Proposed OneModel internalizes complex business logic into a single model, reducing latency by 57.2% and increasing IRR from 64.3% to 83.3%.

Chang Liu, Chaoyang Ning, Dayi Jiang et al.

Proposes a hierarchical Bayesian credibility framework using an ODD-similarity kernel for partial pooling across cities.

Doyeon Jang

EgoInfinity is a modular web-scale 4D hand-object interaction engine that automatically extracts high-quality data from internet videos for robot retargeting and learning.

Gaotian Wang, Kejia Ren, Andrew Morgan et al.

MemTrace reveals what final accuracy misses in long-term memory, emphasizing evidence use over retrieval.

Xianxuan Long, Zhikai Chen, Shenglai Zeng et al.

Pareto LoRA improves multimodal model balance by Pareto-optimal gradient integration, achieving 44.9% better image quality.

Xiwen Wei, Mark Nutter, Madhusudhanan Srinivasan et al.

Proposes PDAGENT-BENCH, a 353-task benchmark evaluating LLM/VLMs for holistic VLSI physical design automation.

Qiufeng Li, Rongqian Chen, Quan Cheng et al.

ACE-EGO-0 unifies human and robot data via spatial, structural, and temporal alignment for VLA pretraining, boosting manipulation performance.

Hao Li, Ganlong Zhao, Yufei Liu et al.

Proposes primal-dual inference for constrained diffusion models, enabling sampling from distributions with average constraints with theoretical convergence guarantees.

Samar Hadou, Yigit Berkay Uslu, Alejandro Ribeiro

This study benchmarks 12 LLM pipeline configurations on MetaSyn, revealing a screening bottleneck with a maximum recall of 52.7% despite 90.9% retrieval recall at K=200.

Anzhe Xie, Weihang Su, Yujia Zhou et al.

R2RDreamer enhances 2D manipulation policies' spatial generalization via 3D-aware augmentation and occlusion-aware video completion, achieving significant performance gains with limited demonstrations.

Xiuwei Xu, Haowen Sun, Angyuan Ma et al.

Proposes Qwen-RobotWorld, a language-conditioned video world model using double-stream MMDiT and 8.6M embodied video-text pairs, achieving top performance on multiple benchmarks.

Jie Zhang, Xiaoyue Chen, Anzhe Chen et al.

MeshLoom is a feed-forward non-rigid mesh registration network that reconstructs vertex deformations across sequences within seconds, outperforming state-of-the-art methods.

Jianqi Chen, Jiraphon Yenphraphai, Xiangjun Tang et al.

Integrates Riemannian geometry and deep learning to analyze biological shape variability, improving classification and trajectory modeling.

Gary P. T. Choi, Khanh Dao Duc, Shira Faigenbaum-Golovin et al.

TuneJury is a pairwise preference reward model trained on 17,500 human judgments, achieving 0.7086 accuracy, outperforming non-pseudo-label models for music preference alignment.

Yonghyun Kim, Junwon Lee, Haiwen Xia et al.

Developed a theoretical framework for reranking risk based on DCG variation, validated by experiments on TREC data showing close alignment between predicted and observed deviations.

Debasis Ganguly

Introduced PReLU-TST using PReLU-IPM for higher test power.

Yuha Park, Yongdai Kim

MA-SBI uses side-channel information for calibration-free simulation inference, enhancing accuracy.

Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R. et al.

BinTrack uses trajectory-based binary search to improve open-source spatial QA accuracy by 22.8%.

Dongbin Na, Chanwoo Kim, Soonbin Rho et al.

FaNO improves physical system modeling by decomposing dynamic and persistent responses.

Hao Tang, Yuechen Duan, Jiongyu Zhu et al.

Semantic Flip synthesizes out-of-distribution samples to improve embodied refusal, achieving an F1 of 0.9559 on spatial localization.

Dongbin Na, Chanwoo Kim, Giyun Choi et al.