OmniMem does explicit sparse KV retrieval over the full history for autoregressive long-video generation, keeping the query-relevant details that are lost when the KV cache is truncated or compressed, and improves Dynamic Degree by 52.3% at comparable memory cost.

We propose an interleaved multi-resolution diffusion transformer architecture that departs from conventional hourglass designs. By distributing high- and low-resolution blocks in a mixed topology, S²DiT improves memory efficiency and temporal coherence for streaming video generation under constrained compute budgets.

We investigate architectural and training adaptations that enable diffusion transformers to operate efficiently on mobile platforms. Our study analyzes the trade-offs between denoising step reduction, model scaling, and visual fidelity, providing principled strategies for real-time video generation on edge devices.

Proposed a novel diffusion-based dataset distillation framework, utilizing DDIM inversion and latent distribution matching to synthesize compact datasets, maintaining high representativeness for efficient downstream training.

SnapGen-V presents a full-stack acceleration framework for large-scale video diffusion models on edge devices. By combining adversarial step distillation, mobile-aware architecture redesign, and inference scheduling optimization, we demonstrate real-time video generation on mobile hardware.

We introduce a high-compression autoencoder tailored for video diffusion models, aiming to reduce latent dimensionality while preserving perceptual fidelity. H3AE systematically balances reconstruction quality, bitrate, and downstream generative performance, enabling scalable video diffusion under limited memory budgets.

We study structured token pruning strategies for state space models, analyzing their impact on sequence modeling efficiency and representation fidelity. Our findings reveal principled sparsification patterns that preserve downstream performance under reduced computational budgets.

SF-V explores single-forward video generation to reduce iterative denoising overhead in diffusion models. By reformulating temporal generation dynamics, the method improves efficiency while maintaining competitive visual fidelity.

We propose a streamlined inference pipeline for video diffusion models, addressing the high memory footprint and computational cost of temporal attention mechanisms. Our approach integrates memory-aware attention restructuring and dynamic scheduling to enable efficient single-GPU training and inference.

ToR-SSM investigates token reduction mechanisms in sequence models for language and vision tasks. We characterize the interaction between sparsification, representation stability, and generalization, offering insights into scalable sequence modeling.

LOTUS introduces a learning-based framework for online thermal and latency management in edge AI systems. By jointly modeling dynamic voltage-frequency scaling and workload variation, the method achieves energy-efficient deployment under runtime constraints.

DACO presents a compression-DVFS co-design framework that adaptively adjusts model sparsity and hardware frequency to minimize energy consumption while preserving runtime performance.

We investigate sub-byte quantization strategies for sound event detection on hardware accelerators that support uncommon bit-width representations. By relaxing conventional uniform quantization assumptions, we demonstrate improved accuracy-efficiency trade-offs under constrained memory and compute budgets.

MOC formulates CPU-GPU co-optimization for DNN inference as a multi-objective optimization problem, balancing power consumption, latency, and thermal constraints on mobile platforms.

We propose a compiler-aware neural architecture search framework for real-time super-resolution on mobile devices. By incorporating hardware- and compiler-level constraints directly into the search objective, the resulting architectures achieve improved latency-quality trade-offs and reliable deployment across mobile runtimes.

We present a neural architecture and pruning search framework for achieving real-time super-resolution on mobile devices. By jointly optimizing network topology and structured sparsity under hardware constraints, the resulting models deliver favorable latency-quality trade-offs and reliable on-device performance.