This paper introduces a quantitative framework using the GlobalOpinionQA dataset to evaluate how well language models represent diverse global opinions, revealing biases and stereotypes.

Esin Durmus, Karina Nguyen, Thomas I. Liao et al.

This review summarizes recent advances in Optimal Transport (2012-2023), covering theory, algorithms, and applications in machine learning.

Eduardo Fernandes Montesuma, Fred Ngolè Mboula, Antoine Souloumiac

COMPASS employs differentiable causal discovery to identify key environment parameters, reducing sim-to-real trajectory differences by 40% and boosting task success to 85%.

Peide Huang, Xilun Zhang, Ziang Cao et al.

REFLECT combines hierarchical multimodal summaries with large language models for robot failure explanation and correction, achieving 88% explanation accuracy and 79% correction success.

Zeyi Liu, Arpit Bahety, Shuran Song

LeanDojo introduces ReProver, a retrieval-augmented language model trained on 98,734 theorems, achieving 51.2% proof success with only one week GPU training.

Kaiyu Yang, Aidan M. Swope, Alex Gu et al.

Position Interpolation (PI) extends RoPE-based LLaMA models to 32768 tokens with minimal fine-tuning, greatly improving long-context tasks.

Shouyuan Chen, Sherman Wong, Liangjian Chen et al.

Introduces MESS benchmark for zero-shot semantic segmentation across 22 diverse datasets, leveraging CLIP-based models with detailed performance analysis.

Benedikt Blumenstiel, Johannes Jakubik, Hilde Kühne et al.

Using relative position embeddings and train set priming for arithmetic transformer length generalization, achieving up to 99.9% accuracy.

Samy Jelassi, Stéphane d'Ascoli, Carles Domingo-Enrich et al.

Shikra model enables multimodal LLMs to perform referential dialogue, improving localization tasks.

Keqin Chen, Zhao Zhang, Weili Zeng et al.

FunQA enhances VLM understanding of counter-intuitive videos via multi-turn dialogues, featuring 312K QA pairs.

Binzhu Xie, Sicheng Zhang, Zitang Zhou et al.

InterCode: Standardizing interactive coding with execution feedback to enhance code generation.

John Yang, Akshara Prabhakar, Karthik Narasimhan et al.

RVT employs a multi-view transformer with virtual view rendering, achieving 26% success improvement and 36x faster training on RLBench tasks.

Ankit Goyal, Jie Xu, Yijie Guo et al.

KOSMOS-2 is a multimodal large language model with grounding and referring capabilities, achieving state-of-the-art performance on spatial understanding and vision-language tasks.

Zhiliang Peng, Wenhui Wang, Li Dong et al.

Reduce hallucination in multi-modal models using LRV-Instruction dataset and GAVIE method.

Fuxiao Liu, Kevin Lin, Linjie Li et al.

RoboCook uses GNN and self-supervised learning for complex long-horizon soft body manipulation with only 20 minutes of data per tool.

Haochen Shi, Huazhe Xu, Samuel Clarke et al.

Introduces Human-AI Coevolution concept, analyzing feedback loops in recommender systems and their societal impacts.

Dino Pedreschi, Luca Pappalardo, Emanuele Ferragina et al.

GKD (Generalized Knowledge Distillation) leverages self-generated samples and teacher feedback, significantly boosting T5 model performance on summarization, translation, and reasoning tasks.

Rishabh Agarwal, Nino Vieillard, Yongchao Zhou et al.

OpenMask3D achieves zero-shot open-vocabulary 3D instance segmentation, excelling on ScanNet200's long-tail classes.

Ayça Takmaz, Elisabetta Fedele, Robert W. Sumner et al.

Waymo evaluates ADS safety using diverse methods, emphasizing the importance of event-level reasoning.

Francesca M. Favaro, Trent Victor, Henning Hohnhold et al.

Proposed MME benchmark evaluates 30 multimodal large models across 14 subtasks, measuring perception and cognition with manual instruction design.

Chaoyou Fu, Peixian Chen, Yunhang Shen et al.