NEO-ov, a fully native end-to-end vision-language model, supports multi-image and video understanding with superior fine-grained perception and spatial reasoning.

Haiwen Diao, Jiahao Wang, Penghao Wu et al.

Proposes Bidirectional Evolutionary Search (BES), combining forward candidate evolution with backward goal decomposition to enhance exploration and verification in language models.

Guowei Xu, Zhenting Qi, Huangyuan Su et al.

Introduced a physics-grounded tactile representation CoP for zero-shot sim-to-real transfer in complex manipulation tasks.

Jiahe Pan, Stelian Coros, Jitendra Malik et al.

Proposes Calibrated Collective Oversight (CCO), integrating multiple auxiliary signals with Conformal Decision Theory for online calibration, ensuring AI behavior aligns with safety targets.

William Overman, Mohsen Bayati

VisualMem introduces a structured visual memory module integrated with text memory, achieving 95% accuracy in personal entity recall, surpassing caption-based methods by over 40%.

Viet Nguyen, Thao Nguyen, Vishal M. Patel et al.

OmniVerifier-M1 employs symbolic bounding boxes and decoupled reinforcement learning to enhance visual verification accuracy, achieving 0.68 on ViVerBench.

Xinchen Zhang, Bowei Liu, Jiale Liu et al.

Proposes CAPO, a cross-annotator preference optimization method, enabling LLMs to learn and reproduce stable individual explanation behaviors, outperforming prompting and SFT.

Beiduo Chen, Pingjun Hong, Ziyun Zhang et al.

LearnWeak framework uses a stronger reference agent to identify model weaknesses, synthesizes targeted tasks, and improves small CUAs by 11.6% on average across 8 domains.

Suji Kim, Kangsan Kim, Sung Ju Hwang

FluxMem models memory as a dynamically evolving heterogeneous graph with three stages, achieving state-of-the-art results in complex reasoning and web navigation tasks.

Jizhan Fang, Buqiang Xu, Zhixian Wang et al.

H-consistency framework for multi-label metric optimization; introduces O(l) surrogate loss with exact decomposition.

Mehryar Mohri, Yutao Zhong

CubePart: An open-vocabulary, part-controllable 3D generator for semantic structure generation.

Yiheng Zhu, Kangle Deng, Jean-Philippe Fauconnier et al.

CORE algorithm enables rapid reasoning improvement using fewer samples and rollouts through contrastive reflection.

Linas Nasvytis, Simon Jerome Han, Ben Prystawski et al.

BIRDNet encodes mined Boolean implication graphs into sparse, interpretable deep neural networks, achieving near state-of-the-art AUROC with 96x fewer active parameters on six biomedical datasets.

Tirtharaj Dash

This study reveals architecture-specific failure signatures in VLA models via black-box action monitoring, emphasizing the importance of architecture-matched monitors.

Krishnam Gupta

LiveBrowseComp shows that search agents often verify memory: on 335 fresh-fact questions, closed-book accuracy stayed below 2%.

HuiMing Fan, Xiao Wang, Zheng Chu et al.

GraphSteal employs traversal-based reconstruction to recover over 90% of hidden knowledge graphs, exposing privacy vulnerabilities in Graph RAG systems.

Jinze Gu, Qinghua Mao, Xi Lin et al.

SHIFT method selects data using inference-time hidden-state dynamics, enhancing RLVR performance.

Jianghao Wu, Jianfei Cai, Weiqiang Wang et al.

Mobile-Aptus enhances mobile agents' interaction via confidence-driven framework, boosting task success rate by 26%.

Zheng Wu, Pengzhou Cheng, Zongru Wu et al.

Woodpecker Distillation uses weak models to diagnose and correct local reasoning bugs, improving mathematical reasoning accuracy by 1.4% on average.

Dayu Wang, Jiaye Yang, Weikang Li et al.

DeGO framework decouples rigid and nonrigid motion, achieving a 13.5% improvement in human-centric instances.

Yang Gao, Wuyang Li, Po-Chien Luan et al.