LPSDA leverages Lie point symmetries to enhance neural PDE solvers, reducing training data needs by over tenfold and improving generalization.

Johannes Brandstetter, Max Welling, Daniel E. Worrall

Wukong: 100M Chinese cross-modal dataset with contrastive and token interaction techniques, boosting zero-shot classification accuracy to 73.03%.

Jiaxi Gu, Xiaojun Meng, Guansong Lu et al.

Contrastive training (SimCTG) and contrastive search improve diversity and coherence in neural text generation, outperforming SOTA methods.

Yixuan Su, Tian Lan, Yan Wang et al.

This study analyzes how variations in ground truth affect query performance prediction (QPP) evaluation, recommending stable metric-model combinations.

Debasis Ganguly, Suchana Datta, Mandar Mitra et al.

Virtual binocular vision-based Tac3D sensor achieves real-time 3D contact deformation and force distribution measurement.

Lunwei Zhang, Yue Wang, Yao Jiang

Recurrent neural networks with explicit memory and progressive training enable extreme algorithmic extrapolation, solving tasks beyond training scope with high accuracy.

Arpit Bansal, Avi Schwarzschild, Eitan Borgnia et al.

Proposes causal intervention and ROME method to locate and edit factual associations in GPT, achieving high success rates and better control over knowledge editing.

Kevin Meng, David Bau, Alex Andonian et al.

A convex-relaxation–FTRL–rounding framework achieves 9.22-approximate no-regret for online Pandora’s Box.

Evangelia Gergatsouli, Christos Tzamos

Compiler support for sparse tensor computations in MLIR, automating sparse code generation to improve efficiency.

Aart J. C. Bik, Penporn Koanantakool, Tatiana Shpeisman et al.

MaskGIT accelerates image generation by 64x using bidirectional transformers, improving quality.

Huiwen Chang, Han Zhang, Lu Jiang et al.

AlphaCode leverages large-scale Transformer models with filtering and clustering to achieve top54.3% in competitive programming, solving 34.2% of problems.

Yujia Li, David Choi, Junyoung Chung et al.

Integrating classical and data-driven methods, this work proposes a multi-layered robotic grasping framework, significantly improving stability and adaptability.

Hanbo Zhang, Jian Tang, Shiguang Sun et al.

Survey of hallucination in NLG, covering metrics, mitigation, and task-specific research.

Ziwei Ji, Nayeon Lee, Rita Frieske et al.

Proposes TACTiS, a Transformer-based model using attention copulas for joint probabilistic forecasting of high-dimensional multivariate time series.

Alexandre Drouin, Étienne Marcotte, Nicolas Chapados

GMC introduces a geometric contrastive framework with a two-level architecture, achieving state-of-the-art robustness in missing modality scenarios.

Petra Poklukar, Miguel Vasco, Hang Yin et al.

MP-PDE unifies classical local solvers with message passing and improves autoregressive stability via pushforward training.

Johannes Brandstetter, Daniel Worrall, Max Welling

Proposed LEDNet for joint low-light enhancement and deblurring, trained on LOL-Blur dataset with 12,000 pairs, significantly improving night image quality.

Shangchen Zhou, Chongyi Li, Chen Change Loy

Proposes automated red teaming using language models to generate and detect harmful outputs in 280B parameter chatbots, employing multi-strategy approaches.

Ethan Perez, Saffron Huang, Francis Song et al.

Introduces a system of SDE-based score model for graph generation, capturing complex node-edge dependencies with high fidelity.

Jaehyeong Jo, Seul Lee, Sung Ju Hwang

This survey categorizes autonomous driving scenario generation into data-driven, adversarial, and knowledge-based methods, highlighting five key challenges.

Wenhao Ding, Chejian Xu, Mansur Arief et al.