Exact excluded-pool audits certify missed mass; in the zero-miss regime, the optimal label complexity is Ω(N₀/m).

Martin Anthony, Kaveh Salehzadeh Nobari

DAPM model achieves UAV monocular depth estimation from any height, pitch, roll, and FOV, reaching state-of-the-art performance.

Tong Ling, Wenhui Diao, Yingchao Feng et al.

Proposes context-weighted discrete flow matching, reducing perplexity by 63% via local context-aware sampling and loss.

Daniil Cherniavskii, Daniel Severo, Karen Ullrich

M2S method predicts posterior mean and maps it to scores, improving generative PPL to 143.3.

Jingyuan Li, Xiaoyi Jiang, Yixuan Jiang et al.

Unified moral-value dataset for instruction tuning enhances AI's ethical alignment, improving value-behavior consistency.

Zhaohui Zeng, Florian Mai

Geo3R is a training-free geometric reasoning framework that reduces spatial hallucinations in multimodal large models, improving accuracy by over 10%.

Mingyu Wang, Weilin Jin, Wenbo Li et al.

BoE framework optimizes candidate selection under partial verification, improving medical VQA accuracy by 0.4% with limited evidence budget.

Cenwei Zhang, Teng Fang, Yuxia Wang et al.

The study uses DFT+U and HSE06 cluster expansion methods to reveal long- and short-range anion order in SrTiO3-xHx, highlighting the stability of the O4H2 cis configuration.

Tzu-chen Liu, Chris Wolverton

Introduces ViSTR-Bench, a benchmark for evaluating spatial-temporal reasoning in dynamic scenes, covering Motion Perception, Spatial Relations, Outcome Prediction, and Physical Dynamics.

Han Li, Si Liu, Zehao Huang et al.

REFACT enhances long-text reasoning by adaptive fact restatement, reducing tokens and improving evidence density.

Zhensheng Jin, Xin Dai, Zhenghao Liu et al.

SubSplat uses SPGR to render high-res views from 256×256 inputs, reaching 25.52 dB on RealEstate10K.

Jiun Lee, Jaekwang Kim, Sangmin Lee

Robostral Navigate is a 8B vision-language model using monocular RGB input, achieving 77.4% success in navigation benchmarks.

Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra et al.

The paper defines AI-native systems by revision authority: autonomous implementation rewriting with escalation, verification, and fallback; no empirical metrics are reported.

Cheng Tan

LeakyLMs exploits token timing to infer model architecture and inference optimizations, revealing proprietary details with over 90% accuracy.

Sadegh Majidi, Niloofar Mireshghallah, Kazem Taram

Axolotl3D unifies multi-modal inputs for faithful 3D shape completion under occlusion and multi-view conditions.

Anita Hu, Maria Shugrina

Proposes Masked Topology Modeling (MTM) for self-supervised learning on CAD B-rep graphs, achieving state-of-the-art results in geometric and topological understanding.

Heinrich Jiang, Jennifer Jang

EVO optimizes cache schedules via evolutionary search, achieving 8.05x action-generation speedup, reducing FLOPs to as low as 1.96G.

Siying Wang, Kangye Ji, Di Wang et al.

By orchestrating small language models, the hybrid system of Qwen3-4B and Foundation-Sec-8B outperforms single LLMs in malware analysis with 35.30% accuracy.

Adel ElZemity, Shujun Li, Budi Arief

PerceptDrive uses adaptive expert routing to fuse perception priors, achieving 90.4 PDMS on NAVSIM v1 without test-time candidate search.

Yushan Liu, Tianxiong Lv, Bohua Wang et al.

Transforms active inference into a convex Markov decision process, enabling efficient EFE minimization with theoretical guarantees.

Nikola Milosevic, Nicolás Hinrichs, Nico Scherf