AINeutralarXiv – CS AI · Apr 136/10
🧠Researchers investigate how multimodal large language models (MLLMs) can assist with usability evaluation of user interfaces by analyzing text and visual context together. The study compares MLLM-generated assessments against expert evaluations, finding that these models can effectively prioritize usability issues by severity and offer complementary insights to traditional resource-intensive evaluation methods.
AINeutralarXiv – CS AI · Apr 106/10
🧠Q-Probe introduces a novel agentic framework for scaling image quality assessment to high-resolution images by addressing limitations in existing reinforcement learning approaches. The research presents Vista-Bench, a new benchmark for fine-grained degradation analysis, and demonstrates state-of-the-art performance across multiple resolution scales through context-aware probing mechanisms.
AINeutralarXiv – CS AI · Apr 76/10
🧠Researchers identify critical limitations in current Multimodal Large Language Models' ability to understand physics and physical world dynamics. They propose Scene Dynamic Field (SDF), a new approach using physics simulators that achieves up to 20.7% performance improvements on fluid dynamics tasks.
AIBullisharXiv – CS AI · Apr 66/10
🧠Researchers have developed ForgeryGPT, a new multimodal AI framework that can detect, localize, and explain image forgeries through natural language interaction. The system combines advanced computer vision techniques with large language models to provide interpretable analysis of tampered images, addressing limitations in current forgery detection methods.
🧠 GPT-4
AINeutralarXiv – CS AI · Mar 276/10
🧠Researchers introduce ReLope, a new routing method for multimodal large language models that uses KL-regularized LoRA probes and attention mechanisms to improve cost-performance balance. The method addresses the challenge of degraded probe performance when visual inputs are added to text-only LLMs.
AINeutralarXiv – CS AI · Mar 276/10
🧠Researchers benchmarked 20 multimodal AI models on neuroimaging tasks using MRI and CT scans, finding that while technical attributes like imaging modality are nearly solved, diagnostic reasoning remains challenging. Gemini-2.5-Pro and GPT-5-Chat showed strongest diagnostic performance, while open-source MedGemma-1.5-4B demonstrated promising results under few-shot prompting.
🏢 Meta🧠 GPT-5🧠 Gemini
AIBullisharXiv – CS AI · Mar 276/10
🧠Photon is a new framework that efficiently processes 3D medical imaging for AI visual question answering by using variable-length token sequences and adaptive compression. The system reduces computational costs while maintaining accuracy through instruction-conditioned token scheduling and custom gradient propagation techniques.
AINeutralarXiv – CS AI · Mar 276/10
🧠A benchmarking study reveals demographic bias in multimodal large language models used for face verification, testing nine models across different ethnicity and gender groups. The research found that face-specialized models outperform general-purpose MLLMs, but accuracy doesn't correlate with fairness, and bias patterns differ from traditional face recognition systems.
🏢 Meta
AIBullisharXiv – CS AI · Mar 276/10
🧠Researchers introduce TimeLens, a family of multimodal large language models optimized for video temporal grounding that outperforms existing open-source models and even surpasses proprietary models like GPT-5 and Gemini-2.5-Flash. The work addresses critical data quality issues in existing benchmarks and introduces improved training datasets and algorithmic design principles.
🧠 GPT-5🧠 Gemini
AINeutralarXiv – CS AI · Mar 266/10
🧠Researchers introduce GameplayQA, a new benchmarking framework for evaluating multimodal large language models on 3D virtual agent perception and reasoning tasks. The framework uses densely annotated multiplayer gameplay videos with 2.4K diagnostic QA pairs, revealing substantial performance gaps between current frontier models and human-level understanding.
AIBullisharXiv – CS AI · Mar 96/10
🧠Researchers introduce Place-it-R1, an AI framework that uses Multimodal Large Language Models to insert objects into videos while maintaining physical realism. The system employs Chain-of-Thought reasoning to ensure inserted objects interact naturally with their environment, addressing the gap between visual quality and physical plausibility in video editing.
AIBullisharXiv – CS AI · Mar 55/10
🧠FeedAIde is a new AI-powered mobile app feedback system that uses Multimodal Large Language Models to guide users through submitting detailed bug reports and feature requests. The iOS framework captures contextual information like screenshots and asks follow-up questions to improve feedback quality, with testing showing enhanced completeness compared to traditional feedback forms.
AIBullisharXiv – CS AI · Mar 36/108
🧠AdaFocus is a new training-free framework for adaptive visual reasoning in Multimodal Large Language Models that addresses perceptual redundancy and spatial attention issues. The system uses a two-stage pipeline with confidence-based cropping decisions and semantic-guided localization, achieving 4x faster inference than existing methods while improving accuracy.
AINeutralarXiv – CS AI · Mar 36/104
🧠Researchers introduce EgoNight, the first comprehensive benchmark for nighttime egocentric vision understanding, featuring day-night aligned videos and visual question answering tasks. The benchmark reveals significant performance drops in state-of-the-art multimodal large language models when operating under low-light conditions.
AIBullisharXiv – CS AI · Mar 36/103
🧠Researchers propose HIMM, a new memory framework for AI embodied agents that separates episodic and semantic memory to improve long-term performance. The system achieves significant gains on benchmarks, with 7.3% improvement in LLM-Match and 11.4% in LLM MatchXSPL, addressing key challenges in deploying multimodal language models as embodied agent brains.
AIBullisharXiv – CS AI · Mar 26/1018
🧠Researchers developed RD-MLDG, a new framework that uses multimodal large language models with reasoning chains to improve domain generalization in deep learning. The approach addresses challenges in cross-domain visual recognition by leveraging reasoning capabilities rather than just visual feature invariance, achieving state-of-the-art performance on standard benchmarks.
AINeutralarXiv – CS AI · Mar 26/1012
🧠Researchers introduce Ref-Adv, a new benchmark for testing multimodal large language models' visual reasoning capabilities in referring expression tasks. The benchmark reveals that current MLLMs, despite performing well on standard datasets like RefCOCO, rely heavily on shortcuts and show significant gaps in genuine visual reasoning and grounding abilities.
AIBullisharXiv – CS AI · Mar 26/1014
🧠Researchers propose a data-efficient framework to convert generative Multimodal Large Language Models into universal embedding models without extensive pre-training. The method uses hierarchical embedding prompts and Self-aware Hard Negative Sampling to achieve competitive performance on embedding benchmarks using minimal training data.
AIBullisharXiv – CS AI · Feb 276/108
🧠Researchers have developed FactGuard, an AI framework that uses multimodal large language models and reinforcement learning to detect video misinformation. The system addresses limitations of existing models by implementing iterative reasoning processes and external tool integration to verify information across video content.
AINeutralarXiv – CS AI · Apr 145/10
🧠Researchers have developed GEVO, a glyph-driven fine-tuning framework for multimodal large language models designed to analyze the evolution of ancient Chinese characters. The study introduces a comprehensive benchmark with 11 tasks and over 130,000 instances, demonstrating that even smaller 2B-scale models can achieve significant performance improvements in understanding character evolution and historical text transformation.
AINeutralarXiv – CS AI · Mar 44/102
🧠Researchers developed new prompting-based approaches using multimodal large language models to generate real-time video commentary that considers both content relevance and timing. The study introduces dynamic interval-based decoding that adjusts prediction timing based on utterance duration, showing improved alignment with human commentary patterns without requiring model fine-tuning.
AINeutralarXiv – CS AI · Mar 34/103
🧠Researchers introduced VisJudge-Bench, the first comprehensive benchmark for evaluating AI models' ability to assess visualization quality and aesthetics, revealing significant gaps between advanced models like GPT-5 and human expert judgment. They developed VisJudge, a specialized model that achieved 60.5% better correlation with human assessments compared to GPT-5.
