20 accepted papers
Recent advances in large language models (LLMs) have intensified the need to deliver both rapid responses and high-quality outputs. More powerful models yield better results but incur higher inference latency, whereas smaller models are faster yet less capable. Recent work proposes balancing this la…
The operational cost of serving large language models remains prohibitively high, largely due to extreme workload heterogeneity in production traffic. We observe that combining disaggregated inference with resource autoscaling enables fine-grained resource adjustment, allowing inference phases and o…
Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to infrastructure challenges in Jacobian-vector product (JVP)…
Despite rapid progress in auto-regressive video diffusion, we identify an emerging system–algorithm bottleneck that limits both deployability and generation quality: KV-cache memory. In auto-regressive video generation models, the KV-cache grows with generation history and quickly dominates GPU memo…
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel. However, state-of-the-art block-wise dLLMs rely on a ``remasking" mechanism that decodes only the most confident tokens and di…
In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. Interestingly, we find that attention weights can be decoupled into two matrices: a small fraction of large weights with hig…
Despite advances, video diffusion transformers still struggle to generalize beyond their training length, a challenge we term video length extrapolation. We identify two failure modes: model-specific periodic content repetition and a universal quality degradation. Prior works attempt to solve repeti…
Intraoperative hypotension (IOH) prediction using past physiological signals is crucial, as IOH may lead to inadequate organ perfusion and significantly elevate the risk of severe complications and mortality. However, current methods often rely on static modeling, overlooking the complex temporal de
This paper proposes a multi-view collaborative matching strategy for reliable track construction in complex scenarios. We observe that the pairwise matching paradigms applied to image set matching often result in ambiguous estimation when the selected independent pairs exhibit significant occlusions…
Time series forecasting models are becoming increasingly prevalent due to their critical role in decision-making across various domains. However, most existing approaches represent the coupled temporal patterns, often neglecting the distinction between their specific components. In particular, fluct
Although quantization for linear layers has been widely used, its application to accelerate the attention process remains limited. To further enhance the efficiency of attention computation compared to SageAttention while maintaining precision, we propose SageAttention2, which utilizes significantly…
The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new $\texttt{FP4}$ Tensor Cores in Blackwell GPUs to accelerate attention computation. Our implementation achieves $\textbf{1038…
The transformer architecture predominates across various models. As the heart of the transformer, attention has a computational complexity of $O(N^2)$, compared to $O(N)$ for linear transformations. When handling large sequence lengths, attention becomes the primary time-consuming component. Althoug…
An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of corresponding computations. Many studies have utilized the s…
Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a few seconds of video even on high-performance GPUs. This inefficiency primarily arises from the quadratic computational…
Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens, sparse attention reduces computational costs and offers a promising acceleration approach. However, we identify that…
High-frequency and accurate state estimation is crucial for biped robots. This paper presents a tightly-coupled LiDAR-Inertial-Kinematic Odometry (LIKO) for biped robot state estimation based on an iterated extended Kalman filter. Beyond state estimation, the foot contact position is also modeled an…
Recent advances in both legged robot locomotion and Reinforcement Learning have shown a promising path for developing bipedal robot controllers. While the difference in dynamics between real world and simulation, also known as reality gap, still hinders the use. In this paper, we focus on sim-to-rea…
For autonomous driving, drivable region detection is one of the most basic and essential tasks. In this paper, a novel LiDAR-based drivable region detection algorithm which could output a complete, accurate and stable result is proposed. To promote the completeness of the detection result, the Bayes…
Computational energy versus computational precision represents a critical implementation-level tradeoff facing embedded DSP systems. Focusing on multiply-accumulate (MAC) hardware, which is used extensively in DSP implementations (e.g., FIR filtering), this paper proposes an approach that exploits f…