DriveMVS leverages sparse LiDAR as geometric priors, fuses multi-source cues, and employs spatio-temporal decoding to achieve high-accuracy, consistent depth estimation for autonomous driving.

Qihao Sun, Jiarun Liu, Ziqian Ni et al.

InfinityStory combines world-consistent generation and multi-subject transitions, reaching VBench scores of 88.94 and 82.11.

Mohamed Elmoghany, Liangbing Zhao, Xiaoqian Shen et al.

SafeCRS employs Safe-SFT and Safe-GDPO to achieve personalized safety alignment, reducing violations by 96.5% while maintaining recommendation quality.

Haochang Hao, Yifan Xu, Xinzhuo Li et al.

Proposes PhyPrompt, an RL-based two-stage prompt refinement framework, achieving 40.8% joint success with 7B parameters.

Shang Wu, Chenwei Xu, Zhuofan Xia et al.

BeyondSWE benchmark evaluates code agents on cross-repository, domain-specific, dependency migration, and document generation tasks; top model scores 56.65, still far from saturation.

Guoxin Chen, Fanzhe Meng, Jiale Zhao et al.

MoD-DPO reduces cross-modal hallucinations via modality decoupling, boosting accuracy to 88.19%.

Ashutosh Chaubey, Jiacheng Pang, Mohammad Soleymani

Distinguishing acoustic and expectation-related ANN representations enhances EEG-based music identification accuracy.

Shogo Noguchi, Taketo Akama, Tai Nakamura et al.

Proposes RL3DEdit, leveraging VGGT rewards in reinforcement learning for multi-view consistent 3D scene editing, achieving high quality and efficiency.

Jiyuan Wang, Chunyu Lin, Lei Sun et al.

This paper systematically analyzes limitations and complementarities of chunk-level cache (CLC) strategies, proposing a combined approach to improve accuracy.

Samuel Cestola, Tianxiang Xia, Zheng Weiyan et al.

HRL4PFG uses hierarchical reinforcement learning to enhance item-side fairness in recommender systems, significantly boosting user interaction rewards.

Chongjun Xia, Xiaoyu Shi, Hong Xie et al.

Retrievit combines Transformers and SSMs for efficient in-context retrieval, enhancing data efficiency.

Georgios Pantazopoulos, Malvina Nikandrou, Ioannis Konstas et al.

Proposes BrandFusion, a multi-agent framework for seamless brand embedding in text-to-video, improving recognizability and naturalness.

Zihao Zhu, Ruotong Wang, Siwei Lyu et al.

ITO enhances image-text representation via multiple alignment and training-time fusion, surpassing existing baselines.

Hanpeng Liu, Yaqian Li, Zidan Wang et al.

EvoSkill employs iterative failure analysis to automatically discover and refine skills in multi-agent systems, achieving a 7.3% to 12.1% accuracy boost across benchmarks.

Salaheddin Alzubi, Noah Provenzano, Jaydon Bingham et al.

Proposes ADR-VINS, a tightly-coupled monocular visual-inertial filter using pixel reprojection errors, supporting only two corners, achieving 0.143m translation error.

Maulana Bisyir Azhari, Donghun Han, Sung Jun Park et al.

Conformal Policy Control calibrates likelihood-ratio clipping to explore with finite-sample risk control.

Drew Prinster, Clara Fannjiang, Ji Won Park et al.

Strategy-Guided Exploration (SGE) enhances RL in LLMs by generating high-level natural language strategies, improving exploration and task success rates.

Andrew Szot, Michael Kirchhof, Omar Attia et al.

LAD-Drive bridges language and trajectory with action-aware diffusion transformers, improving Driving Score by 59%.

Fabian Schmidt, Karol Fedurko, Markus Enzweiler et al.

Proposed a tensor factorization-based evaluation method combining autorater data and limited human labels for fine-grained generative model assessments.

Felipe Maia Polo, Aida Nematzadeh, Virginia Aglietti et al.

Modular memory combines IWL and ICL to solve forgetting in continual learning.

Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov et al.