UP-NRPA integrates user portraits with nested rollouts for dynamic strategy planning in goal-oriented dialogues, achieving a 56.41% improvement in negotiation SL.

Hui Wang, Fafa Zhang, Meng Liu et al.

AutoSOTA automates AI model optimization using a multi-agent architecture, discovering 105 new SOTA models in 5 hours per paper.

Yu Li, Chenyang Shao, Xinyang Liu et al.

Proposes a five-dimensional auditability framework, emphasizing that accountability depends on system auditability.

Yi Nian, Aojie Yuan, Haiyue Zhang et al.

MO-RiskVAE enhances survival risk prediction in multiple myeloma by tuning latent regularization and structure, achieving higher C-index scores.

Zixuan Chen, Heng Zhang, YuPeng Qin et al.

Combining GPT-4-based semi-structured interviews with interactive visualization enhances procedural legitimacy and trust in large-scale collective decisions.

Suyash Fulay, Prerna Ravi, Emily Kubin et al.

Proposes a consequence-sensitive support compression method in belief arbitration, balancing information retention and resource costs for robust decision-making.

Mark Walsh

Vero is an open RL method for visual reasoning, using the Vero-600K dataset to enhance performance.

Gabriel Sarch, Linrong Cai, Qunzhong Wang et al.

RAR combines retrieval augmentation and reinforcement learning to improve recommendation performance and factuality, outperforming baselines on movie recommendation benchmarks.

Zhenrui Yue, Honglei Zhuang, Zhen Qin et al.

ClawArena evaluates AI agents in evolving info environments, focusing on multi-source conflict reasoning, belief revision, and implicit personalization, across 12 scenarios with 337 rounds.

Haonian Ji, Kaiwen Xiong, Siwei Han et al.

Proposed AAC algorithm uses action entropy to dynamically adjust chunk size, improving robotic task success rates by 2.3%.

Yuanchang Liang, Xiaobo Wang, Kai Wang et al.

A model-based full-body dance generation and control framework combining MoCap, QP, TO, and MPC achieves dynamic stability and expressive motion in humanoid robots.

Shibowen Zhang, Jiayang Wu, Guannan Liu et al.

SODA introduces semi on-policy black-box distillation, achieving 10× faster training with comparable or better performance.

Xiwen Chen, Jingjing Wang, Wenhui Zhu et al.

An end-to-end framework combining natural language reasoning and formal verification to automate research-level mathematical proofs, demonstrated on open problems with minimal human input.

Haocheng Ju, Guoxiong Gao, Jiedong Jiang et al.

CountsDiff models natural number distributions with a novel p(t) schedule and non-monotonic reverse dynamics, excelling in image and scRNA-seq data imputation.

Renzo G. Soatto, Anders Hoel, Greycen Ren et al.

Proposes a semiparametric efficiency-based debiased machine learning framework for valid conformal prediction intervals under runtime confounding.

Keith Barnatchez, Kevin P. Josey, Rachel C. Nethery et al.

This paper surveys methods for learning robotic manipulation interfaces from video, proposing three types: direct video-action policies, latent-action methods, explicit visual interfaces.

Linfang Zheng, Zikai Ouyang, Chen Wang et al.

SymphoMotion jointly controls camera trajectories and object dynamics, achieving coherent video generation with improved fidelity and spatial consistency.

Guiyu Zhang, Yabo Chen, Xunzhi Xiang et al.

SMTPO integrates multi-task fine-tuning and reinforcement learning to optimize multi-turn user preferences, significantly boosting LLM-based conversational recommendation accuracy.

Xingyuan Xiang, Xiangchen Pan, Wei Wei

Proposes Sim2Real-AD, a modular framework combining GOB, PAM, TPT, for zero-shot transfer of VLM-guided RL policies to real vehicles, validated on Ford E-Transit.

Zilin Huang, Zhengyang Wan, Zihao Sheng et al.

Hierarchical Planning with Latent World Models (HWM) enables zero-shot long-horizon visual control, achieving 70% success on real robot tasks, with 3× less computation.

Wancong Zhang, Basile Terver, Artem Zholus et al.