arXiv subjects

Wonpyo Park

Publications and source records attributed to Wonpyo Park.

16 recordsLinked to original sources

arXiv2026

TaskPress: Query-Agnostic KV Cache Compression via Task-Guided Pruning

Long-context inference with large language models is constrained by the linear growth of the key-value cache to sequence length. While pruning offers mitigation, prevailing methods determine query-specific token importance that cannot be reused across unseen queries. In contrast, we introduce TaskPress, a framework for task-guided, query-agnostic KV cache eviction. Instead of optimizing the cache for a single query, TaskPress constructs a reusable memory representation conditioned on a high-level task guide. The guide functions as a meta-query during prefill to filter irrelevant tokens before downstream queries are issued. In addition, TaskPress leverages quantization scale factors as a zero-cost signal for detecting influential representation outliers, providing an efficient proxy for token importance. Experiments on conducted on various tasks with long context input demonstrate that TaskPress efficiently creates a compact, reusable cache across diverse queries.

cs.AI↗

arXiv2026

Activation Quantization of Vision Encoders Needs Prefixing Registers

Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models. Since these applications often demand real-time processing of massive visual data, reducing the inference cost of vision encoders is critical. Quantization offers a practical path, but it remains challenging even at 8-bit precision due to so-called outliers. In this work, we propose $\textit{RegCache}$, a training-free algorithm that mitigates outliers in large-scale pretrained vision encoders and serves as a plug-in module that can be applied on top of other quantization methods. RegCache introduces outlier-prone yet semantically meaningless prefix tokens to the vision encoder, which prevent other tokens from having outliers. Notably, we observe that outliers in vision encoders behave differently from those in language models, motivating two technical innovations: middle-layer prefixing and token deletion. Experimental results show that our method consistently improves quantized model performance across various vision encoders, particularly in extremely low-bit regimes (e.g., 4-bit).

cs.LG↗

arXiv2025

GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance

Post-training quantization is a key technique for reducing the memory and inference latency of large language models by quantizing weights and activations without requiring retraining. However, existing methods either (1) fail to account for the varying importance of hidden features to the end loss or, when incorporating end loss, (2) neglect the critical interactions between model weights. To address these limitations, we propose GuidedQuant, a novel quantization approach that integrates gradient information from the end loss into the quantization objective while preserving cross-weight dependencies within output channels. GuidedQuant consistently boosts the performance of state-of-the-art quantization methods across weight-only scalar, weight-only vector, and weight-and-activation quantization. Additionally, we introduce a novel non-uniform scalar quantization algorithm, which is guaranteed to monotonically decrease the quantization objective value, and outperforms existing methods in this category. We release the code at https://github.com/snu-mllab/GuidedQuant.

cs.LG↗

arXiv2025

LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs

While large language models (LLMs) excel in generating coherent and contextually rich outputs, their capacity to efficiently handle long-form contexts is limited by fixed-length position embeddings. Additionally, the computational cost of processing long sequences increases quadratically, making it challenging to extend context length. To address these challenges, we propose Long-form Context Injection with Recurrent Compression (LCIRC), a method that enables the efficient processing long-form sequences beyond the model's length limit through recurrent compression without retraining the entire model. We further introduce query dependent context modeling, which selectively compresses query-relevant information, ensuring that the model retains the most pertinent content. Our empirical results demonstrate that Query Dependent LCIRC (QD-LCIRC) significantly improves LLM's ability to manage extended contexts, making it well-suited for tasks that require both comprehensive context understanding and query relevance.

cs.CL↗

arXiv2025

Compression Scaling Laws:Unifying Sparsity and Quantization

We investigate how different compression techniques -- such as weight and activation quantization, and weight sparsity -- affect the scaling behavior of large language models (LLMs) during pretraining. Building on previous work showing that weight sparsity acts as a constant multiplier on model size in scaling laws, we demonstrate that this "effective parameter" scaling pattern extends to quantization as well. Specifically, we establish that weight-only quantization achieves strong parameter efficiency multipliers, while full quantization of both weights and activations shows diminishing returns at lower bitwidths. Our results suggest that different compression techniques can be unified under a common scaling law framework, enabling principled comparison and combination of these methods.

cs.LG↗

arXiv2024

Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization

This work suggests fundamentally rethinking the current practice of pruning large language models (LLMs). The way it is done is by divide and conquer: split the model into submodels, sequentially prune them, and reconstruct predictions of the dense counterparts on small calibration data one at a time; the final model is obtained simply by putting the resulting sparse submodels together. While this approach enables pruning under memory constraints, it generates high reconstruction errors. In this work, we first present an array of reconstruction techniques that can significantly reduce this error by more than $90\%$. Unwittingly, however, we discover that minimizing reconstruction error is not always ideal and can overfit the given calibration data, resulting in rather increased language perplexity and poor performance at downstream tasks. We find out that a strategy of self-generating calibration data can mitigate this trade-off between reconstruction and generalization, suggesting new directions in the presence of both benefits and pitfalls of reconstruction for pruning LLMs.

cs.CL↗

arXiv2024

Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization

Despite recent advances in LLM quantization, activation quantization remains to be challenging due to the activation outliers. Conventional remedies, e.g., mixing precisions for different channels, introduce extra overhead and reduce the speedup. In this work, we develop a simple yet effective strategy to facilitate per-tensor activation quantization by preventing the generation of problematic tokens. Precisely, we propose a method to find a set of key-value cache, coined CushionCache, which mitigates outliers in subsequent tokens when inserted as a prefix. CushionCache works in two steps: First, we greedily search for a prompt token sequence that minimizes the maximum activation values in subsequent tokens. Then, we further tune the token cache to regularize the activations of subsequent tokens to be more quantization-friendly. The proposed method successfully addresses activation outliers of LLMs, providing a substantial performance boost for per-tensor activation quantization methods. We thoroughly evaluate our method over a wide range of models and benchmarks and find that it significantly surpasses the established baseline of per-tensor W8A8 quantization and can be seamlessly integrated with the recent activation quantization method.

cs.LG↗

arXiv2023

JaxPruner: A concise library for sparsity research

This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research. JaxPruner aims to accelerate research on sparse neural networks by providing concise implementations of popular pruning and sparse training algorithms with minimal memory and latency overhead. Algorithms implemented in JaxPruner use a common API and work seamlessly with the popular optimization library Optax, which, in turn, enables easy integration with existing JAX based libraries. We demonstrate this ease of integration by providing examples in four different codebases: Scenic, t5x, Dopamine and FedJAX and provide baseline experiments on popular benchmarks.

cs.LG↗

arXiv2022

GRPE: Relative Positional Encoding for Graph Transformer

We propose a novel positional encoding for learning graph on Transformer architecture. Existing approaches either linearize a graph to encode absolute position in the sequence of nodes, or encode relative position with another node using bias terms. The former loses preciseness of relative position from linearization, while the latter loses a tight integration of node-edge and node-topology interaction. To overcome the weakness of the previous approaches, our method encodes a graph without linearization and considers both node-topology and node-edge interaction. We name our method Graph Relative Positional Encoding dedicated to graph representation learning. Experiments conducted on various graph datasets show that the proposed method outperforms previous approaches significantly. Our code is publicly available at https://github.com/lenscloth/GRPE.

cs.LG↗

arXiv2021

Multi-level Distance Regularization for Deep Metric Learning

We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors into multiple levels that represents a degree of similarity between a pair. In the training stage, the model is trained with both MDR and an existing loss function of deep metric learning, simultaneously; the two losses interfere with the objective of each other, and it makes the learning process difficult. Moreover, MDR prevents some examples from being ignored or overly influenced in the learning process. These allow the parameters of the embedding network to be settle on a local optima with better generalization. Without bells and whistles, MDR with simple Triplet loss achieves the-state-of-the-art performance in various benchmark datasets: CUB-200-2011, Cars-196, Stanford Online Products, and In-Shop Clothes Retrieval. We extensively perform ablation studies on its behaviors to show the effectiveness of MDR. By easily adopting our MDR, the previous approaches can be improved in performance and generalization ability.

cs.CV↗

arXiv2020

Diversified Mutual Learning for Deep Metric Learning

Mutual learning is an ensemble training strategy to improve generalization by transferring individual knowledge to each other while simultaneously training multiple models. In this work, we propose an effective mutual learning method for deep metric learning, called Diversified Mutual Metric Learning, which enhances embedding models with diversified mutual learning. We transfer relational knowledge for deep metric learning by leveraging three kinds of diversities in mutual learning: (1) model diversity from different initializations of models, (2) temporal diversity from different frequencies of parameter update, and (3) view diversity from different augmentations of inputs. Our method is particularly adequate for inductive transfer learning at the lack of large-scale data, where the embedding model is initialized with a pretrained model and then fine-tuned on a target dataset. Extensive experiments show that our method significantly improves individual models as well as their ensemble. Finally, the proposed method with a conventional triplet loss achieves the state-of-the-art performance of Recall@1 on standard datasets: 69.9 on CUB-200-2011 and 89.1 on CARS-196.

cs.CV↗

arXiv2020

BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition

The datasets of face recognition contain an enormous number of identities and instances. However, conventional methods have difficulty in reflecting the entire distribution of the datasets because a mini-batch of small size contains only a small portion of all identities. To overcome this difficulty, we propose a novel method called BroadFace, which is a learning process to consider a massive set of identities, comprehensively. In BroadFace, a linear classifier learns optimal decision boundaries among identities from a large number of embedding vectors accumulated over past iterations. By referring more instances at once, the optimality of the classifier is naturally increased on the entire datasets. Thus, the encoder is also globally optimized by referring the weight matrix of the classifier. Moreover, we propose a novel compensation method to increase the number of referenced instances in the training stage. BroadFace can be easily applied on many existing methods to accelerate a learning process and obtain a significant improvement in accuracy without extra computational burden at inference stage. We perform extensive ablation studies and experiments on various datasets to show the effectiveness of BroadFace, and also empirically prove the validity of our compensation method. BroadFace achieves the state-of-the-art results with significant improvements on nine datasets in 1:1 face verification and 1:N face identification tasks, and is also effective in image retrieval.

cs.CV↗

arXiv2020

GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition

In the field of face recognition, a model learns to distinguish millions of face images with fewer dimensional embedding features, and such vast information may not be properly encoded in the conventional model with a single branch. We propose a novel face-recognition-specialized architecture called GroupFace that utilizes multiple group-aware representations, simultaneously, to improve the quality of the embedding feature. The proposed method provides self-distributed labels that balance the number of samples belonging to each group without additional human annotations, and learns the group-aware representations that can narrow down the search space of the target identity. We prove the effectiveness of the proposed method by showing extensive ablation studies and visualizations. All the components of the proposed method can be trained in an end-to-end manner with a marginal increase of computational complexity. Finally, the proposed method achieves the state-of-the-art results with significant improvements in 1:1 face verification and 1:N face identification tasks on the following public datasets: LFW, YTF, CALFW, CPLFW, CFP, AgeDB-30, MegaFace, IJB-B and IJB-C.

cs.CV↗

arXiv2020

Discrete Infomax Codes for Supervised Representation Learning

Learning compact discrete representations of data is a key task on its own or for facilitating subsequent processing of data. In this paper we present a model that produces Discrete InfoMax Codes (DIMCO); we learn a probabilistic encoder that yields k-way d-dimensional codes associated with input data. Our model's learning objective is to maximize the mutual information between codes and labels with a regularization, which enforces entries of a codeword to be as independent as possible. We show that the infomax principle also justifies previous loss functions (e.g., cross-entropy) as its special cases. Our analysis also shows that using shorter codes, as DIMCO does, reduces overfitting in the context of few-shot classification. Through experiments in various domains, we observe this implicit meta-regularization effect of DIMCO. Furthermore, we show that the codes learned by DIMCO are efficient in terms of both memory and retrieval time compared to previous methods.

stat.ML↗

arXiv2019

Regularizing Neural Networks via Stochastic Branch Layers

We introduce a novel stochastic regularization technique for deep neural networks, which decomposes a layer into multiple branches with different parameters and merges stochastically sampled combinations of the outputs from the branches during training. Since the factorized branches can collapse into a single branch through a linear operation, inference requires no additional complexity compared to the ordinary layers. The proposed regularization method, referred to as StochasticBranch, is applicable to any linear layers such as fully-connected or convolution layers. The proposed regularizer allows the model to explore diverse regions of the model parameter space via multiple combinations of branches to find better local minima. An extensive set of experiments shows that our method effectively regularizes networks and further improves the generalization performance when used together with other existing regularization techniques.

cs.LG↗

arXiv2019

Relational Knowledge Distillation

Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output activations of individual data examples represented by the teacher. We introduce a novel approach, dubbed relational knowledge distillation (RKD), that transfers mutual relations of data examples instead. For concrete realizations of RKD, we propose distance-wise and angle-wise distillation losses that penalize structural differences in relations. Experiments conducted on different tasks show that the proposed method improves educated student models with a significant margin. In particular for metric learning, it allows students to outperform their teachers' performance, achieving the state of the arts on standard benchmark datasets.

cs.CV↗