LongVideo-R1 employs hierarchical reasoning and goal-directed navigation, reducing computational costs while maintaining high QA accuracy on long videos.

Jihao Qiu, Lingxi Xie, Xinyue Huo et al.

SibylSense adapts rubric generation via memory tuning and adversarial probing, enhancing RL performance.

Yifei Xu, Guilherme Potje, Shivam Shandilya et al.

Proposes a wavelet-based primal method for causal partial identification via smooth densities, establishing asymptotic normality for quadratic costs.

Sirui Lin, Zijun Gao, Jose Blanchet et al.

RB-VLA model excels in long-horizon tasks, achieving a 52.5% success rate improvement.

Vaidehi Bagaria, Bijo Sebastian, Nirav Kumar Patel

Proposes a three-tiered codified context infrastructure supporting large-scale multi-agent software development.

Aristidis Vasilopoulos

SimLBR employs Latent Blending Regularization to define tight decision boundaries around real images, achieving up to +24.85% accuracy and +69.62% recall, with superior cross-generator generalization.

Aayush Dhakal, Subash Khanal, Srikumar Sastry et al.

Proposes a smooth, efficient, vectorizable contact manifold generation framework combining analytical SDF primitives and novel edge-edge collision routines.

Onur Beker, Andreas René Geist, Anselm Paulus et al.

MeanFuser uses Gaussian Mixture Noise and MeanFlow for one-step multi-modal trajectory generation, boosting efficiency and robustness in autonomous driving.

Junli Wang, Yinan Zheng, Xueyi Liu et al.

SongEcho generates cover songs using Instance-Adaptive Linear Modulation, reducing parameters by 70%.

Sifei Li, Yang Li, Zizhou Wang et al.

VCDF framework enhances robustness of time series causal discovery by stability validation across data blocks, improving VAR-LiNGAM's F1 score by ~0.1.

Gene Yu, Ce Guo, Wayne Luk

Interval-based counterfactual explanations improve AI understanding and trust, with significant experimental results.

Tabea E. Röber, Paul Festor, Rob Goedhart et al.

JavisDiT++ achieves high-quality audio-video generation using MS-MoE and TA-RoPE, surpassing existing methods.

Kai Liu, Yanhao Zheng, Kai Wang et al.

Proposes a primal-dual constrained diffusion model for realistic inorganic defect structures, outperforming existing methods with lower RMSD and forces.

Jingyi Cui, Jacob K. Christopher, Ankita Biswas et al.

SymPL framework significantly enhances spatial reasoning in vision-language models, especially for allocentric perspectives.

Jaeyun Jang, Seunghui Shin, Taeho Park et al.

UniMatch achieves cross-category 3D shape matching via coarse-to-fine language guidance, significantly improving matching accuracy.

Qinfeng Xiao, Guofeng Mei, Bo Yang et al.

Proposes a table-based quantifier elimination method to enhance SAT and ASP solver performance.

Pierre Carbonnelle

Yor-Sarc is the first gold-standard dataset for sarcasm detection in Yorùbá, with 436 annotated instances and a Fleiss' κ of 0.766.

Toheeb Aduramomi Jimoh, Tabea De Wille, Nikola S. Nikolov

SafeDrive integrates sparse world modeling with fine-grained safety reasoning, achieving a PDMS of 91.6% and collision rate of 0.5% in autonomous driving.

Jungho Kim, Jiyong Oh, Seunghoon Yu et al.

Evaluating task complexity via random policies reveals contradictions in PIC and POIC metrics.

Reabetswe M. Nkhumise, Mohamed S. Talamali, Aditya Gilra

L2G-Net employs Cauchy decomposition to enable efficient spectral graph transforms, capturing long-range dependencies with quadratic complexity, outperforming traditional full eigendecomposition.

Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega