VGAS achieves training-free reward alignment by reducing variance and adaptive selection, enhancing biological sequence generation.

Kwanyoung Kim

VPP optimizes long-context LLM inference with virtual stages, boosting throughput by 13.1%.

Yan Shi, Xiaochao Wang, Jingchun Gao et al.

Video-FLAIR uses reinforcement learning to select reasoning modes, improving accuracy and reducing computation.

Yogesh Kulkarni, Pooyan Fazli

MoganColBERT-TR uses MaxSim for token-level retrieval, achieving strong zero-shot performance on five Turkish BEIR datasets, outperforming larger models.

Furkan Yilmaz, Habibe Aleyna Tasdemir, Muhammed Faruk Gozay

VBVR-Pro introduces 300 procedurally generated tasks, rule-based reward scorers, and multi-modal evaluation, advancing scalable and reliable visual reasoning.

Junxiang Xu, Ruisi Wang, Fanyi Pu et al.

VDA framework with VC-OT and VMA effectively mitigates visual dependence drift in unsupervised continual multimodal learning, achieving 62.5% accuracy across six tasks.

Kaichen Li, Zhilin Zhu, Jianhao Huang et al.

Addressing critical global challenges, from food security and disaster risk to disease outbreaks and socio-economic vulnerability, demands high-fidelity geospatial modeling. However, building predicti

Evelyn Ma, Rama Kumar Pasumarthi, Kishwar Shafin et al.

SwarmWorld employs decentralized LLM agents in a shared environment to evolve durable technologies, outperforming isolated search in diversity and resilience.

Subhadeep Pal, Fiona Y. Wang, Markus J. Buehler

Proposes SVD-based channel group-shared low-rank approximation to compress pointwise convolutions in large-kernel CNNs, reducing parameters by over 81%.

Hao Luo, Yiting Yang, Wenyi Zhao et al.

StreamPI employs instruction-anchored streaming multimodal temporal modeling, leveraging pre-trained LLM length extrapolation for parameter-free multi-frame inference, outperforming pi0.5 in robot tasks.

Zhe Liu, Jinghua Hou, Yuxiang Lu et al.

DEDUCE framework enhances LLM robustness against input fact perturbations, showing a 20% accuracy improvement in experiments.

Ping Wang, Xiangguo Sun, Bingbing Xu et al.

SkillShield synthesizes offline security skills embedded in system prompts, reducing malicious code generation success rate from 43.6% to 14.5% across six LLMs.

Xiaodong Wu, Zhimin Zhao, Qi Li et al.

EVOMAL wraps malicious skills in banners, causing self-poisoning with ASP R up to 86.7%.

Xiaodong Wu, Yu Shi, Qi Li et al.

Proposes M-HySMap, activity-weighted hypergraph mapping reducing multicast hops by up to 41%.

Amirreza Khorasanian

AWM-GRPO improves long-document VQA accuracy by 8.1 and 11.9 points.

Dongzhuoran Zhou, Yuqicheng Zhu, Yule Liu et al.

RA-VLA integrates behavior-aligned retrieval with grounded execution, enabling training-free robotic adaptation with 17.6% success rate improvement on unseen tasks.

Sanghwan Jang, Minjin Jeon, Minsoo Kim et al.

CAD reduces cross-modal hallucinations with PCME and CAA, improving CMM and AVHBench accuracy by 14.1% and 8.0%.

Yuchen Deng, Chang Sun, Hai-Tao Zheng et al.

TOPAS jointly optimizes prefix residency and request scheduling, reducing task JCT by up to 39.8% on synthetic workloads.

Hongqiu Ni, Han Tian, Chi Zhang et al.

Using eigenvector analysis, the paper proves more hypercube corners can be programmed as stable states, enhancing storage capacity.

Garimella Rama Murthy

4DStreamCtrl unifies 3D point-track representation for real-time video generation and control, enhancing motion precision.

Shiqian Li, Chenguo Lin, Zhiguang Liu et al.