Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual information representation. Herein, we introduce Visual Tokens Withdrawal (VTW), a plug-and-play module to boost MLLMs for rapid inference. Our approach is inspired by two intriguing phenomena we have observed: (1) the attention sink phenomenon that is prevalent in LLMs also persists in MLLMs, suggesting that initial tokens and nearest tokens receive the majority of attention, while middle vision tokens garner minimal attention in deep layers; (2) the presence of information migration, which implies that visual information is transferred to subsequent text tokens within the first few layers of MLLMs. As per our findings, we conclude that vision tokens are unnecessary in the deep layers of MLLMs. Thus, we strategically withdraw them at a certain layer, enabling only text tokens to engage in subsequent layers. To pinpoint the ideal layer for VTW, we initially analyze a limited set of tiny datasets and choose the first layer that meets the Kullback-Leibler divergence criterion. Our VTW approach can cut computational overhead by over 40% across diverse multimodal tasks while maintaining performance.

Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Mosen Alharthi, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Ma Zhuoheng, Yuhao Du, He Zhang, Saied Alshahrani, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models based on Group Relative Policy Optimization (GRPO). GRPO, while effective, incurs high training costs due to the need to sample multiple completions for each question. Our experiment and theoretical analysis reveal that the number of completions impacts model accuracy yet increases training time multiplicatively, and not all completions contribute equally to policy training---their contribution depends on their relative advantage. To address these issues, we propose CPPO, which prunes completions with low absolute advantages, significantly reducing the number needed for gradient calculation and updates. Additionally, we introduce a dynamic completion allocation strategy to maximize GPU utilization by incorporating additional questions, further enhancing training efficiency. Experiments show that CPPO achieves up to $7.98\times$ speedup on GSM8K and $3.48\times$ on Math while preserving or even enhancing the accuracy compared to the original GRPO. We release our code at https://github.com/lzhxmu/CPPO.

Diffusion models suffer severe object repetition and local distortion when the inference resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate method for patch-wise higher-resolution diffusion extrapolation without training. Our in-depth analysis in this paper shows that using an identical text prompt for different patches leads to repetitive generation, while the absence of a prompt undermines image details. In response, our AccDiffusion v2 novelly decouples the vanilla image-content-aware prompt into a set of patch-content-aware prompts, each of which serves as a more precise description of a patch. Further analysis reveals that local distortion arises from inaccurate descriptions in prompts about the local structure of higher-resolution images. To address this issue, AccDiffusion v2, for the first time, introduces an auxiliary local structural information through ControlNet during higher-resolution diffusion extrapolation aiming to mitigate the local distortions. Finally, our analysis indicates that global semantic information is conducive to suppressing both repetitive generation and local distortion. Hence, our AccDiffusion v2 further proposes dilated sampling with window interaction for better global semantic information during higher-resolution diffusion extrapolation. We conduct extensive experiments, including both quantitative and qualitative comparisons, to demonstrate the efficacy of our AccDiffusion v2. The quantitative comparison shows that AccDiffusion v2 achieves state-of-the-art performance in image generation extrapolation without training. The qualitative comparison intuitively illustrates that AccDiffusion v2 effectively suppresses the issues of repetitive generation and local distortion in image generation extrapolation.

The MiniLED mass transfer process requires high-speed and high-precision devices to guarantee mass production and precise mounting. The motivation of this article is to combine the ability to enable the mechanical transfer approaches to run in the manner of continuous manipulation to increase efficiency. The developed system achieves this objective by proposing a compliant flying ejector-pin transfer (CFET) strategy, whose performance is enhanced by a novel local gain-scheduling iterative learning control (LGS-ILC) scheme. First, a CFET strategy is proposed, which is achieved by incorporating synchronous motion into the flip-chip-on-board transfer method. Then, the development of a flying ejector-pin system is presented, including system design and its working principle. Next, to provide high-speed and high-accuracy tracking controls for CFET implementation, a first-step vibration (FSV) behavior is analytically identified and modeled to capture the dynamic characteristics of the system in the case of high-speed trajectory tracking by ILC-based motion control. Thereafter, to address this behavior, a novel LGS-ILC is designed, which improves the tracking performance by predicting and suppressing FSV. Besides, the convergence of LGS-ILC and control system are analyzed in theory. Finally, a series of verification tests were carried out, including experimental validation of LGS-ILC and closed-loop CFET experiments. The results indicate that the LGS-ILC can effectively improve the performance in high-speed trajectory tracking. Besides, the transfer period and accuracy of the developed system are achieved as 50 ms and$\pm$2.5$\mu$m, respectively, uniformly proving that high-efficiency continuous manipulation is achieved.

Post-training Sparsity (PTS) is a recently emerged av-enue that chases efficient network sparsity with limited data in need. Existing PTS methods, however, undergo significant performance degradation compared with traditional methods that retrain the sparse networks via the whole dataset, especially at high sparsity ratios. In this paper, we attempt to reconcile this disparity by transposing three cardinal factors that profoundly alter the performance of conventional sparsity into the context of PTS. Our endeav-ors particularly comprise (1) A base-decayed sparsity objective that promotes efficient knowledge transferring from dense network to the sparse counterpart. (2) A reducing-regrowing search algorithm designed to ascertain the op-timal sparsity distribution while circumventing overfitting to the small calibration set in PTS. (3) The employment of dynamic sparse training predicated on the preceding as-pects, aimed at comprehensively optimizing the sparsity structure while ensuring training stability. Our proposed framework, termed UniPTS, is validated to be much superior to existing PTS methods across extensive benchmarks. As an illustration, it amplifies the performance of POT, a recently proposed recipe, from 3.9% to 68.6% when pruning ResNet-50 at 90% sparsity ratio on ImageNet. We re-lease the code of our paper at https://github.com/xjjxmu/UniPTS.

Reinforcement Learning from Human Feedback (RLHF) is key to aligning Large Language Models (LLMs), typically paired with the Proximal Policy Optimization (PPO) algorithm. While PPO is a powerful method designed for general reinforcement learning tasks, it is overly sophisticated for LLMs, leading to laborious hyper-parameter tuning and significant computation burdens. To make RLHF efficient, we present ReMax, which leverages 3 properties of RLHF: fast simulation, deterministic transitions, and trajectory-level rewards. These properties are not exploited in PPO, making it less suitable for RLHF. Building on the renowned REINFORCE algorithm, ReMax does not require training an additional value model as in PPO and is further enhanced with a new variance reduction technique. ReMax offers several benefits over PPO: it is simpler to implement, eliminates more than 4 hyper-parameters in PPO, reduces GPU memory usage, and shortens training time. ReMax can save about 46% GPU memory than PPO when training a 7B model and enables training on A800-80GB GPUs without the memory-saving offloading technique needed by PPO. Applying ReMax to a Mistral-7B model resulted in a 94.78% win rate on the AlpacaEval leaderboard and a 7.739 score on MT-bench, setting a new SOTA for open-source 7B models. These results show the effectiveness of ReMax while addressing the limitations of PPO in LLMs.

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 consistent mixed images or more precise mixed labels, but inevitably introduce heavy training overhead or require extra information, undermining ease of use. To this end, we propose an novel and effective Self-Motivated image Mixing method (SMMix), which motivates both image and label enhancement by the model under training itself. Specifically, we propose a max-min attention region mixing approach that enriches the attention-focused objects in the mixed images. Then, we introduce a fine-grained label assignment technique that co-trains the output tokens of mixed images with fine-grained supervision. Moreover, we devise a novel feature consistency constraint to align features from mixed and unmixed images. Due to the subtle designs of the self-motivated paradigm, our SMMix is significant in its smaller training overhead and better performance than other CutMix variants. In particular, SMMix improves the accuracy of DeiT-T/S/B, CaiT-XXS-24/36, and PVT-T/S/M/L by more than +1% on ImageNet-1k. The generalization capability of our method is also demonstrated on downstream tasks and out-of-distribution datasets. Our project is available at https://github.com/ChenMnZ/SMMix.

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 performed on NVIDIA A100 GPUs. Current implementation on N:M sparsity requires a tedious pre-training phase or computationally heavy from-scratch training. To circumvent these problems, this paper presents an efficient solution for achieving N:M fine-grained sparsity from scratch. Specifically, we first make a re-formulation to convert the N:M fine-grained sparsity into a combinatorial problem, in which, the object falls into choosing the best weight combination among $C_M^N$ candidates. Then, we equip each combination with a learnable importance score, which can be jointly optimized along with its associated weights. Through rigorous proof, we demonstrate that the magnitude of the optimized score well reflects the importance of its corresponding weights combination to the training loss. Therefore, by gradually removing combinations with smaller scores till the best one is left, N:M fine-grained sparsity can be efficiently optimized during the normal training phase without any extra expenditure. Comprehensive experimental results have demonstrated that our proposed method for learning best combination, dubbed as LBC, consistently increases the efficacy of the off-the-shelf N:M methods across varying networks and datasets. Our project is released at https://github.com/zyxxmu/LBC.