Large Action Models (LAMs) extend the capabilities of AI systems beyond text generation toward perception, reasoning, and action, enabling applications across robotics, autonomous systems, smart manufacturing, healthcare, and the Internet of Things. This Special Issue of ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) brings together five contributions addressing key challenges in LAM research, including safety and robustness against jailbreak and adversarial attacks, semantic-perceptual integration for robotic manipulation, efficient deployment on edge devices, and natural-language-driven decision-making for networked systems. Together, these articles span the theoretical, implementation, and application dimensions of LAMs, offering both practical solutions and a foundation for future research toward LAM-based systems that are safe, efficient, and reliably grounded in action.
Non-Fungible Tokens (NFTs) and other Web3 multimedia are typically stored off-chain because image and video assets exceed practical on-chain storage budgets, creating a gap between immutable ownership records and long-term media availability. This article proposes a collection-level neural compression approach that converts an entire NFT collection into a single compact decoder. The decoder maps a token’s integer index directly to its reconstructed image and is intentionally trained to memorize the collection so that no per-image latent codes are stored. To minimize the decoder’s on-chain footprint, we parameterize weights in the frequency domain, progressively prune high-frequency coefficients via zigzag-ordered masking, and apply run-length plus Huffman entropy coding to the resulting sparse parameters. Across three 10,000-image NFT benchmarks, Bored Ape Yacht Club (BAYC), Azuki, and CryptoPunks, the compressed artifacts are reduced to 7.63 MB, 17.09 MB, and 3.33 MB, respectively. These artifacts achieve up to \(177\times\) smaller size than PNG while maintaining high reconstruction quality, measured by Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), with PSNR \(\geq\) 33 dB and SSIM \(\geq\) 0.967. We further report Ethereum storage gas estimates showing that collection-level on-chain deployment becomes feasible at \(10^{3}\) – \(10^{4}\) USD under representative fee assumptions, reducing on-chain deployment cost by 58.6–99.4%. The main contribution is a collection-level compressed decoder that serves as the deployable on-chain storage artifact, removing dependence on external media hosts and avoiding per-image latent storage. These results demonstrate a practical path to self-contained, on-chain availability of large NFT multimedia collections without relying on external storage networks.
The integration of sensory effects—such as wind, heat, and scent—into multimedia applications holds great promise for enhancing user immersion and Quality of Experience (QoE). However, simulating the propagation of such effects in dynamic environments presents considerable challenges, particularly in achieving real-time interactivity, physical plausibility, and perceptual coherence. This article introduces an interactive simulation system based on Smoothed-Particle Hydrodynamics (SPH), designed to model gaseous-like sensory effects for real-time applications. The proposed architecture allows authors to configure virtual environments, define sensor and actuator properties, and simulate the behavior of sensory effects under different conditions. A wind-with-temperature simulation scenario is presented as a proof of concept, demonstrating the feasibility of the approach. Experimental results indicate that the proposed model captures key physical trends observed in real-world measurements. Thus, the proposed system provides a foundation for the design and evaluation of future mulsemedia experiences.
