In the intricate landscape of modern healthcare, medical image classification emerges as a pivotal task, driving crucial decisions in diagnosis, treatment planning, and patient management. This process involves the systematic categorization of various types of medical imagery--including X-rays, CT scans, MRIs, and ultrasound--into distinct classes that assist healthcare professionals in identifying anomalies, understanding physiological phenomena, and detecting diseases at early stages. The reliability and precision of image classification are paramount, given that these determinations form the bedrock upon which medical practitioners build their diagnostic and therapeutic strategies, directly impacting patient outcomes. With an increasing influx of complex imaging data and a growing need for rapid, accurate interpretation, the medical sector faces significant pressure to evolve beyond traditional analysis methods, necessitating innovative solutions that enhance the efficiency and accuracy of image classification. The advent of large foundation models in artificial intelligence has ushered in a transformative era of computational capabilities. These models, characterized by their extensive scale, diverse training datasets, and impressive adaptability, have demonstrated profound impacts across various domains.

We construct the first provable watermarking scheme for language models with public detectability or verifiability: we use a private key for watermarking and a public key for watermark detection. Our protocol is the first watermarking scheme that does not embed a statistical signal in generated text. Rather, we directly embed a publicly-verifiable cryptographic signature using a form of rejection sampling. We show that our construction meets strong formal security guarantees and preserves many desirable properties found in schemes in the private-key watermarking setting. In particular, our watermarking scheme retains distortion-freeness and model agnosticity. We implement our scheme and make empirical measurements over open models in the 7B parameter range. Our experiments suggest that our watermarking scheme meets our formal claims while preserving text quality.

The automatic extraction of biomedical entities and their interaction from unstructured data remains a challenging task due to the limited availability of expert-labeled standard datasets. In this paper, we introduce PETAI-LOR, a retrieval-based language framework that is augmented by tailored chunk scorer. Unlike previous retrieval-augmented language models (LM) that retrieve relevant documents by calculating the similarity between the input sentence and the candidate document set, PETAILOR segments the sentence into chunks and retrieves the relevant chunk from our pre-computed chunk-based relational key-value memory. Moreover, in order to comprehend the specific requirements of the LM, PETAI-LOR adapt the tailored chunk scorer to the LM. We also introduce GM-CIHT, an expert annotated biomedical triple extraction dataset with more relation types. This dataset is centered on the non-drug treatment and general biomedical domain. Additionally, we investigate the efficacy of triple extraction models trained on general domains when applied to the biomedical domain. Our experiments reveal that PETAI-LOR achieves state-of-the-art performance on GM-CIHT

Large language models have shown breakthrough potential in many NLP domains. Here we consider their use for stylometry, specifically authorship identification in Early Modern English drama. We find both promising and concerning results; LLMs are able to accurately predict the author of surprisingly short passages but are also prone to confidently misattribute texts to specific authors. A fine-tuned t5-large model outperforms all tested baselines, including logistic regression, SVM with a linear kernel, and cosine delta, at attributing small passages. However, we see indications that the presence of certain authors in the model's pre-training data affects predictive results in ways that are difficult to assess.

Generative language models (LMs) are increasingly used for document class-prediction tasks and promise enormous improvements in cost and efficiency. Existing research often examines simple classification tasks, but the capability of LMs to classify on complex or specialized tasks is less well understood. We consider a highly complex task that is challenging even for humans: the classification of legal reasoning according to jurisprudential philosophy. Using a novel dataset of historical United States Supreme Court opinions annotated by a team of domain experts, we systematically test the performance of a variety of LMs. We find that generative models perform poorly when given instructions (i.e. prompts) equal to the instructions presented to human annotators through our codebook. Our strongest results derive from fine-tuning models on the annotated dataset; the best performing model is an in-domain model, LEGAL-BERT. We apply predictions from this fine-tuned model to study historical trends in jurisprudence, an exercise that both aligns with prominent qualitative historical accounts and points to areas of possible refinement in those accounts. Our findings generally sound a note of caution in the use of generative LMs on complex tasks without fine-tuning and point to the continued relevance of human annotation-intensive classification methods.

Despite considerable performance improvements, current conversational AI systems often fail to meet user expectations. We discuss several pragmatic limitations of current conversational AI systems. We illustrate pragmatic limitations with examples that are syntactically appropriate, but have clear pragmatic deficiencies. We label our complaints as "Turing Test Triggers" (TTTs) as they indicate where current conversational AI systems fall short compared to human behavior. We develop a taxonomy of pragmatic considerations intended to identify what pragmatic competencies a conversational AI system requires and discuss implications for the design and evaluation of conversational AI systems.

Large Language Models (LLMs) are evolving to integrate multiple modalities, such as text, image, and audio into a unified linguistic space. We envision a future direction based on this framework where conceptual entities defined in sequences of text can also be imagined as modalities. Such a formulation has the potential to overcome the cognitive and computational limitations of current models. Several illustrative examples of such potential implicit modalities are given. Along with vast promises of the hypothesized structure, expected challenges are discussed as well.

Generalist robot manipulators need to learn a wide variety of manipulation skills across diverse environments. Current robot training pipelines rely on humans to provide kinesthetic demonstrations or to program simulation environments and to code up reward functions for reinforcement learning. Such human involvement is an important bottleneck towards scaling up robot learning across diverse tasks and environments. We propose Generation to Simulation (Gen2Sim), a method for scaling up robot skill learning in simulation by automating generation of 3D assets, task descriptions, task decompositions and reward functions using large pre-trained generative models of language and vision. We generate 3D assets for simulation by lifting open-world 2D object-centric images to 3D using image diffusion models and querying LLMs to determine plausible physics parameters. Given URDF files of generated and human-developed assets, we chain-of-thought prompt LLMs to map these to relevant task descriptions, temporal decompositions, and corresponding python reward functions for reinforcement learning. We show Gen2Sim succeeds in learning policies for diverse long horizon tasks, where reinforcement learning with non temporally decomposed reward functions fails. Gen2Sim provides a viable path for scaling up reinforcement learning for robot manipulators in simulation, both by diversifying and expanding task and environment development, and by facilitating the discovery of reinforcement-learned behaviors through temporal task decomposition in RL. Our work contributes hundreds of simulated assets, tasks and demonstrations, taking a step towards fully autonomous robotic manipulation skill acquisition in simulation.

Applications of robotics (such as telepresence, transportation, elder-care, remote health care, cleaning, warehouse logistics, and delivery) are bringing significant changes in individuals' lives and are having profound social impact. Despite the envisioned potential of robotics, the goal of ubiquitous robot assistants augmenting quality of life (and quality of work life) has not yet been realized. Key challenges lie in the complexities of four overarching human-centric objectives that such systems must aim for: 1) improving quality of life of people, especially marginalized communities; 2) anticipating and mitigating unintended negative consequences of technological development; 3) enabling robots to adapt to the desires and needs of human counterparts; 4) respecting the need for human autonomy and agency. Pursuing these objectives requires an integrated cohort of technologists, behavioral scientists and social scientists with a shared vision to pursue a deep, multidisciplinary understanding of how robots interact with individuals and society. We introduce a new term, socially cognizant robotics, to describe this multi-faceted interdisciplinary branch of technology. The emerging practitioner, the socially cognizant roboticist, represents the convergence of socially aware technologists, who can develop intelligent devices that adapt to human and social behavior; and technology-aware social scientists and policymakers, who can translate studies of robotics' social effects into actionable and technically-viable principles and policies. A primary element of socially cognizant robotics is a deliberate "invitation to the table" for social scientists, who bring analytical perspectives and methods that are not typically present in robotics. These perspectives cover two levels of human-technology interaction that we view as essential: the human-robot dyad (Section 2) and the robot-society dyad (Section 3). Figure 1 illustrates how these levels might operate in the context of the workplace and everyday life.

Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for increasingly advanced AI systems to pose existential risks. This paper reviews the evidence for existential risks from AI via misalignment, where AI systems develop goals misaligned with human values, and power-seeking, where misaligned AIs actively seek power. The review examines empirical findings, conceptual arguments and expert opinion relating to specification gaming, goal misgeneralization, and power-seeking. The current state of the evidence is found to be concerning but inconclusive regarding the existence of extreme forms of misaligned power-seeking. Strong empirical evidence of specification gaming combined with strong conceptual evidence for power-seeking make it difficult to dismiss the possibility of existential risk from misaligned power-seeking. On the other hand, to date there are no public empirical examples of misaligned power-seeking in AI systems, and so arguments that future systems will pose an existential risk remain somewhat speculative. Given the current state of the evidence, it is hard to be extremely confident either that misaligned power-seeking poses a large existential risk, or that it poses no existential risk. The fact that we cannot confidently rule out existential risk from AI via misaligned power-seeking is cause for serious concern.