GRKV introduces a training-free KV-cache merging method that uses global regression to distribute information from evicted tokens, solving the over-merging problem inherent in span-based retention.

BlockBatch introduces a novel framework that efficiently accelerates diffusion language model (dLLM) inference by simultaneously executing multiple block-size branches for a single request, achieving…

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…

Moment-KV introduces a novel momentum-based technique to compress the Key-Value (KV) cache during the decoding phase of LLM generation, significantly improving fidelity in long-generation tasks.

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…

The paper introduces 'infilling extraction' to accurately model training data memorization in Diffusion Language Models (DLMs), finding that bidirectional masking significantly increases the extractab…

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…

CachePrune introduces a privacy-aware, fine-grained KV cache sharing mechanism that allows LLM inference systems to safely reuse cache entries across users' requests, significantly improving efficienc…

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…

TAPS introduces a target-aware prefix selection method that optimizes the trade-off between draft tree acceptance and verification cost, achieving significant speedups in speculative decoding.

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 proposes AsymCache, a computation-latency-aware KV cache management system that optimizes LLM inference by aligning cache eviction decisions with GPU attention kernel performance, significan…

The paper proposes SubFit, a novel compression technique that achieves superior LLM compression by replacing non-contiguous, submodule-level components (Attention and FeedForward) with lightweight res…

The paper proposes a novel trace-aware decoding framework, combining Temporal-Spatial Parallel Decoding (TSPD) and Confidence Extrapolation (CE), to significantly accelerate the inference of diffusion…

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…

The paper systematically characterizes column-level activation sparsity across various diffusion model architectures, demonstrating that element-level sparsity metrics significantly overestimate the a…

This paper introduces a new scaling law for sparse language models trained with limited data, demonstrating that sparsity can significantly improve performance and delay data saturation during multi-e…

The paper proposes DLLM-VSR, a novel Diffusion Large Language Model framework for Visual Speech Recognition, achieving state-of-the-art performance by treating transcription as iterative masked denois…

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…