DualCoT-VLA enhances vision-language-action models with parallel reasoning for complex tasks, achieving state-of-the-art performance.

Zhide Zhong, Junfeng Li, Junjie He et al.

3D-Layout-R1 achieves language-guided spatial layout editing via scene graph reasoning, with a 15% IoU increase and 25% reduction in center-distance error.

Haoyu Zhen, Xiaolong Li, Yilin Zhao et al.

The study reveals dual mechanisms of spatial variable binding in vision-language models, enhancing performance on the COCO dataset.

Kelly Cui, Nikhil Prakash, Shoval Messica et al.

Scaling DoRA achieves high-rank adaptation via factored norms and fused kernels, significantly reducing memory usage and enhancing speed.

Alexandra Zelenin, Alexandra Zhuravlyova

TiCo method significantly enhances time control in dialogue models using Spoken Time Markers, reducing MAE to 4.54 seconds.

Kai-Wei Chang, Wei-Chih Chen, En-Pei Hu et al.

DexDrummer combines trajectory planning and residual RL, achieving an F1 score of 1.0.

Hung-Chieh Fang, Amber Xie, Jennifer Grannen et al.

MemDLM embeds a simulated denoising process into training via bi-level optimization, enhancing DLM training efficiency and long-context understanding.

Zehua Pei, Hui-Ling Zhen, Weizhe Lin et al.

SPA method uses carefully designed prompts to generate large-scale synthetic data for effective knowledge injection.

Kexian Tang, Jiani Wang, Shaowen Wang et al.

NMR framework addresses humanoid motion retargeting via dynamic mapping, significantly reducing joint jumps and self-collisions.

Qingrui Zhao, Kaiyue Yang, Xiyu Wang et al.

P-Flow employs test-time prompt optimization with VLMs to customize dynamic visual effects without model training, achieving high fidelity and diversity.

Rui Zhao, Mike Zheng Shou

GeoFusion-CAD extends long-sequence CAD generation via geometric state space, enhancing accuracy for 240-step commands.

Xiaolei Zhou, Chuangjie Fang, Jie Wu et al.

Proposes Adaptive Video Distillation with adaptive regression and temporal regularization, enabling stable few-step high-quality video synthesis.

Yuyang You, Yongzhi Li, Jiahui Li et al.

Proposes an image-conditioned RL framework for online VO parameter tuning, achieving 3x longer feature tracks and 3x lower computation.

Simone Nascivera, Leonard Bauersfeld, Jeff Delaune et al.

TableLong method enhances long-context reasoning with table data, achieving an average improvement of 8.24%.

Huaibing Xie, Guoliang Zhao, Yang Liu et al.

WinDiNet uses pretrained video models to simulate urban wind flows rapidly, optimizing pedestrian comfort with 112-frame rollouts in under a second.

Janne Perini, Rafael Bischof, Moab Arar et al.

SqueezeComposer uses temporal speed-up and diffusion models to efficiently generate high-quality long-form music.

Jianyi Chen, Rongxiu Zhong, Shilei Zhang et al.

LongCat-Flash-Prover enhances Lean4 formal reasoning via tool-integrated RL, achieving 97.1% pass rate on MiniF2F-Test.

Jianing Wang, Jianfei Zhang, Qi Guo et al.

VARS introduces dual vectors and weak rewards for online user preference learning, improving multi-session interaction efficiency by 3.2% success over baselines.

Yuren Hao, Shuhaib Mehri, ChengXiang Zhai et al.

PUPPET framework predicts LLM-driven belief shifts with r=0.3-0.5, revealing systematic biases.

Jocelyn Shen, Amina Luvsanchultem, Jessica Kim et al.

Proposes Spectral-Sphere-Constrained Hyper-Connections (sHC), overcoming Birkhoff polytope limitations to enhance expressivity and stability.

Zhaoyi Liu, Haichuan Zhang, Ang Li