Transformer-enhanced PPO optimizes MEC collaboration for LLM inference, boosting task completion by 15%.

Ngoc Hung Nguyen, Bjorn Landfeldt

HPFA uses hypergraphs and paired trajectories to efficiently localize LLM reasoning failures, achieving 64.6% accuracy.

Runchuan Zhu, Hongbin Lai, Bowen Jiang et al.

ChunkVAE enables efficient 3D modeling via local chunk compression and stitching, scaling from 512³ to 1536³ resolution.

Kaiyi Zhang, Zhihao Liang, Haolin Liu et al.

BIP! Ranker is a Spark-based open-source library for large-scale citation impact metrics, supporting multidimensional scholarly impact assessment.

Ilias Kanellos, Serafeim Chatzopoulos, Thanasis Vergoulis

AdaThinkV uses adaptive reinforcement learning to optimize token usage, achieving 40.79% accuracy with 22.7% fewer tokens in video reasoning.

Jingqi Tian, Haoji Zhang, Lin Chen et al.

SpatioLM enhances vision-language models' spatial reasoning using a plug-and-play module, achieving 71.6 on VSI-Bench without extra 3D inputs.

Jing Wu, Jianhua Wu, Jiayi Guan et al.

Proposes PCSD, leveraging local persistent teacher signals to improve self-distillation in RL, achieving +15.6% success rate on ALFWorld.

Chunji Lv, Yangguang Wei, Junlin Liu et al.

Teleopit employs VR-based full-body, hand, and viewpoint mapping, achieving 95% task success on humanoid robots.

Bingqian Wu, Zicheng Xu, Xianghui Fan et al.

PartMat employs a single global latent to achieve efficient, material-aware 3D part decomposition, surpassing existing methods in accuracy and scalability.

Guangming Fu, Jin Song, Yiyun Fei et al.

SearchMaster improves search agent accuracy from 38.19% to 51.52% through self-play.

Wentao Tan, Qiong Cao, Jiaqi Wang et al.

Proposed CoNav-UAV models dual-altitude UAV cooperation as a Stackelberg game, achieving up to 30.8 success rate improvement.

Junru Song, Wenhao Zhang, Yang Yang et al.

LiveLight enables real-time video relighting with interactive 3D lighting control, significantly enhancing user experience.

Yue Ma, Jiangming Wang, Yucheng Wang et al.

SPEAR enhances community search with selection-aware adaptive rewriting, boosting semantic similarity by 18.2%.

Wenbin Wu, Yuzhong Wu, Yufan Xu et al.

DAPD significantly improves privilege illusion by dual-path and dual-source anchoring, with an average gain of 2.00 points.

Jianyu Wu, Yizhou Wang, Encheng Su et al.

Proposes MODE algorithm to optimize mutual direct effects in reciprocal matching, boosting match counts by 20%.

Yoji Tomita

G-Skin leverages 2D generative priors to learn skeleton binding for 3D Gaussian representations, addressing data scarcity with high-fidelity animation.

Yuxin Yao, Kendong Liu, Shiqi Zhou et al.

MeanFlow achieves unified RAW restoration under extreme low-light and motion blur, improving PSNR by up to 7.42 dB.

Zepu Wang, Jingze Liang, Weijie Xiao et al.

Proposes LIA-MTR, a linear O(N) cross-modal bridge with multi-timescale retention, enabling infinite-context vision-language processing.

Ashfak Yeafi, Mehedi Hasan, Md Khairul Islam

Introduces Parametrized Stochastic Circuits (PSCs) framework with JAX-based torx for stochastic dynamics optimization.

Guillaume Verdon, Leo Tyrpak, Owen Lockwood et al.

Proposes Humanoid-PoseNet and Humanoid-ActionNet for learning construction tasks from worker demonstrations, achieving 82.45mm MPJPE accuracy.

Yanxi Liu, Yizhi Liu