Related papers: VideoMLA: Low-Rank Latent KV Cache for Minute-Scal…

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video…

Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text and image information to fully attend to one another within…

KV Cache is commonly used to accelerate LLM inference with long contexts, yet its high memory demand drives the need for cache compression. Existing compression methods, however, are largely heuristic and lack dynamic budget allocation. To…

Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…

Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language alignment, yet they remain limited in visual-spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual…

Large Language Models (LLMs) face limitations due to the high demand on GPU memory and computational resources when handling long contexts. While sparsify the Key-Value (KV) cache of transformer model is a typical strategy to alleviate…

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory…

Large Language Models (LLMs) exhibit pronounced memory-bound characteristics during inference due to High Bandwidth Memory (HBM) bandwidth constraints. In this paper, we propose an L2 Cache-oriented asynchronous KV Cache prefetching method…

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

Video diffusion models have recently made great progress in generation quality, but are still limited by the high memory and computational requirements. This is because current video diffusion models often attempt to process…

While autoregressive (AR) Vision-Language-Action (VLA) models have demonstrated formidable reasoning capabilities in robotic tasks, their sequential decoding process often incurs high inference latency and may amplify error accumulation…

Vision-Language Models (VLMs) are crucial for applications requiring integrated understanding textual and visual information. However, existing VLMs struggle with long videos due to computational inefficiency, memory limitations, and…

Vision-Language Models (VLMs) face a critical memory bottleneck when processing long-form video content due to the linear growth of the Key-Value (KV) cache with sequence length. Existing solutions predominantly employ reactive eviction…

Recent advancements in Large Visual Language Models (LVLMs) have gained significant attention due to their remarkable reasoning capabilities and proficiency in generalization. However, processing a large number of visual tokens and…

Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance. Nonetheless, the Key-Value (KV) cache expands linearly over time, leading to substantial…

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…

Vision-Language-Action (VLA) models have demonstrated strong multi-modal reasoning capabilities, enabling direct action generation from visual perception and language instructions in an end-to-end manner. However, their substantial…

The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes…