AINeutralarXiv – CS AI · Jun 116/10
🧠Researchers developed instruction-based vector steering to redirect temporal attention in Large Audio-Language Models (LALMs), enabling these systems to concentrate on acoustically relevant regions without retraining. The technique achieves 60-68% accuracy in locating queried sound events, substantially outperforming standard prompting methods, revealing how LALMs encode temporal structure in audio understanding.
AIBullisharXiv – CS AI · Jun 116/10
🧠Researchers introduce MultiToP, a framework that reduces hallucinations in video language models by selectively replacing unreliable visual tokens before text generation. The method achieves 50.60% F1 score improvement on hallucination benchmarks while maintaining general video understanding performance, demonstrating that targeted token refinement can enhance multimodal AI reliability without modifying base models.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce IMUG-Bench, a comprehensive benchmark designed to evaluate unified multimodal models (UMMs) on their ability to handle multi-turn interleaved image-text dialogues. The benchmark reveals that current models struggle with exposure bias in generation tasks and that test-time scaling strategies like Chain-of-Thought can improve performance.
AIBullisharXiv – CS AI · Jun 96/10
🧠Researchers introduce MOSS-Video-Preview, a cross-attention architecture enabling real-time video understanding where models process frames continuously and revise answers as new information arrives. The approach achieves 5x speedup in time-to-first-token and 2.7x higher decoding throughput compared to decoder-only models, while maintaining competitive offline performance.
AINeutralarXiv – CS AI · Jun 96/10
🧠LargeMonitor is a new framework that uses large pretrained foundation models to detect and diagnose distribution shifts in online task-free continual learning systems without requiring explicit task labels or training-coupled optimization. The approach decouples drift detection from adaptation strategy selection, enabling more precise responses to different types of data stream variations.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce OmniGameArena, a comprehensive UE5-based benchmark for evaluating vision-language model agents across diverse game environments (solo, PvP, cooperative), along with the Improvement Dynamics Curve methodology that tracks agent performance evolution through iterative refinement rather than single snapshots.
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 propose Efficient Operator Search, a differentiable framework that automates the design of token-reduction operators for multimodal foundation models. The approach unifies previously distinct manual techniques like pruning and merging into a shared search space, discovering hybrid operators that achieve better accuracy-efficiency trade-offs than hand-designed baselines.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce Partial Information Decomposition (PID), a framework for analyzing how multimodal language models integrate vision and language inputs by separating unique, redundant, and synergistic contributions. The analysis reveals distinct modality-use patterns across task types and identifies visual dominance as a bottleneck in audio-visual fusion systems.
AIBullisharXiv – CS AI · Jun 26/10
🧠Researchers developed EviOSAHS, an evidence-grounded AI framework that combines visual analysis of facial features with clinical data to screen for obstructive sleep apnea, achieving 94.86% sensitivity and outperforming direct multimodal prompting approaches. The system decomposes facial images into seven anatomical queries before final clinical adjudication, providing a more reliable and auditable screening workflow than traditional foundation model prompting.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce MLLM-Microscope, a novel analytical system that examines the internal representations of multimodal large language models (MLLMs) by measuring linearity, intrinsic dimension, and anisotropy across transformer layers. Testing on LLaVA-NeXT and OmniFusion reveals that modality fusion approaches significantly influence how embeddings behave within the model architecture, with OmniFusion demonstrating more consistent dimensional properties across layers.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers introduce FAM-Bench, a multimodal benchmark dataset containing 2,500 expert-verified instances designed to evaluate AI models' ability to assess food suitability for specific health conditions. The benchmark addresses a gap in existing food AI systems by testing health-aware reasoning through dish suitability assessment and comparative analysis tasks across 13 diet-related conditions.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers introduce PInVerify, an offline benchmark for training embodied AI agents to verify whether objects match fine-grained descriptions through active viewpoint selection. The benchmark includes 3,000 episodes across 18 object categories and evaluates multimodal language models at on-device scale, with best results reaching 85.6% accuracy using fine-tuned approaches.
AIBearisharXiv – CS AI · May 286/10
🧠A comprehensive study reveals that multimodal large language models exhibit significant hallucination problems in agricultural imaging tasks, with image interpretation achieving only 63-75% zero-shot accuracy and text-to-image generation producing up to 91% biologically inconsistent scenes. These findings highlight critical reliability gaps that could undermine the trustworthiness of AI-driven agricultural platforms.
🧠 GPT-5🧠 Gemini
AINeutralarXiv – CS AI · May 126/10
🧠Researchers demonstrate that overlaying coordinate grids on chart images significantly improves multimodal LLM accuracy for data extraction tasks, reducing error rates from 25.5% to 19.5%. This spatial priming approach outperforms semantic methods like Chain-of-Thought prompting, suggesting that explicit spatial context is more effective than high-level semantic guidance for current-generation vision-language models.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce FreqAdapter, a parameter-efficient fine-tuning method that operates in the frequency domain rather than signal space to adapt pre-trained models like CLIP and LLaVA. The approach uses multi-scale adaptation strategies and text-guided prompts to improve model efficiency and performance with minimal training parameters and fast convergence.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce PPU-Bench, a benchmark for testing personalized partial unlearning in multimodal AI models, addressing the challenge of selectively removing sensitive memorized information while preserving model utility. The study reveals significant trade-offs between forgetting target knowledge and retaining non-target facts, proposing Boundary-Aware Optimization as a solution for fine-grained factual control.
AIBullisharXiv – CS AI · May 126/10
🧠Researchers demonstrate that large multimodal models develop internal visual representations when solving spatial reasoning tasks, improving puzzle-solving accuracy from 83% to 89% by integrating visual tokens into chain-of-thought reasoning. The findings suggest AI systems spontaneously form world models without explicit visual supervision, with practical applications for enhancing spatial reasoning capabilities.
AINeutralarXiv – CS AI · May 116/10
🧠LithoBench introduces a comprehensive benchmark dataset for evaluating large multimodal models on remote-sensing lithology interpretation, containing 10,000 expert-annotated instances across cognitive levels from identification to reasoning. The research reveals significant gaps in current vision-language models' ability to handle knowledge-intensive geological tasks, highlighting the challenges of applying general-purpose AI to specialized domain expertise.
AIBullisharXiv – CS AI · May 76/10
🧠Researchers introduce JASTIN, an instruction-driven framework that combines frozen audio encoders with fine-tuned LLMs to evaluate generative audio models with zero-shot capabilities. The approach achieves state-of-the-art correlation with human ratings across speech, sound, and music evaluation tasks without task-specific retraining.
AINeutralarXiv – CS AI · May 46/10
🧠Researchers benchmarked leading multimodal AI models (GPT-4o, Gemini, Claude, etc.) against standard computer vision tasks and found they perform as respectable generalists but lag significantly behind specialized models. The study reveals these foundation models excel at semantic tasks but struggle with geometric understanding, with GPT-4o leading non-reasoning models while reasoning variants show promise on 3D tasks.
🧠 GPT-4🧠 Claude🧠 Gemini
AINeutralarXiv – CS AI · Apr 146/10
🧠Researchers reveal that unified multimodal models (UMMs) combining language and vision capabilities fail to achieve genuine synergy, exhibiting divergent information patterns that undermine reasoning transfer to image synthesis. An information-theoretic framework analyzing ten models shows pseudo-unification stems from asymmetric encoding and conflicting response patterns, with only models implementing contextual prediction achieving stronger text-to-image reasoning.
AINeutralarXiv – CS AI · Apr 136/10
🧠Researchers introduce 3D-VCD, an inference-time framework that reduces hallucinations in 3D-LLM embodied agents by contrasting predictions against distorted scene graphs. The method addresses failures specific to 3D spatial reasoning without requiring model retraining, advancing reliability in embodied AI systems.
AIBearisharXiv – CS AI · Apr 136/10
🧠Researchers introduce GRM, a frequency-selective jailbreak framework that exploits vulnerabilities in audio large language models while maintaining utility preservation. By strategically perturbing specific frequency bands rather than entire spectrums, GRM achieves 88.46% jailbreak success rates with better trade-offs between attack effectiveness and transcription quality compared to existing methods.
AIBullisharXiv – CS AI · Mar 36/107
🧠Researchers introduce AG-VAS, a new AI framework that uses large multimodal models for zero-shot visual anomaly segmentation. The system employs learnable semantic anchor tokens and achieves state-of-the-art performance on industrial and medical benchmarks without requiring training data for specific anomaly types.
