Proposed turning circle-based control barrier function (TC-CBF) integrated with MPC significantly improves collision avoidance for nonholonomic vehicles, reducing unnecessary deceleration by 15%.

Changyu Lee, Kiyong Park, Jinwhan Kim

Introduces VILBench and 73.6K vision-language process reward data, enabling training of a 3B PRM that outperforms baselines by 3.3%.

Haoqin Tu, Weitao Feng, Hardy Chen et al.

LACLRec enhances sequential recommendation using a learnable sequence augmenter and triplet contrastive learning.

Wei Wang, Yujie Lin, Jianli Zhao et al.

DINeMo leverages large pretrained models for pseudo-correspondence, enabling zero-shot 3D pose estimation with 67.3% gap reduction to supervised methods.

Weijie Guo, Guofeng Zhang, Wufei Ma et al.

FLeCS integrates gene networks into coupled ODEs, enabling scalable inference of single-cell transcriptional dynamics with improved interpretability.

Paul Bertin, Joseph D. Viviano, Alejandro Tejada-Lapuerta et al.

AVUT benchmark evaluates audio-centric video understanding, introducing multi-task tasks and a permutation filtering mechanism to prevent text shortcuts.

Yudong Yang, Jimin Zhuang, Guangzhi Sun et al.

Gemma 3 introduces multimodal, 128K tokens long context, and vision understanding, using architecture improvements and distillation, outperforming Gemma 2.

Gemma Team, Aishwarya Kamath, Johan Ferret et al.

AdaptiVocab reduces token usage by over 25% via lightweight vocabulary adaptation, boosting efficiency in low-resource domains.

Itay Nakash, Nitay Calderon, Eyal Ben David et al.

MusiCoT enhances music generation quality through chain-of-musical-thought prompting, surpassing existing models.

Max W. Y. Lam, Yijin Xing, Weiya You et al.

Reinforcement learning optimizes language models for inference time objectives, improving pass@k and voting accuracy by reducing gradient variance.

Yunhao Tang, Kunhao Zheng, Gabriel Synnaeve et al.

Proposes a Plan+Solver multi-agent system with multi-turn query rewriting, achieving 95% query understanding accuracy and 92% task success in office scenarios.

Songtao Sun, Jingyi Li, Yuanfei Dong et al.

ImF uses implicit fingerprints to protect LLMs, achieving a success rate of 90%.

Jiaxuan Wu, Wanli Peng, Hang Fu et al.

OpenFunGraph leverages foundation models to generate functional 3D scene graphs, outperforming Open3DSG and ConceptGraph.

Chenyangguang Zhang, Alexandros Delitzas, Fangjinhua Wang et al.

Proposes an optimization-based multivariate conformal set with minimal volume, ensuring finite-sample coverage.

Sacha Braun, Liviu Aolaritei, Michael I. Jordan et al.

Proposes Frequency Dynamic Convolution (FDConv) that learns diverse frequency responses with minimal parameter increase, boosting dense image prediction tasks.

Linwei Chen, Lin Gu, Liang Li et al.

PhysTwin combines spring-mass physics with generative shape models, reconstructing deformable objects from sparse videos with high fidelity.

Hanxiao Jiang, Hao-Yu Hsu, Kaifeng Zhang et al.

₩ON: First open leaderboard for Korean financial LLMs, evaluating 1,119 submissions.

Guijin Son, Hyunwoo Ko, Haneral Jung et al.

Proposes a lifelong evolutionary swarm control framework combining NEAT and regularization, achieving over 85% task retention across dynamic environments.

Lorenzo Leuzzi, Simon Jones, Sabine Hauert et al.

Survey on LLMs in mathematical reasoning and optimization, focusing on Chain-of-Thought and tool-augmented methods.

Ali Forootani

Proposes a quantitative evaluation to measure semantic residuals in 3D Gaussian Splatting, validated for privacy-preserving mapping scenarios.

Simona Kocour, Assia Benbihi, Aikaterini Adam et al.