VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput f…

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

The paper proposes SimSD, a plug-and-play speculative decoding algorithm that adapts diffusion language models (dLLMs) to achieve fast, token-level acceleration by restoring causal masking capabilitie…

WaveFilter is a novel, training-free framework that uses wavelet transforms to efficiently filter critical tokens in the KV cache, significantly improving the long-context performance of Diffusion LLM…

DFlare introduces a lightweight layer-wise fusion mechanism to overcome the narrow conditioning bottleneck of existing block diffusion methods, enabling the scaling of draft models and achieving super…

SPARQLe is a hardware-software co-design framework that exploits the inherent sub-precision sparsity of LLM activations to reduce memory traffic and enable efficient computation on lower-bit datapaths…

BudgetDraft introduces an acceptance-aware multi-view training method that trains a sparse-KV speculative decoder to maintain high acceptance rates across varying context lengths and sparsity levels,…

HASTE introduces group-shared fixed fan-in sparsity for multi-label classification, achieving significant wall-clock speedups (up to 25x in backward pass) by enabling efficient GPU execution while mai…

DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…

The paper analyzes the security of a partially masked hardware accelerator for Number Theoretic Transform (NTT) in PQC, demonstrating that the claimed security margins are significantly overestimated…

The paper introduces DSL-LLaDA, a method that lightly adapts a pre-trained masked diffusion language model to perform continuous denoising in embedding space, significantly improving text generation q…

The paper proposes Cross-Layer Sparse Attention (CLSA) to significantly improve the efficiency and accuracy of long-context LLMs by jointly optimizing KV-cache sharing and the routing index across dec…

Real2SAM2Real introduces a framework that uses explicit 3D caches, derived from 3D lifting models, to provide robust geometric guidance to Video Diffusion Models, significantly improving spatiotempora…

The paper proposes a compression pipeline combining few-step distillation and low-bit quantization to significantly reduce the deployment cost and parameter footprint of large dual-expert video diffus…

The paper introduces Sparse Memory-Efficient Training (SMET), a method that stabilizes and optimizes Dynamic Sparse Training (DST) for large language models, enabling stable and memory-efficient spars…

The paper characterizes 'dead-entry' TLB misses in GPUs, which occur when recently evicted translations are immediately re-walked, and proposes DEPOT, a Bloom filter mechanism that significantly reduc…

The paper introduces residualized temporal Sparse Autoencoders (SAEs) to analyze the full spatiotemporal structure of activations generated during the iterative denoising process of diffusion models,…

This paper proposes a hybrid scheduler that dynamically switches between exclusive batching and mixed batching for LLM inference, achieving superior throughput, especially on bandwidth-constrained GPU…

SANA-Streaming introduces a novel, efficient framework that enables real-time, high-resolution streaming video-to-video editing by combining a hybrid diffusion transformer with specialized training an…