dataset with 242,000 industrial parts for semantic-driven CAD modeling.

Ruogu Li, Sikai Li, Yao Mu et al.

Zero-hyperparameter multi-corner analysis using learned priors reduces validation cost by over 10 times.

Wei W. Xing, Kaiqi Huang, Jiazhan Liu et al.