37 accepted papers
Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. However, this sequential generation process is notoriously slow. While caching strategies have proven effective for accelerati…
Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can accelerate generation by skipping redundant denoising steps, existi…
Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whose memory footprints scale linearly with sequence length. We introduce OOMB, a highly memory-efficient training system th…
Test-time adaptation (TTA) has emerged as a promising paradigm for vision–language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works have focused on backpropagation-free TTA methods that rely on cache-based designs, but these introduce two key limitations.…
Computational replication of Chinese calligraphy, a cornerstone of cultural heritage, remains challenging. Existing methods split into two flawed camps: some render high-quality isolated characters yet miss page-level aesthetics (ligatures, spacing, scale), while others attempt page/column synthesis…
The Mixture of Experts (MoE) architecture enables efficient model scaling through conditional computation, where only subset of parameters are activated per input. However, this distributed architecture poses unprecedented challenges for model compression, as conventional quantization methods optimi…
In this paper, we address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. Specifically, we identify a critical issue of **"reconstruction error explosion"** in existing LLMs sparsification methods. This refers to the cumul…
Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models but face prohibitive memory demands due to massive parameterization. Existing pruning methods rely on heuristic metrics or impractical enumeration of expert subsets, leading to suboptimal performance or scalabil…
Recent advances in test-time adaptation (TTA) for Vision-Language Models (VLMs) have garnered increasing attention, particularly through the use of multiple augmented views of a single image to boost zero-shot generalization. Unfortunately, existing methods fail to strike a satisfactory balance betw…
Current methods commonly utilize three-branch structures of inversion, reconstruction, and editing, to tackle consistent image editing task. However, these methods lack control over the generation position of the edited object and have issues with background preservation. To overcome these limitatio…
Data-free quantization (DFQ) enables model quantization without accessing real data, addressing concerns regarding data security and privacy. With the growing adoption of Vision Transformers (ViTs), DFQ for ViTs has garnered significant attention. However, existing DFQ methods exhibit two limitation…
Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to identify important tokens, but this approach is inefficient…
Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as promising solutions. However, fine-tuning LVLMs would require extensive high-qualit…
Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output distribution. However, existing work typically relies on a dualistic dra…
The significant resource requirements associated with Large-scale Language Models (LLMs) have generated considerable interest in the development of techniques aimed at compressing and accelerating neural networks. Among these techniques, Post-Training Quantization (PTQ) has emerged as a subject of…
Existing multi-label knowledge distillation methods simply use regression or single-label classification methods without fully exploiting the essence of multi-label classification, resulting in student models’ inadequate performance and poor functional similarity to teacher models. In this paper, we…
This paper focuses on addressing the issue of image demoiréing. Unlike the large volume of existing studies that rely on learning from paired real data, we attempt to learn a demoiréing model from unpaired real data, i.e., moiré images associated with irrelevant clean images. The proposed method, re…
Post-Training Quantization (PTQ) is a vital technique for network compression and acceleration, gaining prominence as model sizes increase. This paper addresses a critical challenge in PTQ: **the severe impact of outliers on the accuracy of quantized transformer architectures.** Specifically, we int…
The simulated annealing algorithm aims to improve model convergence through multiple restarts of training. However existing annealing algorithms overlook the correlation between different cycles neglecting the potential for incremental learning. We contend that a fixed network structure prevents the…
Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an undisputed principle of diffusion models. We consider that…
Despite recent advances in video-guided robotic imitation learning, many methods still rely on human experts to provide sparse rewards that indicate whether robots have successfully completed tasks. The challenge of enabling robots to autonomously evaluate whether their actions can complete complex,…
Most existing neural network pruning methods hand-crafted their importance criteria and structures to prune. This constructs heavy and unintended dependencies on heuristics and expert experience for both the objective and the parameters of the pruning approach. In this paper, we try to solve this pr…
We focus on addressing the dense backward propagation issue for training efficiency of N:M fine-grained sparsity that preserves at most N out of M consecutive weights and achieves practical speedups supported by the N:M sparse tensor core. Therefore, we present a novel method of Bi-directional Masks…
Vision Transformers (ViT) have made many breakthroughs in computer vision tasks. However, considerable redundancy arises in the spatial dimension of an input image, leading to massive computational costs. Therefore, We propose a coarse-to-fine vision transformer (CF-ViT) to relieve computational bur…
Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent advanced approaches achieved great success, they need to carefully handcraft a compression rate (i.e. number of tokens to r…
Despite excellent performance in image generation, Generative Adversarial Networks (GANs) are notorious for its requirements of enormous storage and intensive computation. As an awesome "performance maker", knowledge distillation is demonstrated to be particularly efficacious in exploring low-priced…
Recent advances in 3D point cloud analysis bring a diverse set of network architectures to the field. However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging, and practically limits healthy development of the field. In t…
Moir$\acute{e}$ patterns appear frequently when taking photos of digital screens, drastically degrading the image quality. Despite the advance of CNNs in image demoir$\acute{e}$ing, existing networks are with heavy design, causing massive computation burden for mobile devices. In this paper, we laun…
CutMix is a vital augmentation strategy that determines the performance and generalization ability of vision transformers (ViTs). However, the inconsistency between the mixed images and the corresponding labels harms its efficacy. Existing CutMix variants tackle this problem by generating more consi…
Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically, benefitting from its data privacy and low computation costs. We argue that an overlooked problem of oscillation is in the PTQ methods. In this paper, we take the initiative to explore an…
"Light-weight super-resolution (SR) models have received considerable attention for their serviceability in mobile devices. Many efforts employ network quantization to compress SR models. However, these methods suffer from severe performance degradation when quantizing the SR models to ultra-low pre…
"While post-training quantization receives popularity mostly due to its evasion in accessing the original complete training dataset, its poor performance also stems from scarce images. To alleviate this limitation, in this paper, we leverage the synthetic data introduced by zero-shot quantization wi…
By forcing N out of M consecutive weights to be non-zero, the recent N:M fine-grained network sparsity has received increasing attention with its two attractive advantages over traditional irregular network sparsity methods: 1) Promising performance at a high sparsity. 2) Significant speedups when p…
Performance evaluation strategy is one of the most important factors that determine the effectiveness and efficiency in Neural Architecture Search (NAS). Existing strategies, such as employing standard training or performance predictor, often suffer from high computational complexity and low general…
Recently, a series of algorithms have been explored for GAN compression, which aims to reduce tremendous computational overhead and memory usages when deploying GANs on resource-constrained edge devices. However, most of the existing GAN compression work only focuses on how to compress the generator…
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression. However, these two techniques are traditionally deployed in an isolated manner, leading to significant accuracy drop when pursuing high compression rates. In this paper, we propose…
Conventional approaches of robotic writing of Chinese character strokes often suffer from limited font generation methods, and thus the writing results often lack of diversity. This has seriously restricted the high quality writing ability of robots. This paper proposes a generative adversarial nets…