Proposed view-adaptive neural renderer improves 3D reconstruction from a single image by correcting view-dependent errors using self-attention, achieving near state-of-the-art results.

U-Chae Jun, Jaeeun Ko, Jiwoo Kang

Proposes VANEB framework, integrating heteroskedastic parameter-dependent EB for personalized federated learning, achieving superior performance on MNIST and CIFAR-10.

Jae Ho Chang, Arnab Auddy, Subhadeep Paul

ReMEMBER employs a gap-conditioned retrieval and evidence refinement framework, improving memory recall and gap resolution in long dialogue summarization with up to 160K tokens.

Hyangsuk Min, Hwanjun Song

Proposes a differentiable MoE gating network with multiple LSTM experts for nonlinear system identification, significantly improving robustness in regime-switching scenarios.

Ali Rajabi, Iman Salehi

Benchmarking five optimizers (SGD, Adam, Adagrad, Adadelta, CGD) with three memory strategies across four transformer architectures; gradient accumulation proved most robust, optimizer performance varies by architecture.

Sarthak Mahapatra, Zihan Zhou, Khatoon Khedri et al.

Proposes Tied Trit-Planes, constraining PTQTP to a nine-level uniform quantizer with lossless folding, enabling efficient disk-streamed MoE serving with 4-bit codes.

Matteo Grella

AeroReformer2 employs a bilateral network with boundary-preserving visual paths and kernel linear cross-modal attention, achieving 62.09% mIoU in spoken-query remote sensing segmentation.

Rui Li, Chenxi Duan, Haoyang Yang

Proposes QCPIKAN, a hybrid quantum-classical physics-informed network, for solving fuzzy PDEs with improved accuracy and theoretical guarantees.

Xiang Rao, Yuxuan Shen

InSituANN leverages IVF with host memory to enable billion-scale vector search on a single GPU, avoiding PCIe bottlenecks and achieving high throughput.

Yuemeng Xu, Zongxi Liu, Junyu Long et al.

Proposes dp_knapsack_sliding_hirschberg combining sliding window and Hirschberg’s algorithm for memory-efficient exact 0/1 knapsack in PyTorch, enabling larger models.

Jędrzej Maczan

FiRe refines images at a fixed noise level, achieving 3× faster inference and 8× fewer FLOPs while maintaining high-quality counterfactuals.

Yan Zeng, Changlu Guo, Oskar Kristoffersen et al.

UniMoMo compresses trained sparse MoE recommendation models via expert merging, achieving speedups of up to 2.21× with minimal performance loss.

Lei Xin, Bin Gu, Peize Li et al.

Proposes FCAC framework combining evidence freshness and randomized audits, achieving 84.4% automation with controlled review workload.

Jie Deng

FailForge extracts procedural skills from failed instances to improve code agent success rate by 6.6 points on SWE benchmarks.

Dongyi Lv, Fushun E, Aichen Cai et al.

Introduces Graph Circuit Learning (GCL), using GNNs for cross-model circuit localization, achieving median edge AUROC of 0.902.

Chester Tan, Moritz Lampert, Courtney Maynard et al.

RenderMatte fine-tunes FLUX.1 with alpha-edge loss and group-relative alignment, achieving state-of-the-art image matting.

Zecheng Ren, Yafei Hu, Jianing Zhao et al.

CALM framework uses kernel density estimation and bootstrap thresholding for real-time anomaly detection in single and multi-testbed environments.

Justyna Witulska, Marcin Szczukiewicz, Artur Tabaka et al.

Biologically-inspired modular SNN (D-SNN) achieves 98% accuracy on MNIST, with tenfold fewer parameters, and resists catastrophic forgetting.

Maksim Bazhenov, Serafim Grubas, Vakhtang Putkaradze

This study systematically analyzes the robustness of internal code correctness signals in LLMs, comparing extraction methods and data variations, with accuracy ranging 41-63%.

Francisco Ribeiro, Sohaila Abdulsattar, Renata Gonzalez et al.

Introduces IoA-Suite for hidden disagreement detection; model F1 only 49.5%, private context is bottleneck.

Kaiming Liu, Fuwen Luo, Ziyue Wang et al.