Study finds LLM-assisted programming shortens idea generation time but reduces creative moments.

Zeinabsadat Saghi, Run Huang, Souti Chattopadhyay

Introduces scale-sensitive shattering, proving equivalence between uniform convergence, learnability, and fat-shattering dimension at optimal scales.

Shashaank Aiyer, Yishay Mansour, Shay Moran et al.

Implement conformal anomaly detection in Python using nonconform to provide statistically calibrated p-values.

Oliver Hennhöfer, Maximilian Kirsch, Christine Preisach

Extends neural posterior estimation (NPE) to support mixed discrete and continuous parameters using a factorized inference network with autoregressive classification and generative models.

Jan Boelts, Cornelius Schröder, Jonas Beck et al.

CUBic employs shared codebooks for unified bimanual perception and control, achieving 12% higher success in RoboTwin benchmarks.

Xingyu Wang, Pengxiang Ding, Jingkai Xu et al.

Proposes SIAA gray-box attack exploiting ViT feature space, achieving near-white-box success rates (~98%) in fake image detection.

Chiara Musso, Joy Battocchio, Andrea Montibeller et al.

Deep learning model predicts ECG with R2 of 0.949, reducing structural uncertainty.

Shaheim Ogbomo-Harmitt, Cesare Magnetti, Jakub Grzelak et al.

Proposes VH-CBM, combining VLM embeddings and minimal annotations via Gaussian Processes to enhance concept accuracy and calibration.

Nicola Debole, Andrea Passerini, Stefano Teso et al.

D-VLA framework uses 'Plane Decoupling' and a four-thread asynchronous pipeline to enhance VLA model sampling efficiency and throughput.

Yucheng Guo, Yongjian Guo, Zhong Guan et al.

N-vium achieves 57.9% inference speedup with mixture-of-exits transformer, no perplexity loss.

Aleksander Lorenc, Frédéric Berdoz, Joël Mathys et al.

Exact Linear Attention (ELA) achieves O(L) complexity via kernel decomposition, eliminating approximation errors, and enhances long-sequence and vision tasks.

Weinuo Ou

OCH3R uses Transformer for single-image multi-object 3D reconstruction, achieving high speed and accuracy.

Yi Du, Yang You, Xiang Wan et al.

CiteVQA evaluates evidence attribution in MLLMs using Strict Attributed Accuracy, revealing reliability gaps in answer-only evaluations.

Dongsheng Ma, Jiayu Li, Zhengren Wang et al.

Proposes a five-layer MLOps architecture enabling collective learning and safety assurance for autonomous vehicle fleets.

Bastian Lampe, Lutz Eckstein

Automated red-teaming system BenchJack detects 8 classes of benchmark flaws, improving robustness.

Hao Wang, Hanchen Li, Qiuyang Mang et al.

Proposes Multi-Rollout On-Policy Distillation (MOPD), leveraging peer successes and failures to enhance model reasoning by 20% on math tasks.

Weichen Yu, Xiaomin Li, Yizhou Zhao et al.

CRAFT uses reward-based fine-tuning with foundation models to improve clinical alignment in medical image synthesis, reducing low-quality hallucinations.

Yunsung Chung, Alex El Darzi, Carlo El Khoury et al.

CUActSpot benchmark enhances GUI complex interaction performance via data synthesis and multimodal evaluation; Phi-Ground-Any-4B excels.

Miaosen Zhang, Xiaohan Zhao, Zhihong Tan et al.

SenseNova-U1 unifies multimodal understanding and generation via NEO-unify architecture, enhancing vision-language model performance.

Haiwen Diao, Penghao Wu, Hanming Deng et al.

CausalCine achieves real-time multi-shot video generation using a causal autoregressive framework, significantly enhancing cross-shot coherence and interactivity.

Yihao Meng, Zichen Liu, Hao Ouyang et al.