F2LLM-v2 offers efficient multilingual embeddings using a two-stage training and matryoshka learning, supporting over 200 languages.

Ziyin Zhang, Zihan Liao, Hang Yu et al.

Spectrally-guided per-instance diffusion noise schedules enhance low-step generative quality.

Carlos Esteves, Ameesh Makadia

Proposed a new algorithm for online learning with ranking feedback, addressing the absence of traditional numeric feedback.

Mingyang Liu, Yongshan Chen, Zhiyuan Fan et al.

Nemotron-Cascade 2 achieves top-tier reasoning with Cascade RL and multi-domain distillation in a 30B MoE model.

Zhuolin Yang, Zihan Liu, Yang Chen et al.

DriveTok leverages 3D deformable cross-attention for efficient multi-view reconstruction and understanding, excelling on the nuScenes dataset.

Dong Zhuo, Wenzhao Zheng, Sicheng Zuo et al.

DreamPartGen achieves semantically grounded part-level 3D generation via collaborative latent denoising, improving geometric fidelity by 53%.

Tianjiao Yu, Xinzhuo Li, Muntasir Wahed et al.

State Space Models (SSM) outperform Vision Transformers (ViT) as vision encoders in VLMs, especially in VQA and localization tasks.

Shang-Jui Ray Kuo, Paola Cascante-Bonilla

A cost-aware evasion framework reveals robustness gaps in phishing detection; median evasion cost is 2, with over 80% attacks on three low-cost features.

Julian Allagan, Mohamed Elbakary, Zohreh Safari et al.

OmniVTA integrates predictive contact modeling with high-frequency tactile feedback for breakthroughs in contact-rich manipulation.

Yuhang Zheng, Songen Gu, Weize Li et al.

FASTER introduces Horizon-Aware Schedule to significantly reduce reaction latency in VLA models.

Yuxiang Lu, Zhe Liu, Xianzhe Fan et al.

The study explores how LLMs encode auditory knowledge and its impact on audio language models.

Ke-Han Lu, Szu-Wei Fu, Chao-Han Huck Yang et al.

OS-Themis framework improves GUI agent performance by 10.3% on AndroidWorld using a multi-agent critic mechanism.

Zehao Li, Zhenyu Wu, Yibo Zhao et al.

Sparse Autoencoders reveal interpretable and steerable features in VLA models, enhancing generalization on the LIBERO benchmark.

Aiden Swann, Lachlain McGranahan, Hugo Buurmeijer et al.

Box Maze framework reduces LLM reasoning error rate to below 1% through memory grounding, structured inference, and boundary enforcement.

Zou Qiang

ADMM-based distributed MPC with control barrier functions for quadrupedal robots reduces planning time by 51%.

Yicheng Zeng, Ruturaj S. Sambhus, Basit Muhammad Imran et al.

ARIADNE uses DPO and RL for coronary angiography, achieving a centerline Dice of 0.838.

Zhan Jin, Yu Luo, Yizhou Zhang et al.

MAPG uses multi-agent probabilistic grounding for metric-semantic goal localization in vision-language navigation, excelling on the HM-EQA benchmark.

Swagat Padhan, Lakshya Jain, Bhavya Minesh Shah et al.

PPI estimator is algebraically equivalent to Cassel et al.'s difference estimator, combining ML predictions with few labels for statistical inference.

Reagan Mozer

VEPO enhances translation quality and tokenization efficiency for low-resource languages using reinforcement learning with verifiable rewards.

Chonghan Liu, Yimin Du, Qi An et al.

Construct Karhunen-Loève expansions using Fredholm integral equation, combined with SVD for consistent solutions.

Cosmin Safta, Habib N. Najm