The ability to identify granular materials facilitates the emergence of various new applications in robotics, ranging from cooking at home to truck loading at mining sites. However, granular material identification remains a challenging and underexplored area. In this work, we present a novel interactive material identification framework that enables robots to identify a wide range of granular materials using only a force-torque sensor for perception. Our framework, comprising interactive exploration, feature extraction, and classification stages, prioritizes simplicity and transparency for seamless integration into various manipulation pipelines. We evaluate the proposed approach through extensive experiments with a real-world dataset comprising 11 granular materials, which we also make publicly available. Additionally, we conducted a comprehensive qualitative analysis of the dataset to offer deeper insights into its nature, aiding future development. Our results show that the proposed method is capable of accurately identifying a wide range of granular materials solely relying on force measurements obtained from direct interaction with the materials. Code and dataset are available at: https://irobotics.aalto.fi/indentify_granular/.

Voice assistants (VAs) are becoming a feature of our everyday life. Yet, the user experience (UX) is often limited, leading to underuse, disengagement, and abandonment. Co-designing interactions for VAs with potential end-users can be useful. Crowdsourcing this process online and anonymously may add value. However, most work has been done in the English-speaking West on dialogue data sets. We must be sensitive to cultural differences in language, social interactions, and attitudes towards technology. Our aims were to explore the value of co-designing VAs in the non-Western context of Japan and demonstrate the necessity of cultural sensitivity. We conducted an online elicitation study (N = 135) where Americans (n = 64) and Japanese people (n = 71) imagined dialogues (N = 282) and activities (N = 73) with future VAs. We discuss the implications for coimagining interactions with future VAs, offer design guidelines for the Japanese and English-speaking US contexts, and suggest opportunities for cultural plurality in VA design and scholarship.

Saudi Arabia now has a matching pair of male and female humanoid robots whose AI is coded to be culturally aligned with the nation's values. Just weeks after the male robot, Muhammed, groped a women's bottom at its debut event, its creator has revealed that a female version, Sarah, was programmed to refuse conversations about sex or politics. Discussing either topic openly is illegal for real Saudi women under Sharia law. Sara'knows that she's a girl, she's 25 years old, she's 1.62m [5ft, 3in], she's wearing Saudi clothing,' according to the CEO of the Riyadh-based firm QSS AI & Robots. Saudi Arabia now has a matching pair of male and female humanoid robots with artificial intelligence (AI) that's culturally Saudi - meaning the'woman' (Sara, above) won't discuss forbidden topics like sex and politics A 3D design of the Sara robot's endo-skeleton (left), which provided a first step toward Saudi company QSS's manufacturing of the female robot.

The expansion of a quartz mine is providing a breath of life to a small, desolate North Carolina town that is now set to become a powerhouse for the world's AI revolution. Sibelco's mines have been extracting quartz in Spruce Pine since the 1970s but its 500 million investment between now and 2027 will fuel the global demand for semiconductors. The expansion comes as Nvidia has become the leading global manufacturer of semiconductor chips, holding roughly 80 percent of the global market share as of last year. The global quartz market value reached 8.5 billion in 2022 and is expected to reach nearly 18.7 billion by 2031, with China topping other countries as the largest customer. The Sibelco mine is located in Spruce Pine, North Carolina and is the top producer of the world's high-purity quartz Sibelco's mining sites are located in the small town of Spruce Pine, about two hours northwest of Charlotte, and increasing its high-purity quartz output will make the US the leading supplier of the mineral.

Figure has developed a full-body humanoid robot, Figure-01, that can walk, talk and interact. Le Van Tam is no stranger to how the vagaries of global trade can determine the fortunes of small coffee farmers like him. He first planted coffee in a patch of land outside Buon Ma Thuot city in Vietnam's Central Highland region in 1995. For years, his focus was on quantity, not quality. Tam used ample amounts of fertilizer and pesticides to boost his yields, and global prices determined how well he did.

Modern contextual lemmatizers often rely on automatically induced Shortest Edit Scripts (SES), namely, the number of edit operations to transform a word form into its lemma. In fact, different methods of computing SES have been proposed as an integral component in the architecture of several state-of-the-art contextual lemmatizers currently available. However, previous work has not investigated the direct impact of SES in the final lemmatization performance. In this paper we address this issue by focusing on lemmatization as a token classification task where the only input that the model receives is the word-label pairs in context, where the labels correspond to previously induced SES. Thus, by modifying in our lemmatization system only the SES labels that the model needs to learn, we may then objectively conclude which SES representation produces the best lemmatization results. We experiment with seven languages of different morphological complexity, namely, English, Spanish, Basque, Russian, Czech, Turkish and Polish, using multilingual and language-specific pre-trained masked language encoder-only models as a backbone to build our lemmatizers. Comprehensive experimental results, both in- and out-of-domain, indicate that computing the casing and edit operations separately is beneficial overall, but much more clearly for languages with high-inflected morphology. Notably, multilingual pre-trained language models consistently outperform their language-specific counterparts in every evaluation setting.

The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI). However, replicating such advancements in open-source models has been challenging. This paper introduces InternLM2, an open-source LLM that outperforms its predecessors in comprehensive evaluations across 6 dimensions and 30 benchmarks, long-context modeling, and open-ended subjective evaluations through innovative pre-training and optimization techniques. The pre-training process of InternLM2 is meticulously detailed, highlighting the preparation of diverse data types including text, code, and long-context data. InternLM2 efficiently captures long-term dependencies, initially trained on 4k tokens before advancing to 32k tokens in pre-training and fine-tuning stages, exhibiting remarkable performance on the 200k ``Needle-in-a-Haystack" test. InternLM2 is further aligned using Supervised Fine-Tuning (SFT) and a novel Conditional Online Reinforcement Learning from Human Feedback (COOL RLHF) strategy that addresses conflicting human preferences and reward hacking. By releasing InternLM2 models in different training stages and model sizes, we provide the community with insights into the model's evolution.

New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data. The task is addressed as a feature-clustering problem and recent studies augment instance representation. However, existing methods fail to capture cluster-friendly representations, since they show less capability to effectively control and coordinate within-cluster and between-cluster distances. Tailored to the NID problem, we propose a Robust and Adaptive Prototypical learning (RAP) framework for globally distinct decision boundaries for both known and new intent categories. Specifically, a robust prototypical attracting learning (RPAL) method is designed to compel instances to gravitate toward their corresponding prototype, achieving greater within-cluster compactness. To attain larger between-cluster separation, another adaptive prototypical dispersing learning (APDL) method is devised to maximize the between-cluster distance from the prototype-to-prototype perspective. Experimental results evaluated on three challenging benchmarks (CLINC, BANKING, and StackOverflow) of our method with better cluster-friendly representation demonstrate that RAP brings in substantial improvements over the current state-of-the-art methods (even large language model) by a large margin (average +5.5% improvement).

Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks by leveraging the fine-grained information that phrases offer. In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information. However, the lack of specific training data and models are the primary challenges to achieve our goal. As a result, we extract pairs of cross-lingual phrases using word alignment information automatically induced from parallel sentences. Subsequently, we train our Cross-lingual Contextualized Phrase Retriever (CCPR) using contrastive learning, which encourages the hidden representations of phrases with similar contexts and semantics to align closely. Comprehensive experiments on both the cross-lingual phrase retrieval task and a downstream task, i.e, machine translation, demonstrate the effectiveness of CCPR. On the phrase retrieval task, CCPR surpasses baselines by a significant margin, achieving a top-1 accuracy that is at least 13 points higher. When utilizing CCPR to augment the large-language-model-based translator, it achieves average gains of 0.7 and 1.5 in BERTScore for translations from X=>En and vice versa, respectively, on WMT16 dataset. Our code and data are available at \url{https://github.com/ghrua/ccpr_release}.

Crop classification is of critical importance due to its role in studying crop pattern changes, resource management, and carbon sequestration. When employing data-driven techniques for its prediction, utilizing various temporal data sources is necessary. Deep learning models have proven to be effective for this task by mapping time series data to high-level representation for prediction. However, they face substantial challenges when dealing with multiple input patterns. The literature offers limited guidance for Multi-View Learning (MVL) scenarios, as it has primarily focused on exploring fusion strategies with specific encoders and validating them in local regions. In contrast, we investigate the impact of simultaneous selection of the fusion strategy and the encoder architecture evaluated on a global-scale cropland and crop-type classifications. We use a range of five fusion strategies (Input, Feature, Decision, Ensemble, Hybrid) and five temporal encoder architectures (LSTM, GRU, TempCNN, TAE, L-TAE) as possible MVL model configurations. The validation is on the CropHarvest dataset that provides optical, radar, and weather time series, and topographic information as input data. We found that in scenarios with a limited number of labeled samples, a unique configuration is insufficient for all the cases. Instead, a specialized combination, including encoder and fusion strategy, should be meticulously sought. To streamline this search process, we suggest initially identifying the optimal encoder architecture tailored for a particular fusion strategy, and then determining the most suitable fusion strategy for the classification task. We provide a technical framework for researchers exploring crop classification or related tasks through a MVL approach.