ThoughtTrace collects user-reported thoughts during multi-turn conversations, improving user behavior prediction (+41.7%) and model alignment (+25.6%) in large-scale datasets.

Chuanyang Jin, Binze Li, Haopeng Xie et al.

CogOmniControl integrates CogVLM and CogOmniDiT for intent-driven video generation, outperforming existing models.

Hongji Yang, Songlian Li, Yucheng Zhou et al.

StitchVM efficiently transfers pretrained pixel reward models into noisy latent space, boosting speed and robustness.

Hyojun Go, Hyungjin Chung, Prune Truong et al.

Quant.npu improves mobile NPU inference efficiency via fully static quantization, reducing latency by 15.1%.

Jinghe Zhang, Daliang Xu, Chenghua Wang et al.

MDCNS framework enhances sequential recommendation via multi-source negative sampling, showing superior experimental performance.

Yuanzi Li, Lingjie Wang, Jingyu Zhao et al.

CaptchaMind achieves 82.9% success rate using reinforcement learning with explicit reasoning supervision, surpassing existing methods.

Pengcheng Wang, Haoxiang Liu, Yang Dai et al.

BrepForge factorizes B-rep synthesis into wireframe serialization and boundary-conditioned surface instantiation, ensuring topological integrity and geometric accuracy.

Jing Li, Yihang Fu, Falai Chen

VASA surpasses SAM3 Agent by 14-25% in open ad-hoc segmentation.

Zilin Wang, Stella X. Yu

CompoSE enables part-aware 3D shape synthesis and editing, outperforming existing methods significantly.

Habib Slim, Shariq Farooq Bhat, Mohamed Elhoseiny et al.

OmniISR unifies centralized and federated learning via intermediate supervision, reducing performance gap by 22.60%.

Wei-Bin Kou, Guangxu Zhu, Ming Tang et al.

CVaR variants in Pandora's box and prophet inequalities reveal tail risk limitations and structural recovery strategies.

Jingwei Ji

Proposes STRELGen, integrating diffusion models with spatio-temporal logic for targeted safety-critical scenario synthesis.

Lorenzo Bonin, Francesco Giacomarra, Luca Bortolussi et al.

MementoGUI enhances long-horizon GUI agents with learned multimodal memory control, improving task success rates by over 20% on benchmarks.

Ziyun Zeng, Hang Hua, Bocheng Zou et al.

Decoupled semantic-spatial Transformer improves NVS fidelity by separating features, achieving 1.1dB PSNR gain with minimal latency.

Yihang Wu, Yihang Sun, Shaofeng Zhang et al.

StableHand estimates dual-hand motion from egocentric video using quality-aware flow matching, reducing W-MPJPE by 20-25%.

Huajian Zeng, Chaohua Yao, Yuantai Zhang et al.

SkillsVote manages open-source agent skills through lifecycle stages, improving task performance by 2.6% on benchmarks.

Hongyi Liu, Haoyan Yang, Tao Jiang et al.

EPIC constructs preference-aligned compact index, reducing memory by 2404× and improving accuracy by 18.79%, enabling efficient on-device personalization.

Changmin Lee, Jaemin Kim, Taesik Gong

Proposes on-policy self-distillation (OPSD), eliminating external teachers, reducing GPU memory by 50%, and improving performance.

Fangming Cui, Sunan Li, Jiahong Li

Proposes TaskGround framework for full-scene household reasoning, boosting success rates by over 20% and reducing input tokens by 18×.

ZhiYuan Feng, Yu Deng, Ruichuan An et al.

Introduces 4DLidarOpen, a large-scale multi-modal dataset with 4D FMCW lidar velocity data, enhancing dynamic scene understanding.

Kane Qian, Xin Zhao, Yining Shi et al.