The University of California, Riverside (UCR), founded in 1954, is a public institution and part of the UC system, located in Southern California’s Inland Empire. UCR is recognized for its diverse student body, strong research centers, and colleges spanning the Humanities, Engineering, and Natural Sciences, offering a wide range of undergraduate programs. We have collaborated with UC Riverside on AI system optimization, including deep learning architecture refinement and robust classification techniques. Our joint efforts contribute to the development of scalable models suitable for deployment in diverse applications. Please read about our latest news and collaborative publications with the University of California, Riverside.

Posts

Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation

/in /by

Radiology Report Generation (RRG) is a critical step toward automating healthcare workflows, facilitating accurate patient assessments, and reducing the workload of medical professionals. Despite recent progress in Large Medical Vision-Language Models (Med-VLMs), generating radiology reports that are both visually grounded and clinically accurate remains a significant challenge. Existing approaches often rely on large labeled corpora for pre-training, costly task-specific preference data, or retrieval-based methods. However, these strategies do not adequately mitigate hallucinations arising from poor cross-modal alignment between visual and linguistic representations. To address these limitations, we propose VALOR:Visual Alignment of Medical Vision-Language Models for GrOunded Radiology Report Generation. Our method introduces a reinforcement learning-based post-alignment framework utilizing Group-Relative Proximal Optimization (GRPO). The training proceeds in two stages: (1) improving the Med-VLM with textual rewards to encourage clinically precise terminology, and (2) aligning the vision projection module of the textually grounded model with disease findings, thereby guiding attention toward image re gions most relevant to the diagnostic task. Extensive experiments on multiple benchmarks demonstrate that VALOR substantially improves factual accuracy and visual grounding, achieving significant performance gains over state-of-the-art report generation methods.

Read more

iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning

/0 Comments/in /by

Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of structured inductive biases. As vision is often the sole modality available for such analysis (i.e. no LiDAR, GPS, etc.), existing video-basedvision-language models (V-VLMs) struggle with spatial reasoning, causal inference, and explainability of events in the input video. To this end, we introduce iFinder, a structured semantic grounding framework that decouples perception from reasoning by translating dash-cam videos into a hierarchical, interpretable data structure for LLMs. iFinder operates as a modular, training-free pipeline that employs pretrained vision models to extract critical cues—object pose, lane positions, and object trajectories—which are hierarchically organized into frame and video-level structures. Combined with a three-block prompting strategy, it enables step-wise, grounded reasoning for the LLM to refine a peer V-VLM’s outputs and provide accurate reasoning. Evaluations on four public dash-cam video benchmarks show that iFinder’s proposed grounding with domain-specific cues—especially object orientation and global context—significantly outperforms end-to-end V-VLMs on four zero-shot driving benchmarks, with up to 39% gains in accident reasoning accuracy. By grounding LLMs with driving domain-specific representations, iFinder offers a zero-shot, interpretable, and reliable alternativeto end-to-end V-VLMs for post-hoc driving video understanding

Read more

NeurIPS 2025 in San Diego from November 30th to December 5th, 2025

/in /by

NEC Laboratories America is heading to San Diego for NeurIPS 2025, where our researchers will present cutting-edge work spanning optimization, AI systems, language modeling, and trustworthy machine learning. This year’s lineup highlights breakthroughs in areas like multi-agent coordination, scalable training, efficient inference, and techniques for detecting LLM-generated text. Together, these contributions reflect our commitment to advancing fundamental science while building real-world solutions that strengthen industry and society. We’re excited to join the global AI community in San Diego from November 30 to December 5 to share our latest innovations.

Read more

iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning

/in /by

Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of structured inductive biases. As vision is often the sole modality available for such analysis (i.e., no LiDAR, GPS, etc.), existing video-based vision-language models (V-VLMs) struggle with spatial reasoning, causal inference, and explainability of events in the input video. To this end, we introduce iFinder, a structured semantic grounding framework that decouples perception from reasoning by translating dash-cam videos into a hierarchical, interpretable data structure for LLMs. iFinder operates as a modular, training-free pipeline that employs pretrained vision models to extract critical cues — object pose, lane positions, and object trajectories — which are hierarchically organized into frame- and video-level structures. Combined with a three-block prompting strategy, it enables step-wise, grounded reasoning for the LLM to refine a peer V-VLM’s outputs and provide accurate reasoning. Evaluations on four public dash-cam video benchmarks show that iFinder’s proposed grounding with domain-specific cues, especially object orientation and global context, significantly outperforms end-to-end V-VLMs on four zero-shot driving benchmarks, with up to 39% gains in accident reasoning accuracy. By grounding LLMs with driving domain-specific representations, iFinder offers a zero-shot, interpretable, and reliable alternative to end-to-end V-VLMs for post-hoc driving video understanding.

Read more

National Intern Day at NEC Laboratories America: Celebrating the Next Generation of Innovators

/in /by

On National Intern Day, NEC Laboratories America celebrates the bright minds shaping tomorrow’s technology. Each summer, interns from top universities work side-by-side with our researchers on real-world challenges in AI, cybersecurity, data science, and more. From groundbreaking research to team-building events, our interns contribute fresh ideas and bold thinking that power NEC’s innovation engine.

Read more

Chain-of-region: Visual Language Models Need Details for Diagram Analysis

/in /by

Visual Language Models (VLMs) like GPT-4V have broadened the scope of LLM applications, yet they face significant challenges in accurately processing visual details, particularly in scientific diagrams. This paper explores the necessity of meticulous visual detail collection and region decomposition for enhancing the performance of VLMs in scientific diagram analysis. We propose a novel approach that combines traditional computer vision techniques with VLMs to systematically decompose diagrams into discernible visual elements and aggregate essential metadata. Our method employs techniques in OpenCV library to identify and label regions, followed by a refinement process using shape detection and region merging algorithms, which are particularly suited to the structured nature of scientific diagrams. This strategy not only improves the granularity and accuracy of visual information processing but also extends the capabilities of VLMs beyond their current limitations. We validate our approach through a series of experiments that demonstrate enhanced performance in diagram analysis tasks, setting a new standard for integrating visual and language processing in a multimodal context.

Read more

Distantly-Supervised Joint Extraction with Noise-Robust Learning

/in /by

Joint entity and relation extraction is a process that identifies entity pairs and their relations using a single model. We focus on the problem of joint extraction in distantly-labeled data,whose labels are generated by aligning entity mentions with the corresponding entity and relation tags using a knowledge base (KB). One key challenge is the presence of noisy labels arising from both incorrect entity and relation annotations, which significantly impairs the quality of supervised learning. Existing approaches, either considering only one source of noise or making decisions using external knowledge, cannot well-utilize significant information in the training data. We propose DENRL, a generalizable framework that 1) incorporates a lightweight transformer backbone into a sequence labeling scheme for joint tagging, and 2) employs a noise-robust framework that regularizes the tagging model with significant relation patterns and entity-relation dependencies, then iteratively self-adapts to instances with less noise from both sources. Surprisingly, experiments1 on two benchmark datasets show that DENRL, using merely its own parametric distribution and simple data-driven heuristics, outperforms large language model-based baselines by a large margin with better interpretability.

Read more

Efficient Transformer Encoders for Mask2Former-style Models

/in /by

Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be taxing on deployed devices. One way to overcome this challenge is by adapting the computation level to the specific needs of the input image rather than the current one size-fits-all approach. To this end, we introduce ECO-M2F or EffiCient TransfOrmer Encoders for Mask2Former-style models. Noting that the encoder module of M2F-style models incur high resource-intensive computations, ECO-M2F provides a strategy to self-select the number of hidden layers in the encoder, conditioned on the input image. To enable this self-selection ability for providing a balance between performance and computational efficiency, we present a three-step recipe. The first step is to train the parent architecture to enable early exiting from the encoder. The second step is to create a derived dataset of the ideal number of encoder layers required for each training example. The third step is to use the aforementioned derived dataset to train a gating network that predicts the number of encoder layers to be used, conditioned on input image. Additionally, to change the computational-accuracy trade off, only steps two and three need to be repeated which significantly reduces retraining time. Experiments on the public datasets show that the proposed approach reduces expected encoder computational cost while maintaining performance, adapts to various user compute resources, is flexible in architecture configurations, and can be extended beyond the segmentation task to object detection.

Read more

GLAD: Content-Aware Dynamic Graphs for Log Anomaly Detection

/in /by

Logs play a crucial role in system monitoring and debugging by recording valuable system information, including events and status. Although various methods have been proposed to detect anomalies in log sequences, they often overlook the significance of considering relationships among system components, such as services and users, which can be identified from log contents. Understanding these relationships is vital for identifying anomalies and their underlying causes. To address this issue, we introduce GLAD, a Graph-based Log Anomaly Detection framework designed to detect relational anomalies in system logs. GLAD incorporates log semantics, relationship patterns, and sequential patterns into a unified framework for anomaly detection. Specifically, GLAD first introduces a field extraction module that utilizes prompt-based few-shot learning to extract essential field information, such as services and users, from log contents. Then GLAD constructs dynamic log graphs for sliding windows by leveraging the log events and extracted fields. These graphs represent events and fields as nodes and their relationships as edges. Subsequently, we propose atemporal-attentive graph edge anomaly detection model for identifying anomalous relationships in the dynamic log graphs. This model employs a Graph Neural Network (GNN)-based encoder enhanced with transformers to capture structural, content, and temporal features. We evaluate our proposed method on three datasets, and the results demonstrate the effectiveness of GLAD in detecting anomalies indicated by varying relation patterns.

Read more

Efficient Controllable Multi-Task Architectures

/in /by

We aim to train a multi-task model such that users can adjust the desired compute budget and relative importance of task performances after deployment, without retraining. This enables optimizing performance for dynamically varying user needs, without heavy computational overhead to train and save models for various scenarios. To this end, we propose a multi-task model consisting of a shared encoder and task-specific decoders where both encoder and decoder channel widths are slimmable. Our key idea is to control the task importance by varying the capacities of task-specific decoders, while controlling the total computational cost by jointly adjusting the encoder capacity. This improves overall accuracy by allowing a stronger encoder for a given budget, increases control over computational cost, and delivers high-quality slimmed sub-architectures based on user’s constraints. Our training strategy involves a novel `Configuration-Invariant Knowledge Distillation’ loss that enforces backbone representations to be invariant under different runtime width configurations to enhance accuracy. Further, we present a simple but effective search algorithm that translates user constraints to runtime width configurations of both the shared encoder and task decoders, for sampling the sub-architectures. The key rule for the search algorithm is to provide a larger computational budget to the higher preferred task decoder, while searching a shared encoder configuration that enhances the overall MTL performance. Various experiments on three multi-task benchmarks (PASCALContext, NYUDv2, and CIFAR100-MTL) with diverse backbone architectures demonstrate the advantage of our approach. For example, our method shows a higher controllability by 33.5% in the NYUD-v2 dataset over prior methods, while incurring much less compute cost.

Read more