This paper introduces a five-category ASR error simulation framework, evaluating its impact on embodied AI safety; findings show error type significantly influences risk levels.

Sihan Jia, Oliver Lemon

Proposes split conformal framework for neural operators, guaranteeing at least 1−γ coverage with probability ≥1−α.

Tom Stent, Nicolas Boullé

CE-MoE reduces GPU hours by 33.3% at 31.5B parameters using layer re-configuration.

Simeng Sun, Roger Waleffe

This study compares sequential and parallel sampling in large language model translation, finding sequential sampling more effective under limited budgets.

Di Wu, Sergey Troshin, Christof Monz et al.

Proposed a low-power end-to-end speech denoising model based on Spiking Neural Networks, achieving over sixfold energy savings with comparable performance.

Ludovic Boulanger, Sean U. N. Wood

NL2AGBench evaluates large models’ ability to convert English geometry problems into AlphaGeometry formal language, achieving over 80% success in closed models.

Samuel Xiao, Judy Song, Rory Hu et al.

ElephantBench constructs a graph-based knowledge probe to diagnose LLMs' ability to recall multiple divergent accounts of long-tail facts, revealing biases towards dominant sources.

Zhuoshi Pan, Junru Lu, Yan Qian et al.

This study systematically analyzes how interlocutor biography visibility across training, inference, and evaluation affects persona-based dialogue generation, revealing leakage mechanisms.

Daniela Occhipinti, Malvina Nissim, Marco Guerini

State-conditioned memory router (LayerRecall) enhances long-range content recovery in video diffusion models, achieving top performance on MemoBench and MovieBench.

Yixuan Ding, Jiahao Kong, Wei Huang et al.

This study introduces a diagnosis-guided post-training approach—Acquire, Repair, Preserve—that boosts small dialogue agents' scores from 10.67 to 38.92, focusing on local decision failures.

Nan Li

ARC-CT employs anatomy-guided contrastive learning, combining regional features to achieve 0.86 macro AUC on chest CT abnormalities.

Huseyin Umut Isik, Mehmet Alp Ozaydin, Sila Kurugol et al.

Unified framework linking generalized splines and Gaussian processes via kernel spaces and regularization, enabling optimal infinite-dimensional inverse estimation.

Michael Unser

Sliding Window Attention (SWA) with sinks outperforms post-trained linear attention, enabling efficient long-context reasoning without extra training.

Alexia Jolicoeur-Martineau, Rhea Sanjay Sukthanker, Pashmina Cameron et al.

Proposes a game-theoretic, ecology-inspired cooperative exploration framework with altruistic utility shaping, using relatedness weights to optimize heterogeneous multi-robot teams.

Brooks A. Butler, Jair Certório, João P. Hespanha et al.

Scaling laws for video diffusion models in driving data show validation loss follows power laws; a 9B-parameter model predicts loss of ~0.0753 with 3.6% error.

Victor Besnier, Anh-Quan Cao, Elias Ramzi et al.

Combines LLMs and textual embeddings for long-form article-video matching, boosting user engagement.

Arnaud Corone, Brice Pierre de la Briere, Gladys Roch et al.

Proposes a scalable dynamic community detection framework using graph neural networks with diffusion-guided contrastive learning on temporal graphs.

Peijie Zhong, Raul Mondragon, Richard G. Clegg

MAIL framework generates chemical hypotheses via dynamic literature retrieval, achieving highest MIOS and MPOS scores.

Mahdi Babaei, Xueshen Li, Yutao Kuang et al.

MaCoPlanner uses knowledge compilation and proactive safety verification, boosting task success to 84.4% with a 2.7% violation rate.

Guipeng Xin, Jiahe Xua, Mohammad Deghat et al.

Proposes STEGNav, a spatio-temporal event graph framework, boosting success rate to 66.3% on GOAT-Bench.

Yang Chen, Zhenyu Huang, Wenbo Fu et al.