Fourier series-based tampering synthesis (FSTS) models invisible tampering parameters, significantly improving real-world forgery localization generalization.

Zeqin Yu, Haotao Xie, Jian Zhang et al.

PCRS-TKA employs tree-structured knowledge and PLMs, achieving 19.70% MRR@10 improvement over baselines.

Yongwen Ren, Chao Wang, Peng Du et al.

ReaSon employs causal information bottleneck and reinforcement learning to select keyframes, significantly improving video reasoning accuracy under limited frame budgets.

Yuan Zhou, Litao Hua, Shilong Jin et al.

VISAGNN introduces a dynamic staleness-aware mechanism, significantly improving large-scale GNN training efficiency and accuracy.

Rui Xue

Energy sparse grids, Glynn symmetrization, and ReLU networks achieve O(m^-1) approximation with only polynomial dimension prefactors.

Yulong Lu, Tong Mao, Jinchao Xu et al.

LLMLagBench uses PELT change-point detection to identify training data cutoffs in LLMs, revealing many models' knowledge ends earlier than declared.

Piotr Pęzik, Konrad Kaczyński, Maria Szymańska et al.

BudgetLeak exploits generation budget side channel for membership inference in RAG systems, achieving 98.2% accuracy.

Hao Li, Jiajun He, Guangshuo Wang et al.

GCAgent employs structured schematic and narrative memory, boosting long-video understanding by 23.5% accuracy, using a multi-stage perception-action-reflection cycle.

Jeong Hun Yeo, Sangyun Chung, Sungjune Park et al.

CPIP creates cost-aware stochastic policies via Boltzmann–Gibbs couplings and stabilizes evaluation with EIF-based one-step estimation.

Johan de Aguas

Introduces GAD, an adversarial framework for black-box LLM distillation, with Qwen2.5-14B approaching GPT-5-Chat performance.

Tianzhu Ye, Li Dong, Zewen Chi et al.

Proposes LongComp with scene factorization to enhance zero-shot generalization in autonomous driving trajectory prediction, reducing OOD gap to 2.8%.

Benjamin Stoler, Jonathan Francis, Jean Oh

MonkeyOCR v1.5 achieves robust document parsing via visual consistency RL and a two-stage pipeline, improving OmniDocBench performance by 2.34%.

Jiarui Zhang, Yuliang Liu, Zijun Wu et al.

ADI-20 dataset expands ADI-17 for Arabic Dialect Identification using ECAPA-TDNN and Whisper models.

Haroun Elleuch, Salima Mdhaffar, Yannick Estève et al.

Unified randomized batch Kaczmarz framework with scale-invariant linear convergence guarantees.

Dong-Yue Xie, Xi Yang

InTRO employs token-level exploration and self-feedback via KL divergence, boosting reasoning accuracy by up to 20% and producing more concise rationales.

Mingye Zhu, Yi Liu, Zheren Fu et al.

MoFa unifies multi-dimensional optimization and fault tolerance models, achieving <5% prediction error for large-scale LLM pretraining performance.

Lu Zhao, Rong Shi, Shaoqing Zhang et al.

AHA! uses 3D Gaussian Splatting for animating humans in diverse scenes, enhancing geometric consistency and free-viewpoint rendering.

Aymen Mir, Jian Wang, Riza Alp Guler et al.

C$^3$TG achieves multi-dimensional text generation with conflict-aware control, significantly improving attribute accuracy.

Yu Li, Zhe Yang, Yi Huang et al.

VeM generates music aligned with video semantics, timing, and rhythm, enhancing audiovisual experience.

Xinyi Tong, Yiran Zhu, Jishang Chen et al.

HardFlow reformulates hard-constrained sampling as trajectory optimization using optimal control, ensuring terminal constraints efficiently.

Zeyang Li, Kaveh Alim, Navid Azizan