Continual and interactive robot learning is a challenging problem as the robot is present with human users who expect the robot to learn novel skills to solve novel tasks perpetually with sample efficiency. In this work we present a framework for robots to query and learn visuo-motor robot skills and task relevant information via natural language dialog interactions with human users. Previous approaches either focus on improving the performance of instruction following agents, or passively learn novel skills or concepts. Instead, we used dialog combined with a language-skill grounding embedding to query or confirm skills and/or tasks requested by a user. To achieve this goal, we developed and integrated three different components for our agent. Firstly, we propose a novel visual-motor control policy ACT with Low Rank Adaptation (ACT-LoRA), which enables the existing SoTA ACT model to perform few-shot continual learning. Secondly, we develop an alignment model that projects demonstrations across skill embodiments into a shared embedding allowing us to know when to ask questions and/or demonstrations from users. Finally, we integrated an existing LLM to interact with a human user to perform grounded interactive continual skill learning to solve a task. Our ACT-LoRA model learns novel fine-tuned skills with a 100% accuracy when trained with only five demonstrations for a novel skill while still maintaining a 74.75% accuracy on pre-trained skills in the RLBench dataset where other models fall significantly short. We also performed a human-subjects study with 8 subjects to demonstrate the continual learning capabilities of our combined framework. We achieve a success rate of 75% in the task of sandwich making with the real robot learning from participant data demonstrating that robots can learn novel skills or task knowledge from dialogue with non-expert users using our approach.

Given that Large Language Models (LLMs) have made significant progress in writing code, can they now be used to autonomously reproduce results from research repositories? Such a capability would be a boon to the research community, helping researchers validate, understand, and extend prior work. To advance towards this goal, we introduce SUPER, the first benchmark designed to evaluate the capability of LLMs in setting up and executing tasks from research repositories. SUPERaims to capture the realistic challenges faced by researchers working with Machine Learning (ML) and Natural Language Processing (NLP) research repositories. Our benchmark comprises three distinct problem sets: 45 end-to-end problems with annotated expert solutions, 152 sub problems derived from the expert set that focus on specific challenges (e.g., configuring a trainer), and 602 automatically generated problems for larger-scale development. We introduce various evaluation measures to assess both task success and progress, utilizing gold solutions when available or approximations otherwise. We show that state-of-the-art approaches struggle to solve these problems with the best model (GPT-4o) solving only 16.3% of the end-to-end set, and 46.1% of the scenarios. This illustrates the challenge of this task, and suggests that SUPER can serve as a valuable resource for the community to make and measure progress.

Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant resources for training from scratch. This paper introduces Gated Slot Attention (GSA), which enhances Attention with Bounded-memory-Control (ABC) by incorporating a gating mechanism inspired by Gated Linear Attention (GLA). Essentially, GSA comprises a two-layer GLA linked via softmax, utilizing context-aware memory reading and adaptive forgetting to improve memory capacity while maintaining compact recurrent state size. This design greatly enhances both training and inference efficiency through GLA's hardware-efficient training algorithm and reduced state size. Additionally, retaining the softmax operation is particularly beneficial in "finetuning pretrained Transformers to RNNs" (T2R) settings, reducing the need for extensive training from scratch. Extensive experiments confirm GSA's superior performance in scenarios requiring in-context recall and in T2R settings.

The rapid adoption of large language models (LLMs) in recommender systems (RS) presents new challenges in understanding and evaluating their biases, which can result in unfairness or the amplification of stereotypes. Traditional fairness evaluations in RS primarily focus on collaborative filtering (CF) settings, which may not fully capture the complexities of LLMs, as these models often inherit biases from large, unregulated data. This paper proposes a normative framework to benchmark consumer fairness in LLM-powered recommender systems (RecLLMs). We critically examine how fairness norms in classical RS fall short in addressing the challenges posed by LLMs. We argue that this gap can lead to arbitrary conclusions about fairness, and we propose a more structured, formal approach to evaluate fairness in such systems. Our experiments on the MovieLens dataset on consumer fairness, using in-context learning (zero-shot vs. few-shot) reveal fairness deviations in age-based recommendations, particularly when additional contextual examples are introduced (ICL-2). Statistical significance tests confirm that these deviations are not random, highlighting the need for robust evaluation methods. While this work offers a preliminary discussion on a proposed normative framework, our hope is that it could provide a formal, principled approach for auditing and mitigating bias in RecLLMs. The code and dataset used for this work will be shared at "gihub-anonymized".

Recent advancements in artificial intelligence (AI), particularly in deep learning and large language models (LLMs), have accelerated their integration into medicine. However, these developments have also raised public concerns about the safe application of AI. In healthcare, these concerns are especially pertinent, as the ethical and secure deployment of AI is crucial for protecting patient health and privacy. This review examines potential risks in AI practices that may compromise safety in medicine, including reduced performance across diverse populations, inconsistent operational stability, the need for high-quality data for effective model tuning, and the risk of data breaches during model development and deployment. For medical practitioners, patients, and researchers, LLMs provide a convenient way to interact with AI and data through language. However, their emergence has also amplified safety concerns, particularly due to issues like hallucination. Second part of this article explores safety issues specific to LLMs in medical contexts, including limitations in processing complex logic, challenges in aligning AI objectives with human values, the illusion of understanding, and concerns about diversity. Thoughtful development of safe AI could accelerate its adoption in real-world medical settings.

Retrieval-Augmented Generation (RAG) has been empirically shown to enhance the performance of large language models (LLMs) in knowledge-intensive domains such as healthcare, finance, and legal contexts. Given a query, RAG retrieves relevant documents from a corpus and integrates them into the LLMs' generation process. In this study, we investigate the adversarial robustness of RAG, focusing specifically on examining the retrieval system. First, across 225 different setup combinations of corpus, retriever, query, and targeted information, we show that retrieval systems are vulnerable to universal poisoning attacks in medical Q\&A. In such attacks, adversaries generate poisoned documents containing a broad spectrum of targeted information, such as personally identifiable information. When these poisoned documents are inserted into a corpus, they can be accurately retrieved by any users, as long as attacker-specified queries are used. To understand this vulnerability, we discovered that the deviation from the query's embedding to that of the poisoned document tends to follow a pattern in which the high similarity between the poisoned document and the query is retained, thereby enabling precise retrieval. Based on these findings, we develop a new detection-based defense to ensure the safe use of RAG. Through extensive experiments spanning various Q\&A domains, we observed that our proposed method consistently achieves excellent detection rates in nearly all cases.

Large language models (LLMs) have shown superb capability of modeling multimodal signals including audio and text, allowing the model to generate spoken or textual response given a speech input. However, it remains a challenge for the model to recognize personal named entities, such as contacts in a phone book, when the input modality is speech. In this work, we start with a speech recognition task and propose a retrieval-based solution to contextualize the LLM: we first let the LLM detect named entities in speech without any context, then use this named entity as a query to retrieve phonetically similar named entities from a personal database and feed them to the LLM, and finally run context-aware LLM decoding. In a voice assistant task, our solution achieved up to 30.2% relative word error rate reduction and 73.6% relative named entity error rate reduction compared to a baseline system without contextualization. Notably, our solution by design avoids prompting the LLM with the full named entity database, making it highly efficient and applicable to large named entity databases.

This project, titled "Machine Translation with Large Language Models: Decoder-only vs. Encoder-Decoder," aims to develop a multilingual machine translation (MT) model. Focused on Indian regional languages, especially Telugu, Tamil, and Malayalam, the model seeks to enable accurate and contextually appropriate translations across diverse language pairs. By comparing Decoder-only and Encoder-Decoder architectures, the project aims to optimize translation quality and efficiency, advancing cross-linguistic communication tools.The primary objective is to develop a model capable of delivering high-quality translations that are accurate and contextually appropriate. By leveraging large language models, specifically comparing the effectiveness of Decoder-only and Encoder-Decoder architectures, the project seeks to optimize translation performance and efficiency across multilingual contexts. Through rigorous experimentation and analysis, this project aims to advance the field of machine translation, contributing valuable insights into the effectiveness of different model architectures and paving the way for enhanced cross-linguistic communication tools.

Term normalization is the process of mapping a term from free text to a standardized concept and its machine-readable code in an ontology. Accurate normalization of terms that capture phenotypic differences between patients and diseases is critical to the success of precision medicine initiatives. A large language model (LLM), such as GPT-4o, can normalize terms to the Human Phenotype Ontology (HPO), but it may retrieve incorrect HPO IDs. Reported accuracy rates for LLMs on these tasks may be inflated due to imbalanced test datasets skewed towards high-frequency terms. In our study, using a comprehensive dataset of 268,776 phenotype annotations for 12,655 diseases from the HPO, GPT-4o achieved an accuracy of 13.1% in normalizing 11,225 unique terms. However, the accuracy was unevenly distributed, with higher-frequency and shorter terms normalized more accurately than lower-frequency and longer terms. Feature importance analysis, using SHAP and permutation methods, identified low-term frequency as the most significant predictor of normalization errors. These findings suggest that training and evaluation datasets for LLM-based term normalization should balance low- and high-frequency terms to improve model performance, particularly for infrequent terms critical to precision medicine.

When Elon Musk shared an image showing Kamala Harris dressed as a "communist dictator" on X last week, it was quite obviously a fake, seeing as Harris is neither a communist nor, to the best of our knowledge, a Soviet cosplayer. And, as many observers noted, the woman in the photo, presumably generated by X's Grok tool, had only a passing resemblance to the vice president. "AI still is unable to accurately depict Kamala Harris," one X user wrote. "Grok put old Eva Longoria in a snazzy outfit and called it a day," another quipped, noting the similarity of the "dictator" pictured to the Desperate Housewives star. "AI just CANNOT replicate Kamala Harris," a third posted.