Proposes UniCRS, a knowledge-enhanced prompt learning framework, unifying recommendation and dialogue tasks, significantly improving semantic consistency.

Xiaolei Wang, Kun Zhou, Ji-Rong Wen et al.

Proposes Nested Exponential Weights (NEW) algorithm leveraging hierarchical similarity structures, achieving regret bounds of O(√neff log n · T).

Matthieu Martin, Panayotis Mertikopoulos, Thibaud Rahier et al.

Proposes 'Adaptive MB' method that estimates residual mode to improve robustness and convergence in multivariate least-squares problems, outperforming traditional RLFs.

Thomas Hitchcox, James Richard Forbes

VectorMapNet predicts sparse polylines end-to-end from onboard sensors, surpassing SOTA by 14.2 mAP on nuScenes.

Yicheng Liu, Tianyuan Yuan, Yue Wang et al.

UNIFIED-IO employs a unified sequence-to-sequence transformer architecture, converting multi-modal inputs and outputs into discrete tokens, trained on over 90 datasets, achieving state-of-the-art multi-task performance.

Jiasen Lu, Christopher Clark, Rowan Zellers et al.

Leveraging large language models (e.g., GPT-3) to guide mutation in genetic programming, generating diverse Python robots with over 300,000 solutions, enabling zero-shot generalization.

Joel Lehman, Jonathan Gordon, Shawn Jain et al.

Proposed TCP framework combines trajectory and control prediction, achieving 75.137 score on CARLA leaderboard with monocular input.

Penghao Wu, Xiaosong Jia, Li Chen et al.

Proposes a novel algorithm that adaptively learns stochastic and adversarial bandits with general graph feedback, achieving poly log T regret in stochastic and O(T^{2/3}) in adversarial environments.

Fang Kong, Yichi Zhou, Shuai Li

RaMViD uses random-mask diffusion and reaches SOTA on BAIR/Kinetics-600.

Tobias Höppe, Arash Mehrjou, Stefan Bauer et al.

Accelerate Sinkhorn algorithm using data-dependent initialization, boosting efficiency without loss of differentiability.

James Thornton, Marco Cuturi

ProcTHOR uses procedural generation to create large-scale diverse environments, enabling RGB-only trained models to achieve SOTA on 6 Embodied AI benchmarks.

Matt Deitke, Eli VanderBilt, Alvaro Herrasti et al.

CERT uses sketch-then-generation continual pre-training, raising PandasEval pass@1 to 28.42%.

Daoguang Zan, Bei Chen, Dejian Yang et al.

Fine-tuning large language models via behavioral cloning to generate natural critiques, improving human evaluation by 50%.

William Saunders, Catherine Yeh, Jeff Wu et al.

Proposed RFedSVRG algorithm achieves O(1/ε²) convergence for federated optimization on Riemannian manifolds, handling non-convex constraints effectively.

Jiaxiang Li, Shiqian Ma

Meta OT leverages meta-learning to predict optimal transport maps, significantly accelerating multiple similar OT problem solutions with minimal computation.

Brandon Amos, Samuel Cohen, Giulia Luise et al.

ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning enhances learning efficiency and stability.

Haozhe Wang, Chao Du, Panyan Fang et al.

Proposes a furthest-answer-based ε-optimal identification algorithm for linear bandits, reducing sample complexity near theoretical limits.

Marc Jourdan, Rémy Degenne

TVflowNET accelerates solving the total variation flow via unsupervised learning, significantly boosting computational efficiency.

Tamara G. Grossmann, Sören Dittmer, Yury Korolev et al.

Concept Relevance Propagation (CRP) integrates local and global XAI, providing human-understandable explanations with concept-level insights.

Reduan Achtibat, Maximilian Dreyer, Ilona Eisenbraun et al.

Introduces neuron partition analysis, proving early-stage rapid convergence and global convergence of mildly parameterized neural networks, surpassing NTK over-parameterization limits.

Mingze Wang, Chao Ma