AdaptiveSpec boosts inference speed by 56% and recovers 93% accuracy by dynamically adjusting draft tree shapes and lossy verification.

Oszkár Urbán, Young D. Kwon, Stylianos I. Venieris et al.

Proposed Unified Hand Action Space (UHAS) enables cross-platform dexterous manipulation; experiments show effective transfer across different hand types.

Luis Felipe Casas, Robert Teal, Keval Shah et al.

Decomposable Probe separates prompt, latent, and score responses, detecting rectified flow through latent selectivity across 23 models.

Patrick Mu Haojie

BVS combines Bayesian optimization and multimodal large language models for fine-grained perception in ultra-high-resolution images, significantly improving accuracy and efficiency.

Geng Li, Yuxin Peng

Proposes an object-centric continuous semantic field method to enhance robot manipulation generalization.

Zheng Sun, Lerong Zhang, Zhihao Li et al.

Proposed cross-survey transfer framework; zero-shot LLMs achieve 52% accuracy on unseen items, nearing supervised models.

Chan-Tung Ku, Chan Hsu, Pei-Cing Huang et al.

SafeGuard employs multi-agent perception and reasoning, achieving 18.7% accuracy improvement in social-risk video detection on SafeVid dataset.

Wenlin Wu, Sheng Zhou, Peipei Song et al.

Proposes Raven-Agent, a modular trading layer for prediction markets, achieving +15.9% risk-adjusted return in replay tests.

Yishu Wang, Yuxuan Wang, Jiaqi Deng et al.

CONFLUX combines 3D latent flow generation with RL control, reaching tri-planar FID 32.3 versus MAISI’s 74.6.

Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge et al.

Proposed cross-device collaborative test-time adaptation using zeroth-order optimization and model merging, reducing error rate by 18.3% on CIFAR10-C.

Yu Mitsuzumi, Akisato Kimura, Yasuhiro Fujiwara et al.

EMA uses DiT Massive Activations: DG improves details and MREP improves dense features; MA disruption leaves BLIP/CLIP win rates at 0.462/0.512.

Chaofan Gan, Zicheng Zhao, Yuanpeng Tu et al.

Prefix-GRPO improves small models in long-horizon environments by reusing teacher trajectory prefixes and online continuation.

Yihan Wang, Zhong Guan, Haoran Sun et al.

R3D constructs 3D scenes from egocentric RGB-D video and uses tool calls to achieve 73.5% accuracy in quantitative 3D reasoning tasks.

Maxwell Horton, Wei Lu, Quan Tran et al.

Oyster-II uses Zero-RL and SERL for constructive safety, raising Chinese long-query safety by 14.65% over joint training.

Jiyang Guan, Yong Xie, Jun Chen et al.

AmpAttention boosts multi-view robotic manipulation success rate to 91%, reducing training time by 33.3%.

Jin Yang, Ping Wei, Nanning Zheng

Proposed a partial bidirectional BDLM Mamba-attention hybrid, boosting long-context inference throughput with parameters from 87M to 350M.

Pranshu Chaturvedi, Parth Shroff, Tarun Suresh et al.

UniCaMo constructs a 3D-grounded noise space for joint control of object and camera motion, improving video coherence and quality.

Long Vu, Tan Ngo, Animesh Karnewar et al.

Proposes EXT++ and PPR to enhance hypergraph RAG, significantly improving fact extraction and chunk retrieval.

Houda Khrouf, Pedro Fillastre, Sebastiao Correia

Proposed a global pose control method for generative view synthesis in Normalized Object Coordinate Space, significantly improving image quality and consistency.

Zhibing Li, Amogh Gupta, Behnoosh Parsa et al.

LLMoxie platform enhances AI agent performance in scientific software development through a three-tier architecture and RSE-Plugins ecosystem.

Landung Setiawan, Anant Mittal, Cordero Core et al.