Proposes Turing-RL, a reinforcement learning approach using discriminative Turing rewards to train human user simulators, outperforming traditional response matching methods.

Yingshan Susan Wang, Cedegao E. Zhang, Linlu Qiu et al.

Proposes DO AS I DO framework that reconstructs human hand-object interactions from monocular RGB videos and retargets them to dexterous robots, outperforming state-of-the-art methods.

Bhawna Paliwal, Haritheja Etukuru, William Liang et al.

Diffusion-Proof framework uses dLLMs for formal theorem proving, achieving a 6.14% improvement over AR models.

Ruida Wang, Rui Pan, Pengcheng Wang et al.

Analyzes observability and consistency of VINS with anchored feature parameterization, demonstrating improved estimator reliability through theoretical and experimental validation.

Mitchell Cohen, Vassili Korotkine, James Richard Forbes

This study compares webpage retraction, self-correction, and expert correction strategies, revealing that self-correction maintains credibility and enhances trust, especially when social connection is strong.

Biswadeep Sen, Yi-Chieh Lee

Proposes STARE, a surprisal-guided advantage reweighting method, stabilizing policy entropy and improving accuracy by 4%-8% on models from 1.5B to 32B.

Haipeng Luo, Qingfeng Sun, Songli Wu et al.

Mining falsifiable research ideas from paper knowledge graphs using categorical structures, filtering ratio ~17:1.

Yuchen Wang, Zhongzhi Luan

Dango is a 1.8B-parameter L1-only model, using filtering to reduce L2 contamination, for studying L1-to-L2 transfer in SLA.

Shiho Matta, Yin Jou Huang, Fei Cheng et al.

WalkOCC uses hybrid 2D-3D learning for monocular 3D occupancy prediction, achieving a 15.6% mIoU improvement on Sidewalk3D.

Yukai Ma, Joe Lin, Liu Liu et al.

Proposes a block-encoding compiler using MPO as a compressed virtual-path linear combination, applied to Heisenberg evolution, reducing resource costs.

Eugene Dumitrescu

smoothbp is a Bayesian hierarchical piecewise regression tool with smoothed transitions and automatic change-point selection, supporting multiple breakpoints and random effects.

Aidan D. Bindoff

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.

ScreenAnnotator tool enhances annotation efficiency for vision-language models using unified annotation atoms and Bayesian verifier.

Like Zhang, Runliang Niu, Shiqi Wang et al.

Improved long-context reasoning using a data recipe and GRPO setup, achieving average gains of 7.2 points.

Xiaoyue Xu, Sikui Zhang, Xiaorong Wang et al.

TimeLAVA evaluates time series data quality using Selective Wavelet-based Wasserstein discrepancy.

Wenqin Liu, Weizhi Quan, Aoqi Zuo et al.

UniTemp enables bidirectional video generation via joint distillation, addressing boundary flickering caused by causal 3D VAE, with strong performance on short and long videos.

Lin Zhang, Sicheng Mo, Zefan Cai et al.

Euclid-Omni unifies deduction and algebra through Euclidea, solving 595/601 Geometry3K problems and 16 IMO-AG-30 problems.

Zhaoyu Li, Hangrui Bi, Youyuan Zhang et al.

CHIEF is a creator-driven video loop that extends student-made films from 1 to 10 minutes.

Denis Savytski, Aiden Lei, Heding Liu et al.

Quantifies text-conditioned impact on grayscale-to-color models (U-Net, Stable Diffusion 1.5); PSNR +5.6%-5.8%, LPIPS -7.6%-11.3%.

Colten Reissmann, Hugo Garrido-Lestache Belinchon