Mitigating climate change requires transforming agriculture to minimize environ mental impact and build climate resilience. Regenerative agricultural practices enhance soil organic carbon (SOC) levels, thus improving soil health and sequestering carbon. A challenge to increasing regenerative agriculture practices is cheaply measuring SOC over time and understanding how SOC is affected by regenerative agricultural practices and other environmental factors and farm management practices. To address this challenge, we introduce an AI-driven Soil Organic Carbon Copilot that automates the ingestion of complex multi-resolution, multi-modal data to provide large-scale insights into soil health and regenerative practices. Our data includes extreme weather event data (e.g., drought and wildfire incidents), farm management data (e.g., cropland information and tillage predictions), and SOC predictions. We find that integrating public data and specialized models enables large-scale, localized analysis for sustainable agriculture. In comparisons of agricultural practices across California counties, we find evidence that diverse agricultural activity may mitigate the negative effects of tillage; and that while extreme weather conditions heavily affect SOC, composting may mitigate SOC loss. Finally, implementing role-specific personas empowers agronomists, farm consultants, policymakers, and other stakeholders to implement evidence-based strategies that promote sustainable agriculture and build climate resilience.

Long-Context Question Answering (LCQA), a challenging task, aims to reason over long-context documents to yield accurate answers to questions. Existing long-context Large Language Models (LLMs) for LCQA often struggle with the "lost in the middle" issue. Retrieval-Augmented Generation (RAG) mitigates this issue by providing external factual evidence. However, its chunking strategy disrupts the global long-context information, and its low-quality retrieval in long contexts hinders LLMs from identifying effective factual details due to substantial noise. To this end, we propose LongRAG, a general, dual-perspective, and robust LLM-based RAG system paradigm for LCQA to enhance RAG's understanding of complex long-context knowledge (i.e., global information and factual details). We design LongRAG as a plug-and-play paradigm, facilitating adaptation to various domains and LLMs. Extensive experiments on three multi-hop datasets demonstrate that LongRAG significantly outperforms long-context LLMs (up by 6.94%), advanced RAG (up by 6.16%), and Vanilla RAG (up by 17.25%). Furthermore, we conduct quantitative ablation studies and multi-dimensional analyses, highlighting the effectiveness of the system's components and fine-tuning strategies. Data and code are available at https://github.com/QingFei1/LongRAG.

Silicon Valley billionaires and anti-poverty activists don't have a lot in common, but in recent years they've joined forces around a shared enthusiasm: programs that guarantee a basic income. Tech entrepreneurs like Sam Altman, chief executive of OpenAI, have promoted direct cash transfers to low-income Americans as a way to cushion them from what the entrepreneurs anticipate could be widespread job losses caused by artificial intelligence. Some local politicians and community leaders, concerned about growing wealth inequality, have also put their faith in these stipends, known as unconditional cash or, in their most ambitious form, a universal basic income. Dozens of small pilot projects testing unconditional cash transfers have popped up in communities around the country, from Alaska to Stockton, Calif. Andrew Yang, an entrepreneur, put the idea of 1,000 monthly payments for all adults at the center of his 2020 presidential campaign.

Dog guides are favored by blind and low-vision (BLV) individuals for their ability to enhance independence and confidence by reducing safety concerns and increasing navigation efficiency compared to traditional mobility aids. However, only a relatively small proportion of BLV individuals work with dog guides due to their limited availability and associated maintenance responsibilities. There is considerable recent interest in addressing this challenge by developing legged guide dog robots. This study was designed to determine critical aspects of the handler-guide dog interaction and better understand handler needs to inform guide dog robot development. We conducted semi-structured interviews and observation sessions with 23 dog guide handlers and 5 trainers. Thematic analysis revealed critical limitations in guide dog work, desired personalization in handler-guide dog interaction, and important perspectives on future guide dog robots. Grounded on these findings, we discuss pivotal design insights for guide dog robots aimed for adoption within the BLV community.

Fixed point lattice actions are designed to have continuum classical properties unaffected by discretization effects and reduced lattice artifacts at the quantum level. They provide a possible way to extract continuum physics with coarser lattices, thereby allowing to circumvent problems with critical slowing down and topological freezing toward the continuum limit. A crucial ingredient for practical applications is to find an accurate and compact parametrization of a fixed point action, since many of its properties are only implicitly defined. Here we use machine learning methods to revisit the question of how to parametrize fixed point actions. In particular, we obtain a fixed point action for four-dimensional SU(3) gauge theory using convolutional neural networks with exact gauge invariance. The large operator space allows us to find superior parametrizations compared to previous studies, a necessary first step for future Monte Carlo simulations.

Lattice gauge-equivariant convolutional neural networks (L-CNNs) can be used to form arbitrarily shaped Wilson loops and can approximate any gauge-covariant or gauge-invariant function on the lattice. Here we use L-CNNs to describe fixed point (FP) actions which are based on renormalization group transformations. FP actions are classically perfect, i.e., they have no lattice artifacts on classical gauge-field configurations satisfying the equations of motion, and therefore possess scale invariant instanton solutions. FP actions are tree-level Symanzik-improved to all orders in the lattice spacing and can produce physical predictions with very small lattice artifacts even on coarse lattices. We find that L-CNNs are much more accurate at parametrizing the FP action compared to older approaches. They may therefore provide a way to circumvent critical slowing down and topological freezing towards the continuum limit.

The application of Artificial Intelligence in the medical market brings up increasing concerns but aids in more timely diagnosis of silent progressing diseases like Diabetic Retinopathy. In order to diagnose Diabetic Retinopathy (DR), ophthalmologists use color fundus images, or pictures of the back of the retina, to identify small distinct features through a difficult and time-consuming process. Our work creates a novel CNN model and identifies the severity of DR through fundus image input. We classified 4 known DR features, including micro-aneurysms, cotton wools, exudates, and hemorrhages, through convolutional layers and were able to provide an accurate diagnostic without additional user input. The proposed model is more interpretable and robust to overfitting. We present initial results with a sensitivity of 97% and an accuracy of 71%. Our contribution is an interpretable model with similar accuracy to more complex models. With that, our model advances the field of DR detection and proves to be a key step towards AI-focused medical diagnosis.

Given a language model (LM), maximum probability is a poor decoding objective for open-ended generation, because it produces short and repetitive text. On the other hand, sampling can often produce incoherent text that drifts from the original topics. We propose contrastive decoding (CD), a reliable decoding approach that optimizes a contrastive objective subject to a plausibility constraint. The contrastive objective returns the difference between the likelihood under a large LM (called the expert, e.g. OPT-13B) and a small LM (called the amateur, e.g. OPT-125M), and the constraint ensures that the outputs are plausible. CD is inspired by the fact that the failures of larger LMs (e.g., repetition, incoherence) are even more prevalent in smaller LMs, and that this difference signals which texts should be preferred. CD requires zero additional training, and produces higher quality text than decoding from the larger LM alone. It also works across model scales (OPT-13B and GPT2-1.5B) and significantly outperforms four strong decoding algorithms (e.g., nucleus, top-k) in automatic and human evaluations across wikipedia, news and story domains.

While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g. action plan generation) have primarily been studied as separate topics. In this paper, we explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner, allowing for greater synergy between the two: reasoning traces help the model induce, track, and update action plans as well as handle exceptions, while actions allow it to interface with external sources, such as knowledge bases or environments, to gather additional information. We apply our approach, named ReAct, to a diverse set of language and decision making tasks and demonstrate its effectiveness over state-of-the-art baselines, as well as improved human interpretability and trustworthiness over methods without reasoning or acting components. Concretely, on question answering (HotpotQA) and fact verification (Fever), ReAct overcomes issues of hallucination and error propagation prevalent in chain-of-thought reasoning by interacting with a simple Wikipedia API, and generates human-like task-solving trajectories that are more interpretable than baselines without reasoning traces. On two interactive decision making benchmarks (ALFWorld and WebShop), ReAct outperforms imitation and reinforcement learning methods by an absolute success rate of 34% and 10% respectively, while being prompted with only one or two in-context examples. Project site with code: https://react-lm.github.io

For the last decade, Amazon has been building an army of robot employees to sort packages and move products safely around its warehouses. Now the company has unveiled its latest robot called Proteus, which it describes as its'first fully autonomous mobile robot'. Proteus is designed to work alongside humans, moving large trolleys full of packages around the warehouse floor. The robot uses Amazon's own safety, perception, and navigation technology to move around autonomously and avoid bumping into human workers. 'Historically, it's been difficult to safely incorporate robotics in the same physical space as people,' the company said in a blog post.