AINeutralarXiv – CS AI · Jun 106/10
🧠Researchers propose MGAP, a training-free decoding method that reduces hallucinations in multimodal large language models (MLLMs) by selectively suppressing language priors while preserving semantic structure. Unlike previous approaches that blindly penalize language biases, MGAP uses geometry-aware subspace projection to distinguish between helpful and harmful language priors, achieving improved hallucination suppression without degrading model coherence.
AIBullisharXiv – CS AI · Jun 96/10
🧠Researchers propose Robust-U1, a framework enabling Multimodal Large Language Models (MLLMs) to self-recover corrupted visual content through supervised fine-tuning and reinforcement learning. The approach demonstrates state-of-the-art robustness on real-world corruption benchmarks, suggesting that visual self-recovery is a critical mechanism for improving MLLM performance under adversarial conditions.
AINeutralarXiv – CS AI · Jun 95/10
🧠Researchers introduce SMART, a new multimodal AI framework for video moment retrieval that combines audio and visual features with shot-aware token compression to locate specific temporal segments in untrimmed videos. The method demonstrates significant performance improvements on benchmark datasets, achieving 1.61% and 2.59% gains in key metrics over previous state-of-the-art approaches.
AIBullisharXiv – CS AI · Jun 96/10
🧠Researchers propose Dual-Path Vision Token Routing (DPVR), a framework that optimizes multimodal large language models by routing vision tokens away from deep transformer layers where they saturate early, instead fusing visual and textual information only in the final layer. The approach reduces computational overhead by 3% while maintaining competitive performance, challenging the assumption that vision tokens must traverse all deep language-model layers.
AINeutralarXiv – CS AI · Jun 86/10
🧠Researchers introduce MoDA (Modulation Adapter), a lightweight module that improves fine-grained visual grounding in multimodal language models through instruction-guided channel-wise modulation. Testing across 12 benchmarks and three MLLM architectures demonstrates consistent performance improvements with minimal computational overhead, suggesting a practical advancement in how AI systems understand detailed visual instructions.
AIBullisharXiv – CS AI · Jun 56/10
🧠Researchers introduce Brick-Composer, a learning framework that enhances multimodal large language models (MLLMs) with physical assembly capabilities through targeted training on brick construction tasks. The study reveals current MLLMs lack reliable spatial reasoning and fine-grained object recognition needed for real-world assembly, but demonstrates that structured learning approaches can improve performance significantly.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers introduce LongSpace-Bench, a video benchmark for evaluating multimodal AI models' ability to remember and retrieve spatial information across long videos, and propose LongSpace, a memory framework that improves long-horizon spatial reasoning by incorporating 3D structural cues and layer-aware memory retrieval.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers present a hybrid content moderation system for livestreams that combines supervised classification with multimodal similarity matching, achieving 67-76% recall at 80% precision. The production-deployed framework reduces user views of unwanted content by 6-8%, demonstrating scalable AI-driven moderation for user-generated video platforms.
AINeutralarXiv – CS AI · Jun 36/10
🧠Researchers introduce CORE, a conflict-oriented reasoning framework that enhances multimodal large language models to detect AI-generated fake news by identifying semantic and physical inconsistencies across images and text. The approach uses a specially annotated Conflict Attribution Corpus and demonstrates superior generalization to unseen manipulation types compared to existing detection methods.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce Med-Scout, a reinforcement learning framework that addresses a critical flaw in multimodal large language models (MLLMs) used for medical diagnosis: geometric blindness, or the inability to ground outputs in objective spatial constraints. The system uses unlabeled medical images with three proxy tasks to derive supervision signals, achieving 40% performance improvements on a new Med-Scout-Bench benchmark while generalizing to broader medical understanding tasks.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers propose a novel multimodal multi-agent framework that uses graph-based knowledge construction and adaptive retrieval-augmented generation to enable autonomous agents to execute complex workflows more effectively. The system combines offline discovery of workflow topology from execution logs with real-time collaborative verification, demonstrating improved performance in novel scenarios with limited training data.
AIBullisharXiv – CS AI · May 286/10
🧠Researchers introduce VCap, a reinforcement learning reward mechanism that improves visual captioning in multimodal AI models by grounding caption verification in actual visual signals. An 8B parameter model trained with VCap outperforms larger open and closed-source competitors on image and video captioning benchmarks, demonstrating that smarter reward design can enable weak-to-strong generalization in AI training.
AIBullisharXiv – CS AI · May 116/10
🧠Researchers introduce BalCapRL, a reinforcement learning framework that improves multimodal image captioning by balancing three competing objectives: utility-aware correctness, reference coverage, and linguistic quality. The method achieves significant performance gains across multiple models by applying reward-decoupled normalization and length-conditional masking, addressing the trade-offs present in existing captioning approaches.
AINeutralarXiv – CS AI · May 96/10
🧠Researchers introduce ICU-Bench, a new benchmark for testing machine unlearning in multimodal AI models, addressing privacy concerns from large-scale training datasets. The benchmark reveals that current unlearning methods struggle with continuous privacy deletion requests, highlighting a critical gap between theoretical approaches and real-world deployment needs.
AINeutralarXiv – CS AI · May 96/10
🧠Researchers introduce CrossCult-KIBench, a benchmark dataset for evaluating how multimodal large language models (MLLMs) handle cross-cultural knowledge insertion across English, Chinese, and Arabic contexts. The work reveals that current AI models struggle to adapt to specific cultural contexts without degrading performance in other cultures, establishing a new research direction for culturally-aware AI systems.
AIBullisharXiv – CS AI · Apr 146/10
🧠Researchers propose Trajectory Induced Preference Optimization (TIPO), a novel method for training mobile GUI agents to respect user privacy preferences while maintaining task execution capability. The approach addresses the challenge that privacy-conscious users generate structurally different execution patterns than utility-focused users, requiring specialized optimization techniques to properly align agent behavior with individual privacy preferences.
AIBullisharXiv – CS AI · Apr 146/10
🧠Researchers introduce BoxTuning, a novel approach for improving video understanding in multimodal AI models by rendering object bounding boxes directly onto video frames as visual prompts rather than encoding them as text tokens. The method achieves 87-93% reduction in text token usage while maintaining full temporal resolution, demonstrating superior performance on video question-answering tasks.
AIBullisharXiv – CS AI · Apr 146/10
🧠Researchers introduce M³KG-RAG, a novel multimodal retrieval-augmented generation system that enhances large language models by integrating multi-hop knowledge graphs with audio-visual data. The approach improves reasoning depth and answer accuracy by filtering irrelevant information through a new grounding and pruning mechanism called GRASP.
$KG
AIBullisharXiv – CS AI · Apr 66/10
🧠Researchers developed QAPruner, a new framework that simultaneously optimizes vision token pruning and post-training quantization for Multimodal Large Language Models (MLLMs). The method addresses the problem where traditional token pruning can discard important activation outliers needed for quantization stability, achieving 2.24% accuracy improvement over baselines while retaining only 12.5% of visual tokens.
AINeutralarXiv – CS AI · Mar 266/10
🧠Researchers introduce GeoSketch, a neural-symbolic AI framework that solves geometric problems through dynamic visual manipulation, including drawing auxiliary lines and applying transformations. The system combines perception, symbolic reasoning, and interactive sketch actions, achieving superior performance on geometric problem-solving benchmarks compared to static image processing methods.
AINeutralarXiv – CS AI · Mar 176/10
🧠Researchers introduce VTC-Bench, a comprehensive benchmark for evaluating multimodal AI models' ability to use visual tools for complex tasks. The benchmark reveals significant limitations in current models, with leading model Gemini-3.0-Pro achieving only 51% accuracy on multi-tool visual reasoning tasks.
🧠 Gemini
AIBullisharXiv – CS AI · Mar 176/10
🧠Researchers propose ES-Merging, a new framework for combining specialized biological multimodal large language models (MLLMs) by using embedding space signals rather than traditional parameter-based methods. The approach estimates merging coefficients at both layer-wise and element-wise granularities, outperforming existing merging techniques and even task-specific fine-tuned models on cross-modal scientific problems.
AIBullisharXiv – CS AI · Mar 166/10
🧠Researchers developed UNIFIER, a continual learning framework for multimodal large language models (MLLMs) to adapt to changing visual scenarios without catastrophic forgetting. The framework addresses visual discrepancies across different environments like high-altitude, underwater, low-altitude, and indoor scenarios, showing significant improvements over existing methods.
🏢 Hugging Face
AINeutralarXiv – CS AI · Mar 116/10
🧠Researchers introduce EgoCross, a new benchmark to evaluate multimodal AI models on egocentric video understanding across diverse domains like surgery, extreme sports, and industrial settings. The study reveals that current AI models, including specialized egocentric models, struggle with cross-domain generalization beyond common daily activities.
AINeutralarXiv – CS AI · Mar 45/104
🧠Researchers introduce HSSBench, a new benchmark designed to evaluate multimodal large language models (MLLMs) on Humanities and Social Sciences tasks across multiple languages. The benchmark contains over 13,000 samples and reveals significant challenges for current state-of-the-art models in cross-disciplinary reasoning.
