Proposes a target-wise model adequacy test to evaluate spectral uncertainty intervals in lattice QCD, validated via empirical coverage and stress tests.

Haozheng Li

Proposed a spectral knowledge transfer framework with two-step embedding, improving low-dimensional representations in rare disease EHRs.

Feiqing Huang, Zongqi Xia, Rong Ma et al.

Proposes GLACIER, a multimodal foundation model using contrastive learning and Finsler geometry for molecular property prediction, achieving SOTA results.

Emily Nguyen, Yongchan Hong, Harsh Toshniwal et al.

Next Forcing introduces multi-chunk prediction to accelerate training and improve accuracy in high-frame-rate video generation, achieving 94.1% success on RoboTwin.

Gangwei Xu, Qihang Zhang, Jiaming Zhou et al.

AMNet introduces modality-agnostic inference for low-light video enhancement, maintaining high performance even with missing auxiliary modalities, outperforming state-of-the-art methods.

Hangfeng Liang, Yutao Hu, Yanhan Hu et al.

EEVEE framework employs a router-conditioned prompt set with co-evolution to enhance LLM robustness across heterogeneous task streams, improving scores by 10.38-24.32 points.

Weixian Xu, Shilong Liu, Mengdi Wang

Introduces Data2Story, a multi-agent framework transforming data into verifiable multimodal stories with evidence traceability and interactive content.

Kevin Qinghong Lin, Batu EI, Yuhong Shi et al.

This paper introduces feedback alignment in self-distillation, comparing three feedback types; structure-aligned critique outperforms others with +16.11% accuracy.

Semih Kara, Oğuzhan Ersoy

Unified analysis of GP-UCB and DEC in RKHS bandits via MAIR framework, revealing their fundamental differences and advantages.

Yunbei Xu

Piper decouples training strategies via IR, enabling flexible multi-strategy scheduling with performance parity and efficiency gains.

Megan Frisella, Shubham Tiwari, Andy Ruan et al.

COGENT integrates Graph Neural Networks with Neural ODEs for continuous long-term physical forecasting on irregular meshes, outperforming traditional autoregressive models.

Zesheng Liu, Maryam Rahnemoonfar

Introduces Itô maps for arbitrary-step SDE sampling, enabling conditional sampling and control, enhancing diversity and efficiency.

Zhengkai Pan, Peter Potaptchik, Wenxi Yao et al.

JOIN employs opposition-score and task-conditioned manipulability for autonomous heterogeneous bimanual collaboration, achieving 95% success in real-world tests.

Drake Moore, Matt Cheng, Xiang Zhi Tan et al.

Proposes an efficient online algorithm for drifting halfspaces under Massart noise, achieving an error bound of η + ˜O(Δ^{1/3}/γ), nearly matching theoretical limits.

Mingchen Ma, Guyang Cao, Jelena Diakonikolas et al.

MOFA-VTON employs diffusion models with dual-region masks and cross-attention-based layout adjustment, enabling user-controlled, fine-grained virtual try-on with diverse styles.

Xiaoyu Han, Chenyang Wang, Jing Wang et al.

Prolog-based neuro-symbolic skill enables LLM-guided service placement with validated constraints and explainability, improving transparency and policy compliance.

Jacopo Massa, Giuseppe Bisicchia, Patrizio Dazzi et al.

This paper introduces a fully distributed multi-UGV exploration framework combining descriptor-based loop closure detection and loop-aware hierarchical planning, achieving AR@1 of 89.9% and reducing exploration time by 15%.

Zhiwei Li, Haiou Liu, Xijun Zhao et al.

VISTA introduces a hybrid user simulator combining UI and API actions, with six metrics for realism and coverage, outperforming existing methods in diverse scenarios.

Yunan Lu, Ryan Shea, Yusen Zhang et al.

Proposes HiViG, a history-aware visually grounded test-time framework, boosting GUI task success rates by 5.8% (Qwen3-VL-32B) and 9% (Gemini-3-Flash) through macro-action history and visual error verification.

Jaewoo Lee, Zaid Khan, Archiki Prasad et al.

This paper introduces flexible sequence kernels based on evolutionary substitution matrices, leveraging Gaussian processes for data-efficient protein property prediction, outperforming embedding-based methods.

Martin Jankowiak, Yerdos Ordabayev, Rudraksh Tuwani et al.