Semantic Similarity Rating (SSR) significantly reduces mode collapse in silicon sampling, improving distribution fidelity with minimal parameters.

Oscar Heath, Rohan Alexander

AIx4Soccer integrates football club management and athlete development using PDI framework and Tak Tik marketplace.

Frederico Falconi Costa, Salvador Cesar Costa, Fabricio F. Costa

Forecasts Spiral Jetty's state in 2030/2050 using complexity-signature regression and climate-conditioned diffusion.

Alev Cinbarci, Sean Kalaycioglu

TEA module combined with deep learning improves agricultural VLN success rate to 0.54, reducing navigation error to 2.70m.

Xiaobei Zhao, Xingqi Lyu, Xin Chen et al.

The study reveals benchmark scoring errors for computer-use agents, proposing a four-stage reliability framework with 15.3% incorrect failure verdicts.

Zihan Dong, Zhiyuan Ma, Zekun Wang et al.

ShadowDancer learns unified dynamic representations from video-shadow pairs, enabling precise, label-free action transfer across diverse scenarios.

Jin Cao, Zian Meng, Kaipeng Zhang

TARS learns camera motion at high-noise diffusion steps, reaching 83.18% R-Prec, 72.76% T-Prec, and 10.34° V-MPGE.

Jiwen Liu, Shujuan Li, Xiaohan Li et al.

The study optimizes T count for sparse QROM, achieving bounds of Θ(√sm + √sn).

Tongyang Li, Fengning Ou, Xinzhao Wang et al.

Large-scale evaluation of 194 VLMs shows model size correlates with overall accuracy (ρ=0.68), but not with robustness to multi-attribute bias; data quality is more critical.

Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos

LM-GRASP employs online imitation learning with Transformer to generate instance-specific solutions, outperforming traditional heuristics with 28.4 units improvement on PFSP.

Mohand Mezmaz, Grégoire Danoy

CCFormer integrates cross-field attention with hierarchical sequence compression, boosting recommendation accuracy by 3.57% CTR and 1.71% ad revenue, with 2.21× faster training.

Yunlong Wang, Huizhe Zhang, Haonan Hu et al.

VIG-RL employs reinforcement learning to dynamically search, select, and insert verified images, achieving state-of-the-art multimodal grounding.

Qinhan Yu, Jun Guang, Chong Chen et al.

Flux-OPD uses evolving contexts and reverse KL decomposition to stabilize open-domain distillation, outperforming existing methods with +2-3 score improvements.

Yuran Wang, Zekun Wang, Bohan Zeng et al.

MMLDSum-LLM enhances long-document summarization with visual alignment and keyword awareness, improving cross-modal consistency.

Xianpeng Zhang, Jiahua Yang, Dongyu Chen et al.

SKIMIX integrates multi-agent skill retrieval, anti-dilution routing, and adaptive evolution, boosting open-ended reasoning by 33%.

Jia Luo

Proposed STEREODISCO framework applies semantic differential method to discover and quantify stereotypical axes in LLM internal representations, revealing new bias dimensions beyond prior social psychology research.

Farane Jalali Farahani, Corina Dima, Mojtaba Nayyeri et al.

Proposes an expand-then-compress framework using multi-teacher policy distillation, improving Qwen3-1.7B's reasoning by 2.0%-8.3%.

Songshuo Lu, Zhi Chen, Yaohua Tang

ROCS improves recommendation efficiency by delaying request-candidate interaction, achieving a 3x QPS boost.

Yuxin Chen, Liang Luo, Buyun Zhang et al.

SpatialCLI employs a three-stage framework to internalize spatial perception, boosting VLM reasoning from 29.3% to 84.6% accuracy using tools, surpassing GPT-5.6 Sol.

Yang Zhou, Zixuan Huang, Sunzhu Li et al.

GAMER constructs an Action-Centric Graph with dual-stream TD learning, boosting inference success by 20.81%.

Xu Zheng, Chaohao Lin, Zhuomin Chen et al.