The cHM algorithm is a universal framework for continuous optimization, excelling on 28 benchmark functions.

Piotr A. Kowalski, Szymon Kucharczyk, Jacek Mańdziuk

FalconBC uses flow matching for amortized inference of latent-conditioned physiological boundary conditions, enhancing cardiovascular modeling efficiency.

Chloe H. Choi, Alison L. Marsden, Daniele E. Schiavazzi

Introduced Spatio-Temporal Token Scoring (STTS) to enhance video VLMs efficiency by 62% with minimal performance drop.

Jianrui Zhang, Yue Yang, Rohun Tripathi et al.

Loc3R-VLM enables language-based localization and 3D reasoning from monocular video input, outperforming existing methods.

Kevin Qu, Haozhe Qi, Mihai Dusmanu et al.

LoST efficiently tokenizes 3D shapes by semantic salience for autoregressive generation, using only 0.1%-10% of tokens.

Niladri Shekhar Dutt, Zifan Shi, Paul Guerrero et al.

Efficient training-free multi-token prediction via embedding-space probing, improving LLaMA3 acceptance length by 12%.

Raghavv Goel, Mukul Gagrani, Mingu Lee et al.

RAMP uses reinforcement learning for adaptive mixed-precision quantization, achieving 6% size and 1-3% quality improvements for on-device LLM inference.

Arpit Singh Gautam, Saurabh Jha

This review discusses how synthetic data, virtual environments, and domain adaptation improve autonomous driving perception and planning, emphasizing digital twins and vision-language models.

A. Humnabadkar, A. Sikdar, B. Cave et al.

AgentVLN employs VLM-as-Brain with cross-space mapping and active exploration, achieving superior long-horizon navigation with 73.5% success rate on RxR-CE.

Zihao Xin, Wentong Li, Yixuan Jiang et al.

Adaptive Domain Models leverage Bayesian distillation and warm rotation for efficient training in geometric and neuromorphic AI.

Houston Haynes

Proposed a maximum-projection Bayesian optimization with sensitivity analysis for efficient turbine design under scarce CFD data, achieving a 6% efficiency increase.

Eric Diehl, Adem Tosun, Dimitrios Loukrezis

Proposed a pipeline combining foundation models and MORL for context-aware human preference-driven robot navigation, enhancing adaptability and transparency.

Tharun Sethuraman, Subham Agrawal, Nils Dengler et al.

LLMs as semantic interfaces and ethical mediators in neuro-digital ecosystems, introducing Neuro-Linguistic Integration.

Alexander V. Shenderuk-Zhidkov, Alexander E. Hramov

Introduces FloorPlan-VLN, leveraging structured floor plans as global priors, achieving over 60% success rate improvement with concise instructions.

Kehan Chen, Yan Huang, Dong An et al.

StereoWorld, a camera-conditioned stereo video generator, improves 3D consistency and speed by 3x, using RoPE encoding and attention decomposition.

Yang-Tian Sun, Zehuan Huang, Yifan Niu et al.

GSU dataset evaluates LLMs' spatial reasoning over grids, revealing limitations of visual modality in 3D understanding.

Risham Sidhu, Julia Hockenmaier

A synthesizable RTL architecture for predictive coding networks, supporting local prediction-error dynamics, executed directly in hardware.

Timothy Oh

MetaClaw combines skill-driven fast adaptation and policy optimization, boosting accuracy by up to 32% in continuous deployment.

Peng Xia, Jianwen Chen, Xinyu Yang et al.

Utilizing a Quadratic Surrogate Attractor to enhance Particle Swarm Optimization's global convergence and robustness.

Maurizio Clemente, Marcello Canova

Optimization-embedded active multi-fidelity surrogate learning for airfoil shape optimization improves cruise efficiency by 41.05% and take-off lift by 20.75%.

Isaac Robledo, Alberto Vilariño, Arnau Miró et al.