Proposes a knowledge-guided LVLM framework achieving 99.53% AUC for deepfake detection, enhancing generalization and explainability.

Peipeng Yu, Jianwei Fei, Hui Gao et al.

Proposes Cosmos-Reason1, integrating hierarchical physics ontology with multimodal LLMs, achieving significant improvements in physical commonsense and embodied reasoning.

NVIDIA, :, Alisson Azzolini et al.

Proposes collaborative self-play (CSP) framework with Reinforced Self-Training (ReST) to improve tool use and uncertainty calibration in language models.

Jacob Eisenstein, Reza Aghajani, Adam Fisch et al.

DualToken employs dual visual vocabularies to unify understanding and generation, achieving 82.0% zero-shot accuracy on ImageNet with 0.25 rFID.

Wei Song, Yuran Wang, Zijia Song et al.

Concat-ID leverages VAE and 3D self-attention for universal identity-preserving video synthesis across multiple scenarios.

Yong Zhong, Zhuoyi Yang, Jiayan Teng et al.

Introduces multi-output conformal prediction (M-R2CCP, M-R2C2R) for reliable uncertainty quantification in 2D/3D anatomical landmark localization.

Jef Jonkers, Frank Coopman, Luc Duchateau et al.

HDLCoRe uses prompt engineering and retrieval augmentation to improve HDL code generation without fine-tuning, reducing hallucinations by 28%.

Heng Ping, Shixuan Li, Peiyu Zhang et al.

FlexVLN combines an LLM planner with supervised execution, achieving strong zero-shot transfer across REVERIE, SOON, and CVDN-target.

Siqi Zhang, Yanyuan Qiao, Qunbo Wang et al.

INPROVF integrates LLMs and formal verification to efficiently repair high-level robot controllers during assumption violations, reducing repair time by up to 70%.

Qian Meng, Jin Peng Zhou, Kilian Q. Weinberger et al.

CAVE combines 3D neural object volumes with sparse concept learning, achieving robust out-of-distribution performance and faithful interpretability, with 77.4% OOD accuracy.

Nhi Pham, Artur Jesslen, Bernt Schiele et al.

Proposes On-the-Fly GS, a progressive framework enabling near real-time 3DGS optimization, reducing per-image optimization to seconds.

Yiwei Xu, Yifei Yu, Wentian Gan et al.

Introduces conformal e-prediction using E-values and Ville’s inequality for flexible, non-exchangeable, sequential coverage guarantees.

Etienne Gauthier, Francis Bach, Michael I. Jordan

Active RL-based online demonstration transfer significantly improves success rate and sample efficiency in robotic policy transfer.

Muhan Hou, Koen Hindriks, A. E. Eiben et al.

MagicID achieves ID-consistent and dynamic-rich video customization via hybrid preference optimization, surpassing existing methods.

Hengjia Li, Lifan Jiang, Xi Xiao et al.

LLMSeR enhances sequential recommendation by generating pseudo-prior items using LLMs.

Yuqi Sun, Qidong Liu, Haiping Zhu et al.

Reflect-DiT employs in-context reflection to improve text-to-image diffusion, achieving +0.19 score improvement with only 20 samples on GenEval.

Shufan Li, Konstantinos Kallidromitis, Akash Gokul et al.

Introduced a multimodal sarcasm analysis framework, evaluating 12 LVLMs over 2409 samples.

Junjie Chen, Xuyang Liu, Subin Huang et al.

Multi-task SceneScript model with infilling enhances 3D scene layout local correction, achieving 98.6% F1 in local tasks.

Christopher Xie, Armen Avetisyan, Henry Howard-Jenkins et al.

Neural collision classifier with Eikonal regularization enables differentiable robot rendering avoiding static and self-collisions.

Quanyuan Ruan, Jiabao Lei, Wenhao Yuan et al.

Dynamic PDE-based ergodic exploration improves search efficiency for drifting targets in flow fields, achieving 50% higher detection rates.

Luka Lanča, Karlo Jakac, Sylvain Calinon et al.