Proposes DocTrace, a hierarchical evidence graph reasoning model for LongDocVQA, achieving 14.4% accuracy improvement and explicit evidence provenance.

Le Xiang, Zhicheng Guan, Hong Chen et al.

SARF fine-tunes only the visual encoder with feature anchoring and attention correction, reducing failure rate from 100% to 14.2%-56.8% against physical attention hijacking.

Jinquan Zhang, Dongfu Yin, Run Yang et al.

Proposes ICO, an iterative context optimization framework, achieving 74.6% success in semantic-shift jailbreaks with high-quality contexts.

Hujian Zhu, Yihao Huang, Felix Juefei-Xu et al.

EditFlow3D automates local 3D asset editing with trajectory preservation.

Rui Nie, Chuang Wang, Haitao Zhou et al.

Unified fusion framework based on Rank-enhanced linear attention with FiLM conditioning achieves 34-40dB PSNR across multiple optical slit configurations.

Yiming Gong, Kai Wang

Distinguishing emulation and estimation tasks, base models excel in response generation, fine-tuned models in direct distribution prediction.

Seth Grief-Albert, Jessica Bo, Difan Jiao et al.

V-FIND localizes sparse neurons to improve video forgery detection, achieving state-of-the-art results with frozen backbones and linear classifiers.

Shichao Kan, Chengpeng Hong, Jingtong Dou et al.

SparSEEty exploits side channels to reconstruct input tokens from sparse activations in confidential VM environments.

Yongwan Jo, Jinyoung Park, Euihyun Lee et al.

Maglev combines sliding-window attention with fixed-size recurrent memory via a parallel-trained predictor, boosting long-sequence modeling by 1-2% accuracy.

Bo Liu, Qiang Liu

Identifies in-context collapse in vision-language models, localizes it to the fusion interface, and introduces CircA adapter for cross-task robustness, boosting 16-shot accuracy from 0.39 to 0.91.

Mohammad Rostami

Optimized constant factors for Hamiltonian simulation via refined Bessel tail handling, approaching factor of 1.

Matthew Pocrnic, Danial Motlagh

Foundation models in astrophysics emphasize transferable representations.

Xiaosheng Zhao, Yuan-Sen Ting

ParEvalLayer combines coverage and bootstrap tests; three benchmarks match full-evaluation decisions after only 15–25% of tasks.

Wei-Jung Huang, Bonan Shen

Learn feasible inventory policies via differentiable projection, achieving an average optimality gap below 1%.

Patrick Helm, Jan-Niklas Doerr, Joren Gijsbrechts et al.

Z-PEFT employs layer-wise spectral features for zero-shot backdoor detection, achieving AUROC 0.9433 on unseen attacks.

Nicola Pitzalis, Donald Shenaj, Giacomo Cignoni et al.

Introduces IBA-Bench for implicit behavior alignment, combining deep retrieval and trajectory-level synthesis, significantly improving personalized LLM agent performance.

Jiajia Song, Bobo Li, Haiwen Yi et al.

Introduces PCTree, leveraging parent-conditioned scoring to boost semi-autoregressive decoding speed by up to 29.5%.

Zixian Li, Tong Li, Chi Xie et al.

QK-Guard prevents low-precision attention collapse via QK normalization, enhancing training stability.

Shuxiao Xie, Shuyang Xie, Yuan Cao et al.

PAES accelerates Evolutionary Strategy by Rao-Blackwellizing uncertain input realizations.

So Nakashima, Tetsuya J. Kobayashi

Adaptive reconstruction technique combines Bayesian inference and active learning for rapid fidelity estimation of bosonic quantum states.

Vasilisa Usova, Phila Rembold, Ian Yang et al.