DGDFEM addresses delayed feedback using dynamic graph neural networks, enhancing data freshness and label accuracy.

Xiaolin Zheng, Zhongyu Wang, Chaochao Chen et al.

A2Nav leverages foundation models for zero-shot robot navigation, surpassing supervised methods with 22.6% success rate on R2R-Habitat.

Peihao Chen, Xinyu Sun, Hongyan Zhi et al.

RAVEN combines retrieval-augmented masked and prefix language modeling to enhance in-context learning.

Jie Huang, Wei Ping, Peng Xu et al.

DREAMWALKER employs explicit world models with environment graphs and scene synthesizers, combined with Monte Carlo Tree Search, to enable strategic mental planning in continuous vision-language navigation, achieving over 78% success rate.

Hanqing Wang, Wei Liang, Luc Van Gool et al.

Proposes AutoMQM, leveraging large language models like PaLM-2 for fine-grained MT error detection and classification, significantly enhancing interpretability.

Patrick Fernandes, Daniel Deutsch, Mara Finkelstein et al.

InstructGLM uses natural language prompts for graph structure description, surpassing GNNs in node classification with instruction fine-tuning.

Ruosong Ye, Caiqi Zhang, Runhui Wang et al.

Proposes a non-singular guiding vector field based on homotopy equivalence for path following, ensuring robustness against singularities.

Zirui Chen, Zongyu Zuo

Neural network-based rotationally invariant closure models, trained on kinetic theory data, achieve high accuracy and stability in active fluid simulations.

Suryanarayana Maddu, Scott Weady, Michael J. Shelley

ModelScopeT2V uses diffusion with spatio-temporal blocks, 1.7B parameters, achieving superior text-to-video synthesis with high temporal coherence.

Jiuniu Wang, Hangjie Yuan, Dayou Chen et al.

PDE-Refiner employs multi-step denoising inspired by diffusion models to achieve accurate long-term PDE predictions, outperforming state-of-the-art neural and hybrid models.

Phillip Lippe, Bastiaan S. Veeling, Paris Perdikaris et al.

Evaluating LLM trustworthiness through alignment techniques, finding aligned models generally perform better in trustworthiness.

Yang Liu, Yuanshun Yao, Jean-Francois Ton et al.

The Coulomb repulsion operator Πε lowers PPP Monte Carlo variance; the default step is ε0=1/(2dκdρ).

Diala Hawat, Gabriel Mastrilli, Rémi Bardenet et al.

Proposes staged speculative decoding with tree-structured batches and two-stage prediction, achieving 3.16x speedup on 762M GPT-2 while preserving quality.

Benjamin Spector, Chris Re

Introduced VPG-C module, significantly enhancing zero-shot performance on DEMON benchmark.

Juncheng Li, Kaihang Pan, Zhiqi Ge et al.

Proposes 3D Gaussian splatting for real-time 1080p scene rendering, achieving ≥30fps with high visual quality and fast training (6-51 min).

Bernhard Kerbl, Georgios Kopanas, Thomas Leimkühler et al.

AgentBench benchmarks 29 LLMs across 8 environments, revealing performance gaps and guiding future improvements.

Xiao Liu, Hao Yu, Hanchen Zhang et al.

Proposes GTE, a general text embedding model trained via multi-stage contrastive learning, with only 110M parameters, surpassing large models in multiple benchmarks.

Zehan Li, Xin Zhang, Yanzhao Zhang et al.

FourLLIE enhances low-light images using Fourier frequency information, surpassing SOTA on four datasets with only 0.31% parameters.

Chenxi Wang, Hongjun Wu, Zhi Jin

MM-Vet evaluates large multimodal models' integrated capabilities, proposing an LLM evaluator to reveal model differences.

Weihao Yu, Zhengyuan Yang, Linjie Li et al.

Quantum variance reduction algorithms outperform classical methods in low-dimensional stochastic optimization, achieving quadratic speedups.

Aaron Sidford, Chenyi Zhang