Multimodal learning plays a critical role in e-commerce recommendation platforms today, enabling accurate recommendations and product understanding. However, existing vision-language models, such as CLIP, face key challenges in e-commerce recommendation systems: 1) Weak object-level alignment, where global image embeddings fail to capture fine-grained product attributes, leading to suboptimal retrieval performance; 2) Ambiguous textual representations, where product descriptions often lack contextual clarity, affecting cross-modal matching; and 3) Domain mismatch, as generic vision-language models may not generalize well to e-commerce-specific data. To address these limitations, we propose a framework, VL-CLIP, that enhances CLIP embeddings by integrating Visual Grounding for fine-grained visual understanding and an LLM-based agent for generating enriched text embeddings. Visual Grounding refines image representations by localizing key products, while the LLM agent enhances textual features by disambiguating product descriptions. Our approach significantly improves retrieval accuracy, multimodal retrieval effectiveness, and recommendation quality across tens of millions of items on one of the largest e-commerce platforms in the U.S., increasing CTR by 18.6%, ATC by 15.5%, and GMV by 4.0%. Additional experimental results show that our framework outperforms vision-language models, including CLIP, FashionCLIP, and GCL, in both precision and semantic alignment, demonstrating the potential of combining object-aware visual grounding and LLM-enhanced text representation for robust multimodal recommendations.

Large Language Models (LLMs) can exhibit latent biases towards specific nationalities even when explicit demographic markers are not present. In this work, we introduce a novel name-based benchmarking approach derived from the Bias Benchmark for QA (BBQ) dataset to investigate the impact of substituting explicit nationality labels with culturally indicative names, a scenario more reflective of real-world LLM applications. Our novel approach examines how this substitution affects both bias magnitude and accuracy across a spectrum of LLMs from industry leaders such as OpenAI, Google, and Anthropic. Our experiments show that small models are less accurate and exhibit more bias compared to their larger counterparts. For instance, on our name-based dataset and in the ambiguous context (where the correct choice is not revealed), Claude Haiku exhibited the worst stereotypical bias scores of 9%, compared to only 3.5% for its larger counterpart, Claude Sonnet, where the latter also outperformed it by 117.7% in accuracy. Additionally, we find that small models retain a larger portion of existing errors in these ambiguous contexts. For example, after substituting names for explicit nationality references, GPT-4o retains 68% of the error rate versus 76% for GPT-4o-mini, with similar findings for other model providers, in the ambiguous context. Our research highlights the stubborn resilience of biases in LLMs, underscoring their profound implications for the development and deployment of AI systems in diverse, global contexts.

Conversational Information Retrieval (CIR) systems, while offering intuitive access to information, face a significant challenge: reliably handling unanswerable questions to prevent the generation of misleading or hallucinated content. Traditional approaches often rely on external classifiers, which can introduce inconsistencies with the core generative Large Language Models (LLMs). This paper introduces Self-Aware LLM for Unanswerability (SALU), a novel approach that deeply integrates unanswerability detection directly within the LLM's generative process. SALU is trained using a multi-task learning framework for both standard Question Answering (QA) and explicit abstention generation for unanswerable queries. Crucially, it incorporates a confidence-score-guided reinforcement learning with human feedback (RLHF) phase, which explicitly penalizes hallucinated responses and rewards appropriate abstentions, fostering intrinsic self-awareness of knowledge boundaries. Through extensive experiments on our custom-built C-IR_Answerability dataset, SALU consistently outperforms strong baselines, including hybrid LLM-classifier systems, in overall accuracy for correctly answering or abstaining from questions. Human evaluation further confirms SALU's superior reliability, achieving high scores in factuality, appropriate abstention, and, most importantly, a dramatic reduction in hallucination, demonstrating its ability to robustly "know when to say 'I don't know'."

We evaluate the impact of large language model-based clinical decision support in live care. In partnership with Penda Health, a network of primary care clinics in Nairobi, Kenya, we studied AI Consult, a tool that serves as a safety net for clinicians by identifying potential documentation and clinical decision-making errors. AI Consult integrates into clinician workflows, activating only when needed and preserving clinician autonomy. We conducted a quality improvement study, comparing outcomes for 39,849 patient visits performed by clinicians with or without access to AI Consult across 15 clinics. Visits were rated by independent physicians to identify clinical errors. Clinicians with access to AI Consult made relatively fewer errors: 16% fewer diagnostic errors and 13% fewer treatment errors. In absolute terms, the introduction of AI Consult would avert diagnostic errors in 22,000 visits and treatment errors in 29,000 visits annually at Penda alone. In a survey of clinicians with AI Consult, all clinicians said that AI Consult improved the quality of care they delivered, with 75% saying the effect was "substantial". These results required a clinical workflow-aligned AI Consult implementation and active deployment to encourage clinician uptake. We hope this study demonstrates the potential for LLM-based clinical decision support tools to reduce errors in real-world settings and provides a practical framework for advancing responsible adoption.

Recent advancements in Large Language Models (LLMs) have catalyzed a paradigm shift from static prediction systems to agentic AI agents capable of reasoning, interacting with tools, and adapting to complex tasks. While LLM-based agentic systems have shown promise across many domains, their application to medical imaging remains in its infancy. In this work, we introduce AURA, the first visual linguistic explainability agent designed specifically for comprehensive analysis, explanation, and evaluation of medical images. By enabling dynamic interactions, contextual explanations, and hypothesis testing, AURA represents a significant advancement toward more transparent, adaptable, and clinically aligned AI systems. We highlight the promise of agentic AI in transforming medical image analysis from static predictions to interactive decision support. Leveraging Qwen-32B, an LLM-based architecture, AURA integrates a modular toolbox comprising: (i) a segmentation suite with phase grounding, pathology segmentation, and anatomy segmentation to localize clinically meaningful regions; (ii) a counterfactual image-generation module that supports reasoning through image-level explanations; and (iii) a set of evaluation tools including pixel-wise difference-map analysis, classification, and advanced state-of-the-art components to assess diagnostic relevance and visual interpretability.

Large language models can be quantized to reduce inference time latency, model size, and energy consumption, thereby delivering a better user experience at lower cost. A challenge exists to deliver quantized models with minimal loss of accuracy in reasonable time, and in particular to do so without requiring mechanisms incompatible with specialized inference accelerators. Here, we demonstrate a simple, end-to-end quantization-aware training approach that, with an increase in total model training budget of less than 0.1%, outperforms the leading published quantization methods by large margins on several modern benchmarks, with both base and instruct model variants. The approach easily generalizes across different model architectures, can be applied to activations, cache, and weights, and requires the introduction of no additional operations to the model other than the quantization itself.

High-quality speech generation for low-resource languages, such as many Indian languages, remains a significant challenge due to limited data and diverse linguistic structures. Duration prediction is a critical component in many speech generation pipelines, playing a key role in modeling prosody and speech rhythm. While some recent generative approaches choose to omit explicit duration modeling, often at the cost of longer training times. We retain and explore this module to better understand its impact in the linguistically rich and data-scarce landscape of India. We train a non-autoregressive Continuous Normalizing Flow (CNF) based speech model using publicly available Indian language data and evaluate multiple duration prediction strategies for zero-shot, speaker-specific generation. Our comparative analysis on speech-infilling tasks reveals nuanced trade-offs: infilling based predictors improve intelligibility in some languages, while speaker-prompted predictors better preserve speaker characteristics in others. These findings inform the design and selection of duration strategies tailored to specific languages and tasks, underscoring the continued value of interpretable components like duration prediction in adapting advanced generative architectures to low-resource, multilingual settings.

Social media platforms serve as a significant medium for sharing personal emotions, daily activities, and various life events, ensuring individuals stay informed about the latest developments. From the initiation of an account, users progressively expand their circle of friends or followers, engaging actively by posting, commenting, and sharing content. Over time, user behavior on these platforms evolves, influenced by demographic attributes and the networks they form. In this study, we present a novel approach that leverages open-source models Llama-3-Instruct, Mistral-7B-Instruct, Gemma-7B-IT through prompt engineering, combined with GPT-2, BERT, and RoBERTa using a joint embedding technique, to analyze and predict the evolution of user behavior on social media over their lifetime. Our experiments demonstrate the potential of these models to forecast future stages of a user's social evolution, including network changes, future connections, and shifts in user activities. Experimental results highlight the effectiveness of our approach, with GPT-2 achieving the lowest perplexity (8.21) in a Cross-modal configuration, outperforming RoBERTa (9.11) and BERT, and underscoring the importance of leveraging Cross-modal configurations for superior performance. This approach addresses critical challenges in social media, such as friend recommendations and activity predictions, offering insights into the trajectory of user behavior. By anticipating future interactions and activities, this research aims to provide early warnings about potential negative outcomes, enabling users to make informed decisions and mitigate risks in the long term.

We introduce TD-Interpreter, a specialized ML tool that assists engineers in understanding complex timing diagrams (TDs), originating from a third party, during their design and verification process. TD-Interpreter is a visual question-answer environment which allows engineers to input a set of TDs and ask design and verification queries regarding these TDs. We implemented TD-Interpreter with multimodal learning by fine-tuning LLaVA, a lightweight 7B Multimodal Large Language Model (MLLM). To address limited training data availability, we developed a synthetic data generation workflow that aligns visual information with its textual interpretation. Our experimental evaluation demonstrates the usefulness of TD-Interpreter which outperformed untuned GPT-4o by a large margin on the evaluated benchmarks.

Retrieval Augmented Generation (RAG) has gradually emerged as a promising paradigm for enhancing the accuracy and factual consistency of content generated by large language models (LLMs). However, existing RAG studies primarily focus on retrieving isolated segments using similarity-based matching methods, while overlooking the intrinsic connections between them. This limitation hampers performance in RAG tasks. To address this, we propose QMKGF, a Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval Augmented Generation. First, we design prompt templates and employ general-purpose LLMs to extract entities and relations, thereby generating a knowledge graph (KG) efficiently. Based on the constructed KG, we introduce a multi-path subgraph construction strategy that incorporates one-hop relations, multi-hop relations, and importance-based relations, aiming to improve the semantic relevance between the retrieved documents and the user query. Subsequently, we designed a query-aware attention reward model that scores subgraph triples based on their semantic relevance to the query. Then, we select the highest score subgraph and enrich subgraph with additional triples from other subgraphs that are highly semantically relevant to the query. Finally, the entities, relations, and triples within the updated subgraph are utilised to expand the original query, thereby enhancing its semantic representation and improving the quality of LLMs' generation. We evaluate QMKGF on the SQuAD, IIRC, Culture, HotpotQA, and MuSiQue datasets. On the HotpotQA dataset, our method achieves a ROUGE-1 score of 64.98\%, surpassing the BGE-Rerank approach by 9.72 percentage points (from 55.26\% to 64.98\%). Experimental results demonstrate the effectiveness and superiority of the QMKGF approach.