Quantization
-
Taming Scalable Visual Tokenizer for Autoregressive Image Generation
2024-12-03 18:59:10Fengyuan Shi, Zhuoyan Luo, Yixiao Ge, Yujiu Yang, Ying Shan, Limin WangAbstract
Existing vector quantization (VQ) methods struggle with scalability, largely attributed to the instability of the codebook that undergoes partial updates during training. The codebook is prone to collapse as utilization decreases, due to the progressively widening distribution gap between non-activated codes and visual features. To solve the problem, we propose Index Backpropagation Quantization (IBQ), a new VQ method for the joint optimization of all codebook embeddings and the visual encoder. Applying a straight-through estimator on the one-hot categorical distribution between the encoded feature and codebook, all codes are differentiable and maintain a consistent latent space with the visual encoder. IBQ enables scalable training of visual tokenizers and, for the first time, achieves a large-scale codebook ($2^{18}$) with high dimension ($256$) and high utilization. Experiments on the standard ImageNet benchmark demonstrate the scalability and superiority of IBQ, achieving competitive results on both reconstruction ($1.00$ rFID) and autoregressive visual generation ($2.05$ gFID). The code and models are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02692
PDF
-
Scaling Image Tokenizers with Grouped Spherical Quantization
2024-12-03 18:01:45Jiangtao Wang, Zhen Qin, Yifan Zhang, Vincent Tao Hu, Bj\"orn Ommer, Rania Briq, Stefan KesselheimAbstract
Vision tokenizers have gained a lot of attraction due to their scalability and compactness; previous works depend on old-school GAN-based hyperparameters, biased comparisons, and a lack of comprehensive analysis of the scaling behaviours. To tackle those issues, we introduce Grouped Spherical Quantization (GSQ), featuring spherical codebook initialization and lookup regularization to constrain codebook latent to a spherical surface. Our empirical analysis of image tokenizer training strategies demonstrates that GSQ-GAN achieves superior reconstruction quality over state-of-the-art methods with fewer training iterations, providing a solid foundation for scaling studies. Building on this, we systematically examine the scaling behaviours of GSQ, specifically in latent dimensionality, codebook size, and compression ratios, and their impact on model performance. Our findings reveal distinct behaviours at high and low spatial compression levels, underscoring challenges in representing high-dimensional latent spaces. We show that GSQ can restructure high-dimensional latent into compact, low-dimensional spaces, thus enabling efficient scaling with improved quality. As a result, GSQ-GAN achieves a 16x down-sampling with a reconstruction FID (rFID) of 0.50.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02632
PDF
-
CEGI: Measuring the trade-off between efficiency and carbon emissions for SLMs and VLMs
2024-12-03 17:32:47Abhas Kumar, Kapil Pathak, Rajesh Kavuru, Prabhakar SrinivasanAbstract
This paper analyzes the performance of Small Language Models (SLMs) and Vision Language Models (VLMs) and evaluates the trade-off between model performance and carbon emissions across 4 essential tasks: Image Captioning, Visual Question Answering (VQA), Dialogue Summarization and Text-to-SQL conversion. Various SLMs and VLMs belonging to the Qwen and LLaMA architecture family are chosen and variants based on model size in terms of the number of parameters, quantization level and fine-tuning parameters are evaluated. The model variant's performance and carbon emissions are calculated. To quantify the trade-off between model performance and carbon emissions, we introduce a novel metric called CEGI (Carbon Efficient Gain Index). This metric represents the carbon emission per unit percentage gain per million trainable parameters . This metric provides a normalized measure to compare model's efficiency in terms of performance improvement relative to their environmental cost. The experiment's outcome demonstrates that fine-tuning SLMs and VLMs can achieve performance levels comparable to Large Language Models (LLMs) while producing significantly less carbon emissions. Our findings suggest that the marginal gains in accuracy from larger models do not justify the substantial increase in carbon emissions. Leveraging lower-bit quantization levels, the proposed metric further enhances energy efficiency without compromising performance. This study highlights balancing high performance and environmental sustainability. It offers a valuable metric for selecting models suitable for environmentally-friendly AI development.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02602
PDF
-
3D representation in 512-Byte:Variational tokenizer is the key for autoregressive 3D generation
2024-12-03 06:31:25Jinzhi Zhang, Feng Xiong, Mu XuAbstract
Autoregressive transformers have revolutionized high-fidelity image generation. One crucial ingredient lies in the tokenizer, which compresses high-resolution image patches into manageable discrete tokens with a scanning or hierarchical order suitable for large language models. Extending these tokenizers to 3D generation, however, presents a significant challenge: unlike image patches that naturally exhibit spatial sequence and multi-scale relationships, 3D data lacks an inherent order, making it difficult to compress into fewer tokens while preserving structural details. To address this, we introduce the Variational Tokenizer (VAT), which transforms unordered 3D data into compact latent tokens with an implicit hierarchy, suited for efficient and high-fidelity coarse-to-fine autoregressive modeling. VAT begins with an in-context transformer, which compress numerous unordered 3D features into a reduced token set with minimal information loss. This latent space is then mapped to a Gaussian distribution for residual quantization, with token counts progressively increasing across scales. In this way, tokens at different scales naturally establish the interconnections by allocating themselves into different subspaces within the same Gaussian distribution, facilitating discrete modeling of token relationships across scales. During the decoding phase, a high-resolution triplane is utilized to convert these compact latent tokens into detailed 3D shapes. Extensive experiments demonstrate that VAT enables scalable and efficient 3D generation, outperforming existing methods in quality, efficiency, and generalization. Remarkably, VAT achieves up to a 250x compression, reducing a 1MB mesh to just 3.9KB with a 96% F-score, and can further compress to 256 int8 tokens, achieving a 2000x reduction while maintaining a 92% F-score.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02202
PDF
-
A Classic-Quantum Hybrid Network Framework: CQH-Net
2024-12-03 00:37:11Ao Liu, Cuihong Wen, Jieci WangAbstract
Deep Learning has shown remarkable capabilities in pattern recognition, feature extraction, and classification decision-making. With the rise of quantum computing, the potential of quantum neural networks (QNNs) in Artificial Intelligence is emerging. However, the intrinsic mechanisms and decision transparency of QNNs remain unclear. In this paper, we propose a classic-quantum hybrid network framework (CQH-Net), which uses traditional machine learning methods for feature extraction and quantizes neural networks for classification tasks. We apply CQH-Net to image classification on public datasets. Experimentally, CQH-Net achieves an average convergence rate improvement of 72.8% compared to classical convolutional networks (CNNs) with identical parameters. On the Fashion MNIST dataset, it reaches a final accuracy of 99.02%, representing a significant increase of 5.07% over CNNs. Furthermore, we explore visual explanations for CQH-Net's decision-making process. Results show that the model effectively captures key data features during training and establishes associations between these features and their corresponding categories. This study demonstrates that quantization enhances the models ability to tackle complex classification problems while providing transparency in its decision-making process further supporting quantum advantages in machine learning.
Abstract (translated)
URL
https://arxiv.org/abs/2412.02059
PDF
-
XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation
2024-12-02 17:58:06Xiang Li, Kai Qiu, Hao Chen, Jason Kuen, Jiuxiang Gu, Jindong Wang, Zhe Lin, Bhiksha RajAbstract
Image tokenizers play a critical role in shaping the performance of subsequent generative models. Since the introduction of VQ-GAN, discrete image tokenization has undergone remarkable advancements. Improvements in architecture, quantization techniques, and training recipes have significantly enhanced both image reconstruction and the downstream generation quality. In this paper, we present XQ-GAN, an image tokenization framework designed for both image reconstruction and generation tasks. Our framework integrates state-of-the-art quantization techniques, including vector quantization (VQ), residual quantization (RQ), multi-scale residual quantization (MSVQ), product quantization (PQ), lookup-free quantization (LFQ), and binary spherical quantization (BSQ), within a highly flexible and customizable training environment. On the standard ImageNet 256x256 benchmark, our released model achieves an rFID of 0.64, significantly surpassing MAGVIT-v2 (0.9 rFID) and VAR (0.9 rFID). Furthermore, we demonstrate that using XQ-GAN as a tokenizer improves gFID metrics alongside rFID. For instance, with the same VAR architecture, XQ-GAN+VAR achieves a gFID of 2.6, outperforming VAR's 3.3 gFID by a notable margin. To support further research, we provide pre-trained weights of different image tokenizers for the community to directly train the subsequent generative models on it or fine-tune for specialized tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01762
PDF
-
Optimizing Domain-Specific Image Retrieval: A Benchmark of FAISS and Annoy with Fine-Tuned Features
2024-12-02 14:43:06MD Shaikh Rahman, Syed Maudud E Rabbi, Muhammad Mahbubur RashidAbstract
Approximate Nearest Neighbor search is one of the keys to high-scale data retrieval performance in many applications. The work is a bridge between feature extraction and ANN indexing through fine-tuning a ResNet50 model with various ANN methods: FAISS and Annoy. We evaluate the systems with respect to indexing time, memory usage, query time, precision, recall, F1-score, and Recall@5 on a custom image dataset. FAISS's Product Quantization can achieve a precision of 98.40% with low memory usage at 0.24 MB index size, and Annoy is the fastest, with average query times of 0.00015 seconds, at a slight cost to accuracy. These results reveal trade-offs among speed, accuracy, and memory efficiency and offer actionable insights into the optimization of feature-based image retrieval systems. This study will serve as a blueprint for constructing actual retrieval pipelines and be built on fine-tuned deep learning networks and associated ANN methods.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01555
PDF
-
Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification
Abstract
Recent speaker verification (SV) systems have shown a trend toward adopting deeper speaker embedding extractors. Although deeper and larger neural networks can significantly improve performance, their substantial memory requirements hinder training on consumer GPUs. In this paper, we explore a memory-efficient training strategy for deep speaker embedding learning in resource-constrained scenarios. Firstly, we conduct a systematic analysis of GPU memory allocation during SV system training. Empirical observations show that activations and optimizer states are the main sources of memory consumption. For activations, we design two types of reversible neural networks which eliminate the need to store intermediate activations during back-propagation, thereby significantly reducing memory usage without performance loss. For optimizer states, we introduce a dynamic quantization approach that replaces the original 32-bit floating-point values with a dynamic tree-based 8-bit data type. Experimental results on VoxCeleb demonstrate that the reversible variants of ResNets and DF-ResNets can perform training without the need to cache activations in GPU memory. In addition, the 8-bit versions of SGD and Adam save 75% of memory costs while maintaining performance compared to their 32-bit counterparts. Finally, a detailed comparison of memory usage and performance indicates that our proposed models achieve up to 16.2x memory savings, with nearly identical parameters and performance compared to the vanilla systems. In contrast to the previous need for multiple high-end GPUs such as the A100, we can effectively train deep speaker embedding extractors with just one or two consumer-level 2080Ti GPUs.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01195
PDF
-
RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy
2024-12-02 05:09:56Geonho Lee, Janghwan Lee, Sukjin Hong, Minsoo Kim, Euijai Ahn, Du-Seong Chang, Jungwook ChoiAbstract
Low-rank adaptation (LoRA) has become the dominant method for parameter-efficient LLM fine-tuning, with LoRA-based quantization error compensation (LQEC) emerging as a powerful tool for recovering accuracy in compressed LLMs. However, LQEC has underperformed in sub-4-bit scenarios, with no prior investigation into understanding this limitation. We propose RILQ (Rank-Insensitive LoRA-based Quantization Error Compensation) to understand fundamental limitation and boost 2-bit LLM accuracy. Based on rank analysis revealing model-wise activation discrepancy loss's rank-insensitive nature, RILQ employs this loss to adjust adapters cooperatively across layers, enabling robust error compensation with low-rank adapters. Evaluations on LLaMA-2 and LLaMA-3 demonstrate RILQ's consistent improvements in 2-bit quantized inference across various state-of-the-art quantizers and enhanced accuracy in task-specific fine-tuning. RILQ maintains computational efficiency comparable to existing LoRA methods, enabling adapter-merged weight-quantized LLM inference with significantly enhanced accuracy, making it a promising approach for boosting 2-bit LLM performance.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01129
PDF
-
FreeCodec: A disentangled neural speech codec with fewer tokens
2024-12-02 02:29:22Youqiang Zheng, Weiping Tu, Yueteng Kang, Jie Chen, Yike Zhang, Li Xiao, Yuhong Yang, Long MaAbstract
Neural speech codecs have gained great attention for their outstanding reconstruction with discrete token representations. It is a crucial component in generative tasks such as speech coding and large language models (LLM). However, most works based on residual vector quantization perform worse with fewer tokens due to low coding efficiency for modeling complex coupled information. In this paper, we propose a neural speech codec named FreeCodec which employs a more effective encoding framework by decomposing intrinsic properties of speech into different components: 1) a global vector is extracted as the timbre information, 2) a prosody encoder with a long stride level is used to model the prosody information, 3) the content information is from a content encoder. Using different training strategies, FreeCodec achieves state-of-the-art performance in reconstruction and disentanglement scenarios. Results from subjective and objective experiments demonstrate that our framework outperforms existing methods.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01053
PDF
-
Improving Detail in Pluralistic Image Inpainting with Feature Dequantization
2024-12-02 02:06:04Kyungri Park, Woohwan JungAbstract
Pluralistic Image Inpainting (PII) offers multiple plausible solutions for restoring missing parts of images and has been successfully applied to various applications including image editing and object removal. Recently, VQGAN-based methods have been proposed and have shown that they significantly improve the structural integrity in the generated images. Nevertheless, the state-of-the-art VQGAN-based model PUT faces a critical challenge: degradation of detail quality in output images due to feature quantization. Feature quantization restricts the latent space and causes information loss, which negatively affects the detail quality essential for image inpainting. To tackle the problem, we propose the FDM (Feature Dequantization Module) specifically designed to restore the detail quality of images by compensating for the information loss. Furthermore, we develop an efficient training method for FDM which drastically reduces training costs. We empirically demonstrate that our method significantly enhances the detail quality of the generated images with negligible training and inference overheads.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01046
PDF
-
Reducing Inference Energy Consumption Using Dual Complementary CNNs
2024-12-02 01:46:07Michail Kinnas, John Violos, Ioannis Kompatsiaris, Symeon PapadopoulosAbstract
Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of these models. Previous efforts, including techniques like model pruning, quantization, and hardware optimization, have made significant strides in this direction. However, there remains a need for more effective on device AI solutions that balance energy efficiency with model performance. In this paper, we propose a novel approach to reduce the energy requirements of inference of CNNs. Our methodology employs two small Complementary CNNs that collaborate with each other by covering each other's "weaknesses" in predictions. If the confidence for a prediction of the first CNN is considered low, the second CNN is invoked with the aim of producing a higher confidence prediction. This dual-CNN setup significantly reduces energy consumption compared to using a single large deep CNN. Additionally, we propose a memory component that retains previous classifications for identical inputs, bypassing the need to re-invoke the CNNs for the same input, further saving energy. Our experiments on a Jetson Nano computer demonstrate an energy reduction of up to 85.8% achieved on modified datasets where each sample was duplicated once. These findings indicate that leveraging a complementary CNN pair along with a memory component effectively reduces inference energy while maintaining high accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01039
PDF
-
Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control
2024-12-02 01:33:49Seongmin Park, Hyungmin Kim, Wonseok Jeon, Juyoung Yang, Byeongwook Jeon, Yoonseon Oh, Jungwook ChoiAbstract
Deep neural network (DNN)-based policy models like vision-language-action (VLA) models are transformative in automating complex decision-making across applications by interpreting multi-modal data. However, scaling these models greatly increases computational costs, which presents challenges in fields like robot manipulation and autonomous driving that require quick, accurate responses. To address the need for deployment on resource-limited hardware, we propose a new quantization framework for IL-based policy models that fine-tunes parameters to enhance robustness against low-bit precision errors during training, thereby maintaining efficiency and reliability under constrained conditions. Our evaluations with representative robot manipulation for 4-bit weight-quantization on a real edge GPU demonstrate that our framework achieves up to 2.5x speedup and 2.5x energy savings while preserving accuracy. For 4-bit weight and activation quantized self-driving models, the framework achieves up to 3.7x speedup and 3.1x energy saving on a low-end GPU. These results highlight the practical potential of deploying IL-based policy models on resource-constrained devices.
Abstract (translated)
URL
https://arxiv.org/abs/2412.01034
PDF
-
A Wave is Worth 100 Words: Investigating Cross-Domain Transferability in Time Series
2024-12-01 11:35:06Xiangkai Ma, Xiaobin Hong, Wenzhong Li, Sanglu LuAbstract
Time series analysis is a fundamental data mining task that supervised training methods based on empirical risk minimization have proven their effectiveness on specific tasks and datasets. However, the acquisition of well-annotated data is costly and a large amount of unlabeled series data is under-utilized. Due to distributional shifts across various domains and different patterns of interest across multiple tasks. The problem of cross-domain multi-task migration of time series remains a significant challenge. To address these problems, this paper proposes a novel cross-domain pretraining method based on Wave Quantization (termed as WQ4TS), which can be combined with any advanced time series model and applied to multiple downstream tasks. Specifically, we transfer the time series data from different domains into a common spectral latent space, and enable the model to learn the temporal pattern knowledge of different domains directly from the common space and utilize it for the inference of downstream tasks, thereby mitigating the challenge of heterogeneous cross-domains migration. The establishment of spectral latent space brings at least three benefits, cross-domain migration capability thus adapting to zero- and few-shot scenarios without relying on priori knowledge of the dataset, general compatible cross-domain migration framework without changing the existing model structure, and robust modeling capability thus achieving SOTA results in multiple downstream tasks. To demonstrate the effectiveness of the proposed approach, we conduct extensive experiments including three important tasks: forecasting, imputation, and classification. And three common real-world data scenarios are simulated: full-data, few-shot, and zero-shot. The proposed WQ4TS achieves the best performance on 87.5% of all tasks, and the average improvement of the metrics on all the tasks is up to 34.7%.
Abstract (translated)
URL
https://arxiv.org/abs/2412.00772
PDF
-
LAMBDA: Covering the Multimodal Critical Scenarios for Automated Driving Systems by Search Space Quantization
2024-11-30 15:57:05Xinzheng Wu, Junyi Chen, Xingyu Xing, Jian Sun, Ye Tian, Lihao Liu, Yong ShenAbstract
Scenario-based virtual testing is one of the most significant methods to test and evaluate the safety of automated driving systems (ADSs). However, it is impractical to enumerate all concrete scenarios in a logical scenario space and test them exhaustively. Recently, Black-Box Optimization (BBO) was introduced to accelerate the scenario-based test of ADSs by utilizing the historical test information to generate new test cases. However, a single optimum found by the BBO algorithm is insufficient for the purpose of a comprehensive safety evaluation of ADSs in a logical scenario. In fact, all the subspaces representing danger in the logical scenario space, rather than only the most critical concrete scenario, play a more significant role for the safety evaluation. Covering as many of the critical concrete scenarios in a logical scenario space through a limited number of tests is defined as the Black-Box Coverage (BBC) problem in this paper. We formalized this problem in a sample-based search paradigm and constructed a coverage criterion with Confusion Matrix Analysis. Furthermore, we propose LAMBDA (Latent-Action Monte-Carlo Beam Search with Density Adaption) to solve BBC problems. LAMBDA can quickly focus on critical subspaces by recursively partitioning the logical scenario space into accepted and rejected parts. Compared with its predecessor LaMCTS, LAMBDA introduces sampling density to overcome the sampling bias from optimization and Beam Search to obtain more parallelizability. Experimental results show that LAMBDA achieves state-of-the-art performance among all baselines and can reach at most 33 and 6000 times faster than Random Search to get 95% coverage of the critical areas in 2- and 5-dimensional synthetic functions, respectively. Experiments also demonstrate that LAMBDA has a promising future in the safety evaluation of ADSs in virtual tests.
Abstract (translated)
URL
https://arxiv.org/abs/2412.00517
PDF
-
Scaling Transformers for Low-Bitrate High-Quality Speech Coding
2024-11-29 16:58:02Julian D Parker, Anton Smirnov, Jordi Pons, CJ Carr, Zack Zukowski, Zach Evans, Xubo LiuAbstract
The tokenization of speech with neural audio codec models is a vital part of modern AI pipelines for the generation or understanding of speech, alone or in a multimodal context. Traditionally such tokenization models have concentrated on low parameter-count architectures using only components with strong inductive biases. In this work we show that by scaling a transformer architecture with large parameter count to this problem, and applying a flexible Finite Scalar Quantization (FSQ) based bottleneck, it is possible to reach state-of-the-art speech quality at extremely low bit-rates of $400$ or $700$ bits-per-second. The trained models strongly out-perform existing baselines in both objective and subjective tests.
Abstract (translated)
URL
https://arxiv.org/abs/2411.19842
PDF
-
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
2024-11-29 12:06:03Qixiu Li, Yaobo Liang, Zeyu Wang, Lin Luo, Xi Chen, Mozheng Liao, Fangyun Wei, Yu Deng, Sicheng Xu, Yizhong Zhang, Xiaofan Wang, Bei Liu, Jianlong Fu, Jianmin Bao, Dong Chen, Yuanchun Shi, Jiaolong Yang, Baining GuoAbstract
The advancement of large Vision-Language-Action (VLA) models has significantly improved robotic manipulation in terms of language-guided task execution and generalization to unseen scenarios. While existing VLAs adapted from pretrained large Vision-Language-Models (VLM) have demonstrated promising generalizability, their task performance is still unsatisfactory as indicated by the low tasks success rates in different environments. In this paper, we present a new advanced VLA architecture derived from VLM. Unlike previous works that directly repurpose VLM for action prediction by simple action quantization, we propose a omponentized VLA architecture that has a specialized action module conditioned on VLM output. We systematically study the design of the action module and demonstrates the strong performance enhancement with diffusion action transformers for action sequence modeling, as well as their favorable scaling behaviors. We also conduct comprehensive experiments and ablation studies to evaluate the efficacy of our models with varied designs. The evaluation on 5 robot embodiments in simulation and real work shows that our model not only significantly surpasses existing VLAs in task performance and but also exhibits remarkable adaptation to new robots and generalization to unseen objects and backgrounds. It exceeds the average success rates of OpenVLA which has similar model size (7B) with ours by over 35% in simulated evaluation and 55% in real robot experiments. It also outperforms the large RT-2-X model (55B) by 18% absolute success rates in simulation. Code and models can be found on our project page (this https URL).
Abstract (translated)
URL
https://arxiv.org/abs/2411.19650
PDF
-
Quantized Delta Weight Is Safety Keeper
2024-11-29 08:05:50Yule Liu, Zhen Sun, Xinlei He, Xinyi HuangAbstract
Recent advancements in fine-tuning proprietary language models enable customized applications across various domains but also introduce two major challenges: high resource demands and security risks. Regarding resource demands, recent work proposes novel partial compression, such as BitDelta, to quantize the delta weights between the fine-tuned model and base model. Regarding the security risks, user-defined fine-tuning can introduce security vulnerabilities, such as alignment issues, backdoor attacks, and hallucinations. However, most of the current efforts in security assessment focus on the full-precision or full-compression models, it is not well-discussed how the partial compression methods affect security concerns. To bridge this gap, we evaluate the robustness of delta-weight quantization against these security threats. In this paper, we uncover a "free lunch" phenomenon: partial compression can enhance model security against fine-tuning-based attacks with bearable utility loss. Using Llama-2-7b-chat as a case study, we show that, with under 10% utility degradation, the partial compression mitigates alignment-breaking risks by up to 66.17%, harmful backdoor vulnerabilities by 64.46%, and targeted output manipulation risks by up to 90.53%. We further apply LogitLens to visualize internal state transformations during forward passes, suggesting mechanisms for both security failure and recovery in standard versus compressed fine-tuning. This work offers new insights into selecting effective delta compression methods for secure, resource-efficient multi-tenant services.
Abstract (translated)
URL
https://arxiv.org/abs/2411.19530
PDF
-
DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding
2024-11-29 07:54:56Jungbin Cho, Junwan Kim, Jisoo Kim, Minseo Kim, Mingu Kang, Sungeun Hong, Tae-Hyun Oh, Youngjae YuAbstract
Human motion, inherently continuous and dynamic, presents significant challenges for generative models. Despite their dominance, discrete quantization methods, such as VQ-VAEs, suffer from inherent limitations, including restricted expressiveness and frame-wise noise artifacts. Continuous approaches, while producing smoother and more natural motions, often falter due to high-dimensional complexity and limited training data. To resolve this "discord" between discrete and continuous representations, we introduce DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding, a novel method that decodes discrete motion tokens into continuous motion through rectified flow. By employing an iterative refinement process in the continuous space, DisCoRD captures fine-grained dynamics and ensures smoother and more natural motions. Compatible with any discrete-based framework, our method enhances naturalness without compromising faithfulness to the conditioning signals. Extensive evaluations demonstrate that DisCoRD achieves state-of-the-art performance, with FID of 0.032 on HumanML3D and 0.169 on KIT-ML. These results solidify DisCoRD as a robust solution for bridging the divide between discrete efficiency and continuous realism. Our project page is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2411.19527
PDF
-
MPQ-Diff: Mixed Precision Quantization for Diffusion Models
2024-11-28 19:38:26Rocco Manz Maruzzelli, Basile Lewandowski, Lydia Y. ChenAbstract
Diffusion models (DMs) generate remarkable high quality images via the stochastic denoising process, which unfortunately incurs high sampling time. Post-quantizing the trained diffusion models in fixed bit-widths, e.g., 4 bits on weights and 8 bits on activation, is shown effective in accelerating sampling time while maintaining the image quality. Motivated by the observation that the cross-layer dependency of DMs vary across layers and sampling steps, we propose a mixed precision quantization scheme, MPQ-Diff, which allocates different bit-width to the weights and activation of the layers. We advocate to use the cross-layer correlation of a given layer, termed network orthogonality metric, as a proxy to measure the relative importance of a layer per sampling step. We further adopt a uniform sampling scheme to avoid the excessive profiling overhead of estimating orthogonality across all time steps. We evaluate the proposed mixed-precision on LSUN and ImageNet, showing a significant improvement in FID from 65.73 to 15.39, and 52.66 to 14.93, compared to their fixed precision quantization, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2412.00144
PDF
