Proposes a framework for LLM-based social simulation using importance sampling and optimal transport to generate population-aligned persona sets.

Zhengyu Hu, Jianxun Lian, Zheyuan Xiao et al.

The OnlineHOI framework achieves state-of-the-art results in online human-object interaction generation and perception on Core4D and OAKINK2 datasets.

Yihong Ji, Yunze Liu, Yiyao Zhuo et al.

FHIR-AgentBench evaluates LLM performance in EHR QA under HL7 FHIR, highlighting data retrieval and reasoning challenges.

Gyubok Lee, Elea Bach, Eric Yang et al.

Proposes dual spectral encoding and geometric functional maps for unsupervised graph alignment, improving robustness and discriminability.

Maysam Behmanesh, Erkan Turan, Maks Ovsjanikov

InterAct enhances 3D human-object interaction data quality with a unified optimization framework, expanding the dataset to 30.70 hours.

Sirui Xu, Dongting Li, Yucheng Zhang et al.

SMapper introduces an open-hardware, multi-sensor platform integrating LiDAR, cameras, and IMU for high-precision SLAM data collection and benchmarking.

Pedro Miguel Bastos Soares, Ali Tourani, Miguel Fernandez-Cortizas et al.

Dark-ISP enhances low-light object detection by directly processing Bayer RAW images, outperforming existing methods.

Jiasheng Guo, Xin Gao, Yuxiang Yan et al.

RewardDance scales reward models up to 26B parameters, improving visual generation quality and robustness against reward hacking.

Jie Wu, Yu Gao, Zilyu Ye et al.

Proposes CAI ratio for unsupervised LLM evaluation, effectively guiding model selection in dynamic environments.

Cheng Chen, Haiyan Yin, Ivor Tsang

SWE-Mirror uses cross-repository issue mirroring to expand authentic, verifiable datasets, boosting model performance by +21.8% to +46.0%.

Junhao Wang, Daoguang Zan, Shulin Xin et al.

EVDI++ uses event cameras for video deblurring and interpolation, improving video quality.

Chi Zhang, Xiang Zhang, Chenxu Jiang et al.

EASE framework uses LLMs for algorithm generation and optimization, supporting multi-domain applications.

Adam Viktorin, Tomas Kadavy, Jozef Kovac et al.

VIRAL aligns visual representations to enhance multimodal large models' performance on visual tasks, with an average improvement of 9.4%.

Heeji Yoon, Jaewoo Jung, Junwan Kim et al.

Proposes GF-VLA framework combining scene graphs and information theory for dual-arm robot manipulation, achieving over 95% graph accuracy.

Shunlei Li, Longsen Gao, Jiuwen Cao et al.

RaC method enhances robot efficiency and robustness in long-horizon tasks by scaling recovery and correction, reducing data collection time by 10x.

Zheyuan Hu, Robyn Wu, Naveen Enock et al.

DiverValue-Bench evaluates LLMs' alignment with diverse human values, revealing geographic and demographic disparities.

Yao Liang, Dongcheng Zhao, Feifei Zhao et al.

UFC method achieves spatial control in diffusion models with few samples, nearing fully supervised baselines.

Kiet T. Nguyen, Chanhyuk Lee, Donggyun Kim et al.

Astra employs multi-agent LLMs to optimize CUDA kernels, achieving an average speedup of 1.32×.

Anjiang Wei, Tianran Sun, Yogesh Seenichamy et al.

Proposes Wasserstein-based performance prediction and data selection framework for federated models, ensuring privacy and efficiency.

Wenqian Li, Youjia Yang, Ruoxi Jia et al.

PersonaFuse framework enhances human-LLM interactions by activating personality traits, significantly improving emotional intelligence.

Yixuan Tang, Yi Yang, Ahmed Abbasi