Robust Grounding with MLLMs against Occlusion and Small Objects via Language-guided Semantic Cues

While Multimodal Large Language Models (MLLMs) have enhanced grounding capabilities in general scenes, their robustness in crowded scenes remains underexplored. Crowded scenes entail visual challenges (i.e., occlusion and small objects), which impair object semantics and degrade grounding performance. In contrast, language expressions are immune to such degradation and preserve object semantics. In light of these observations, we propose a novel method that overcomes such constraints by leveraging Language-Guided Semantic Cues (LGSCs). Specifically, our approach introduces a Semantic Cue Extractor (SCE) to derive semantic cues of objects from the visual pipeline of an MLLM. We then guide these cues using corresponding text embeddings to produce LGSCs as linguistic semantic priors. Subsequently, they are reintegrated into the original visual pipeline to refine object semantics. Extensive experiments and analyses demonstrate that incorporating LGSCs into an MLLM effectively improves grounding accuracy in crowded scenes.

GTA-Crime: A Synthetic Dataset and Generation Framework for Fatal Violence Detection with Adversarial Snippet-Level Domain Adaptation

Recent advancements in video anomaly detection (VAD) have enabled identification of various criminal activities in surveillance videos, but detecting fatal incidents such as shootings and stabbings remains difficult due to their rarity and ethical issues in data collection. Recognizing this limitation, we introduce GTA-Crime, a fatal video anomaly dataset and generation framework using Grand Theft Auto 5 (GTA5). Our dataset contains fatal situations such as shootings and stabbings, captured from CCTV multiview perspectives under diverse conditions including action types, weather, time of day, and viewpoints. To address the rarity of such scenarios, we also release a framework for generating these types of videos. Additionally, we propose a snippet-level domain adaptation strategy using Wasserstein adversarial training to bridge the gap between synthetic GTA-Crime features and real-world features like UCF-Crime. Experimental results validate our GTA-Crime dataset and demonstrate that incorporating GTA-Crime with our domain adaptation strategy consistently enhances real world fatal violence detection accuracy. Our dataset and the data generation framework are publicly available at https://github.com/ta-ho/GTA-Crime.

DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes

Multimodal Large Language Models (MLLMs) have demonstrated significant visual understanding capabilities, yet their fine-grained visual perception in complex real-world scenarios, such as densely crowded public areas, remains limited. Inspired by the recent success of reinforcement learning (RL) in both LLMs and MLLMs, in this paper, we explore how RL can enhance visual perception ability of MLLMs. Then we develop a novel RL-based framework, Deep Inspection and Perception with RL (DIP-R1) designed to enhance the visual perception capabilities of MLLMs, by comprehending complex scenes and looking through visual instances closely. DIP-R1 guides MLLMs through detailed inspection of visual scene via three simply designed rule-based reward modelings. First, we adopt a standard reasoning reward encouraging the model to include three step-by-step processes: 1) reasoning for understanding visual scenes, 2) observing for looking through interested but ambiguous regions, and 3) decision-making for predicting answer. Second, a variance-guided looking reward is designed to examine uncertain regions for the second observing process. It explicitly enables the model to inspect ambiguous areas, improving its ability to mitigate perceptual uncertainties. Third, we model a weighted precision-recall accuracy reward enhancing accurate decision-making. We explore its effectiveness across diverse fine-grained object detection data consisting of challenging real-world environments, such as densely crowded scenes. Built upon existing MLLMs, DIP-R1 achieves consistent and significant improvement across various in-domain and out-of-domain scenarios. It also outperforms various existing baseline models and supervised fine-tuning methods. Our findings highlight the substantial potential of integrating RL into MLLMs for enhancing capabilities in complex real-world perception tasks.

In-situ and Non-contact Etch Depth Prediction in Plasma Etching via Machine Learning (ANN & BNN) and Digital Image Colorimetry

Precise monitoring of etch depth and the thickness of insulating materials, such as Silicon dioxide and silicon nitride, is critical to ensuring device performance and yield in semiconductor manufacturing. While conventional ex-situ analysis methods are accurate, they are constrained by time delays and contamination risks. To address these limitations, this study proposes a non-contact, in-situ etch depth prediction framework based on machine learning (ML) techniques. Two scenarios are explored. In the first scenario, an artificial neural network (ANN) is trained to predict average etch depth from process parameters, achieving a significantly lower mean squared error (MSE) compared to a linear baseline model. The approach is then extended to incorporate variability from repeated measurements using a Bayesian Neural Network (BNN) to capture both aleatoric and epistemic uncertainty. Coverage analysis confirms the BNN's capability to provide reliable uncertainty estimates. In the second scenario, we demonstrate the feasibility of using RGB data from digital image colorimetry (DIC) as input for etch depth prediction, achieving strong performance even in the absence of explicit process parameters. These results suggest that the integration of DIC and ML offers a viable, cost-effective alternative for real-time, in-situ, and non-invasive monitoring in plasma etching processes, contributing to enhanced process stability, and manufacturing efficiency.

Survey and Evaluation of Converging Architecture in LLMs based on Footsteps of Operations

The advent of the Attention mechanism and Transformer architecture enables contextually natural text generation and compresses the burden of processing entire source information into singular vectors. Based on these two main ideas, model sizes gradually increases to accommodate more precise and comprehensive information, leading to the current state-of-the-art LLMs being very large, with parameters around 70 billion. As the model sizes are growing, the demand for substantial storage and computational capacity increases. This leads to the development of high-bandwidth memory and accelerators, as well as a variety of model architectures designed to meet these requirements. We note that LLM architectures have increasingly converged. This paper analyzes how these converged architectures perform in terms of layer configurations, operational mechanisms, and model sizes, considering various hyperparameter settings. In this paper, we conduct a concise survey of the history of LLMs by tracing the evolution of their operational improvements. Furthermore, we summarize the performance trends of LLMs under various hyperparameter settings using the RTX 6000, which features the state-of-the-art Ada Lovelace architecture. We conclude that even the same model can exhibit different behaviors depending on the hyperparameters or whether it is deployed in server or edge environments.