Related papers: Sci-Reasoning: A Dataset Decoding AI Innovation Pa…
As Natural Language Processing (NLP) systems become increasingly integrated into human social life, these technologies will need to increasingly rely on social intelligence. Although there are many valuable datasets that benchmark isolated…
In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions. Describing scientific tables goes beyond…
Artificial intelligence (AI) is reshaping scientific discovery, evolving from specialized computational tools into autonomous research partners. We position Agentic Science as a pivotal stage within the broader AI for Science paradigm,…
Current advances in AI and its applicability have highlighted the need to ensure its trustworthiness for legal, ethical, and even commercial reasons. Sub-symbolic machine learning algorithms, such as the LLMs, simulate reasoning but…
The rapid expansion of research across machine learning, vision, and language has produced a volume of publications that is increasingly difficult to synthesize. Traditional bibliometric tools rely mainly on metadata and offer limited…
Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…
The Abstraction and Reasoning Corpus (ARC) poses a stringent test of general AI capabilities, requiring solvers to infer abstract patterns from only a handful of examples. Despite substantial progress in deep learning, state-of-the-art…
Artificial intelligence (AI) has emerged as a promising tool for channel state information (CSI) feedback. While recent research primarily focuses on improving feedback accuracy on a specific dataset through novel architectures, the…
Generative AI (GenAI) tools are radically expanding the scope and capability of automation in knowledge work such as academic research. While promising for augmenting cognition and streamlining processes, AI-assisted research tools may also…
Advocates for Neuro-Symbolic Artificial Intelligence (NeSy) assert that combining deep learning with symbolic reasoning will lead to stronger AI than either paradigm on its own. As successful as deep learning has been, it is generally…
Designing wise AI policy is a grand challenge for society. To design such policy, policymakers should place a premium on rigorous evidence and scientific consensus. While several mechanisms exist for evidence generation, and nascent…
Synthesizing clinical evidence largely relies on systematic reviews of clinical trials and retrospective analyses from medical literature. However, the rapid expansion of publications presents challenges in efficiently identifying,…
AI has proven highly successful at urban planning analysis -- learning patterns from data to predict future conditions. The next frontier is AI-assisted decision-making: agents that recommend sites, allocate resources, and evaluate…
The rapid growth of scientific literature demands robust tools for automated survey-generation. However, current large language model (LLM)-based methods often lack in-depth analysis, structural coherence, and reliable citations. To address…
Recent advancements in large reasoning models (LRMs) like DeepSeek-R1 and OpenAI o1 series have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length by Chain-of-Thought (CoT). However, a…
Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a generative framework…
Artificial Intelligence (AI) is advancing at an unprecedented pace, with clear potential to enhance decision-making and productivity. Yet, the collaborative decision-making process between humans and AI remains underdeveloped, often falling…
Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…
Bridging continuous perceptual signals and discrete symbolic reasoning is a fundamental challenge in AI systems that must operate under uncertainty. We present a neuro-symbolic framework that explicitly models and propagates uncertainty…
Recent years have seen rapid advances in AI-driven image generation. Early diffusion models emphasized perceptual quality, while newer multimodal models like GPT-4o-image integrate high-level reasoning, improving semantic understanding and…