Proposes a zero-shot active feature acquisition framework using LLM-derived discriminative statistics and MaxEnt closure, significantly improving IBD diagnosis accuracy.

Binyamin Perets, Natalie Mendelson, Shiran Vainberg et al.

REVES employs a two-stage iterative framework optimizing test-time correction, improving +6.5 points on LiveCodeBench, effective for reasoning and constraint satisfaction.

Yuanxin Liu, Ruida Zhou, Xinyan Zhao et al.

Proposes LoopWM, a parameter-shared transformer with iterative latent refinement, achieving 100× parameter efficiency and stable long-horizon environment prediction.

Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang et al.

Introduces Kolmogorov PDE-based diffusion policies with dimension-independent convergence, improving long-horizon control in robotics and manufacturing.

Lekan Molu

Proposes a hierarchical Bayesian credibility framework using an ODD-similarity kernel for partial pooling across cities.

Doyeon Jang

Proposes primal-dual inference for constrained diffusion models, enabling sampling from distributions with average constraints with theoretical convergence guarantees.

Samar Hadou, Yigit Berkay Uslu, Alejandro Ribeiro

FaNO improves physical system modeling by decomposing dynamic and persistent responses.

Hao Tang, Yuechen Duan, Jiongyu Zhu et al.

MyPCBench tests personal intelligent computing agents; Claude Opus 4.6 solves 55.4% of tasks.

Lawrence Keunho Jang, Andrew Keunwoo Jang, Jing Yu Koh et al.

Introduces Entropy-Gated Latent Recursion (EGLR), leveraging layer span L for deterministic inference diversity, boosting reasoning accuracy.

Soham Bhattacharjee, Dushyant Singh Chauhan, Salem Lahlou et al.

MUNI employs an end-to-end multimodal latent diffusion framework for arbitrary-to-arbitrary generation, surpassing baselines in both conditional and unconditional tasks.

Kyeongmin Yeo, Yunhong Min, Minhyuk Sung

NAG architecture separates magnitude and direction in residual streams to address norm growth in deep models.

Tomás Figliolia, Beren Millidge

Introduces active learning with low-rank structure for data selection, enhancing training efficiency.

Vincent Cohen-Addad, Sasidhar Kunapuli, Vahab Mirrokni et al.

Using SAM3 with structured prompts enables zero-shot spacecraft component segmentation without model fine-tuning, achieving 0.385 [email protected] on unseen satellites.

Nicholas A. Welsh, Lennon J. Shikhman, Monty Nehru Attazs et al.

DiRecT employs receding-horizon denoising in diffusion models, enforcing constraints only at the final trajectory, significantly improving safety and performance.

Paolo Giaretta, Zeyang Li, Navid Azizan

AdaNAGED method achieves efficient gradient-free fine-tuning of large language models, reducing memory overhead.

Dmitriy Bystrov, Daniil Medyakov, Dmitry Bylinkin et al.

Proposes EM-NeSy, framing neurosymbolic learning as EM, enabling flexible, non-differentiable symbolic inference with neural updates.

Annegret Seibt, Luc De Raedt, Giuseppe Marra

This paper analyzes the sparsity and geometric structure of on-policy distillation (OPD), revealing small, coordinate-sparse updates that are spectrally concentrated and deviate from source principal directions.

Guo Yu, Wenlin Liu, Yulan Hu et al.

Introduces Trajectory Sensitivity Score (TQS) based on dynamical systems stability to evaluate quantization impact on time-series models.

Mariya Pavlova, Harrison Bo Hua Zhu, Lidia Vitanova et al.

DeepJEB++ leverages 2D latent space interpolation and foundation models to expand a small seed set into 15,360 labeled 3D jet engine brackets, with minimal resources.

Soyoung Yoo, Leekyo Jeong, Jinsu Ra et al.

Proposes Bebop with TV loss and rejection sampling to stabilize MTP acceptance rate, achieving up to 95% and 1.8× RL training acceleration.

Yucheng Li, Huiqiang Jiang, Yang Xu et al.