4DAnyone uses skeleton-conditioned diffusion with RCP and TCR to generate consistent multi-view 4D human videos from monocular input.

Yudong Jin, Tao Xie, Qihang Zhang et al.

G-CARL employs retrieval-grounded claim verification and checklist-aligned reinforcement learning to enhance medical report interpretation accuracy and patient-centricity.

Shiao Xie, Siyu Chen, Jianwei Lv et al.

Proposes TCPα, a margin-controlled confidence target ensuring complete separation between correct and incorrect predictions, improving failure prediction in MIR.

Parampreet Singh, Anushka Singh, Sumit Kumar et al.

Proposed a multi-agent framework integrating conversational data collection, structured processing, and large language model prediction for weather-sensitive travel behavior, achieving up to 71.5% accuracy.

Narges Ahmadi, Yubo Jiao, Jônatas Augusto Manzolli et al.

AI4AI-Bench evaluates LLM agents' recursive self-improvement in training algorithms; mean score 0.166, top 0.250, across 10 algorithm families.

Yizhe Chi, Wenyi Li, Deyao Hong et al.

Inter-X++ uses hybrid motion capture to create 11,388 high-fidelity human interaction sequences, establishing a unified benchmark for perception and generation tasks.

Liang Xu, Chengqun Yang, Zili Lin et al.

DreamHand leverages pretrained video diffusion models as geometry encoders for occlusion-robust 3D hand tracking, outperforming state-of-the-art by 30-40%.

Yufei Liu, Xixi Wang, Hao Li et al.

CalcSeg employs confidence-aware semi-supervised curriculum learning with 3D latent context to improve myocardial scar segmentation from single-stack LGE-CMR, achieving a Dice of 0.677.

Nivetha Jayakumar, Hannah Kim, Amit R. Patel et al.

Proposes physical-support confidence sets for highly coherent dictionaries, quantifying uncertainty and achieving optimal physical resolution with AEB algorithm.

Guan-Ju Peng

Introduces null-model based exact tests and multi-criteria trajectory analysis to reliably measure genuine self-improvement in language models, avoiding measurement artifacts.

Cheng Xu, Nan Yan, Liming Chen et al.

Using PCMCI+ on 105 HSAT datasets, this study uncovers dynamic causal structures of sleep-disordered breathing, highlighting sex and age differences.

Ranveer Singh, Saurabh Mathur, Pranuthi Tenali et al.

Joint visual-trajectory model predicts future surgical scenes and instrument paths, improving long-horizon forecasting with chunked autoregressive strategy.

Weiliang Huang, Huanrong Liu, Bob Zhang et al.

Proposes IAR three-stage framework for retrieval-free document knowledge internalization, boosting domain QA and general skills.

Qian Kou, Xiaofeng Shi, Xiaosong Qiu et al.

This study compares task-level and subtask-level skill induction, finding subtask and text-format skills transfer more reliably, and introduces a skill utility score.

Yiyang Feng, Biddut Sarker Bijoy, Niranjan Balasubramanian et al.

Using XGBoost with first 5-minute trading data, predict Solana memecoin rug pulls within 1 hour.

Jianghai Li, Pavel Kuznetsov, Yury Yanovich et al.

FigmaTrace enhances VLMs in design tasks using a design phase conversion method.

Darshan Deshpande, Yoshinari Fujinuma, Martyna Markiewicz et al.

Proposes a transfer learning framework using deep ReLU networks for nonparametric regression, achieving near-minimax convergence rates in high-dimensional settings.

Junpeng Ren, Carlos Misael Madrid Padilla, Yanzhen Chen et al.

Proposes Video2DoorTraversal, reconstructing instance-aligned, simulation-ready doors from a single RGB video, achieving 96.57% success in real-world door traversal.

Xincheng Tang, Yiji Chen, Youhan Xie et al.

Daedalus-150M employs a convolution-attention hybrid with 6 full attention and 12 convolution layers, trained on 59.9B tokens, outperforming similar models in quality and inference speed.

Christos Koutsiaris

Proposes a deterministic algorithm for exact RLCT computation of 2D polynomial models, improving model selection accuracy.

Grégoire Sergeant-Perthuis, Elias Tsigaridas, Jules Tsukahara