Study finds RAG system improvements in retrieval do not guarantee better QA performance in AI policy analysis.

Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur et al.

MARCH framework significantly reduces LLM hallucination using multi-agent reinforced self-check, enhancing factual consistency in an 8B parameter model.

Zhuo Li, Yupeng Zhang, Pengyu Cheng et al.

EndoVGGT enhances surgical 3D reconstruction with DeGAT, improving PSNR by 24.6% and SSIM by 9.1%.

Falong Fan, Yi Xie, Arnis Lektauers et al.

Chameleon enhances robotic manipulation with geometry-grounded multimodal memory, improving decision reliability in long-horizon tasks.

Xinying Guo, Chenxi Jiang, Hyun Bin Kim et al.

VFIG uses vision-language models for complex figure-to-SVG conversion, achieving a VLM-Judge score of 0.829.

Qijia He, Xunmei Liu, Hammaad Memon et al.

UI-Voyager employs RFT and GRSD, achieving 81% success on AndroidWorld with a 4B model, surpassing human performance.

Zichuan Lin, Feiyu Liu, Yijun Yang et al.

Self-distillation can degrade LLMs' reasoning in math by suppressing uncertainty expression.

Jeonghye Kim, Xufang Luo, Minbeom Kim et al.

Transformer-based DRL policy achieves 12.89-15.12% gap on large OSSP instances, generalizing from small training data.

Faezeh Ardali, Mwembezi A. Nyelele, Gerald M. Knapp

Proposed a simplified, stable flow-matching generative model, scaled twice as large, with twofold FID reduction and improved unseen molecule simulation using molecular embeddings.

Charles Jones, Emmanuel Noutahi, Jason Hartford et al.

ArrayDPS-Refine uses diffusion models for training-free, array-agnostic speech enhancement, significantly reducing nonlinear distortions and improving intelligibility.

Zhongweiyang Xu, Ashutosh Pandey, Juan Azcarreta et al.

Proposes a PSTO-based decentralized end-to-end MARL framework enabling LiDAR-driven control for multi-UAV pursuit, achieving high success and scalability.

Yude Li, Zhexuan Zhou, Huizhe Li et al.

UniScale combines entire-space data expansion and hierarchical Transformer architecture to boost search ranking performance.

Liren Yu, Caiyuan Li, Feiyi Dong et al.

Realiz3D introduces domain-aware diffusion to decouple control signals from visual domain, enabling photorealistic, 3D-consistent multi-view generation.

Ido Sobol, Kihyuk Sohn, Yoav Blum et al.

KG-M3PO integrates dynamic knowledge graphs into multi-task RL, achieving superior efficiency and generalization in partially observable robotic manipulation.

Aditya Narendra, Mukhammadrizo Maribjonov, Dmitry Makarov et al.

HEAR transforms accessibility logs into empathetic, legal-aware reports using semantic slicing and multi-layer reasoning.

Ryoya Koyama, Zhiyao Wang, Devi Karolita et al.

Echoes dataset enhances music deepfake detection generalization through semantic alignment.

Octavian Pascu, Dan Oneata, Horia Cucu et al.

MedObvious exposes the Medical Moravec's Paradox in VLMs via a 1,880-task benchmark for clinical triage.

Ufaq Khan, Umair Nawaz, L D M S S Teja et al.

UniGRPO optimizes text and image generation policies using GRPO, enhancing reasoning-driven visual generation quality.

Jie Liu, Zilyu Ye, Linxiao Yuan et al.

DA-Flow combines diffusion and convolutional features to enhance optical flow estimation in degraded videos.

Jaewon Min, Jaeeun Lee, Yeji Choi et al.

WildWorld dataset offers over 450 actions and explicit state annotations for generative ARPG dynamic world modeling.

Zhen Li, Zian Meng, Shuwei Shi et al.