Pay Attention to Small Weights

Finetuning large pretrained neural networks is known to be resource-intensive, both in terms of memory and computational cost. To mitigate this, a common approach is to restrict training to a subset of the model parameters. By analyzing the relationship between gradients and weights during finetuning, we observe a notable pattern: large gradients are often associated with small-magnitude weights. This correlation is more pronounced in finetuning settings than in training from scratch. Motivated by this observation, we propose NANOADAM, which dynamically updates only the small-magnitude weights during finetuning and offers several practical advantages: first, this criterion is gradient-free -- the parameter subset can be determined without gradient computation; second, it preserves large-magnitude weights, which are likely to encode critical features learned during pretraining, thereby reducing the risk of catastrophic forgetting; thirdly, it permits the use of larger learning rates and consistently leads to better generalization performance in experiments. We demonstrate this for both NLP and vision tasks.

Bridging Video Quality Scoring and Justification via Large Multimodal Models

Classical video quality assessment (VQA) methods generate a numerical score to judge a video's perceived visual fidelity and clarity. Yet, a score fails to describe the video's complex quality dimensions, restricting its applicability. Benefiting from the linguistic output, adapting video large multimodal models (LMMs) to VQA via instruction tuning has the potential to address this issue. The core of the approach lies in the video quality-centric instruction data. Previous explorations mainly focus on the image domain, and their data generation processes heavily rely on human quality annotations and proprietary systems, limiting data scalability and effectiveness. To address these challenges, we propose the Score-based Instruction Generation (SIG) pipeline. Specifically, SIG first scores multiple quality dimensions of an unlabeled video and maps scores to text-defined levels. It then explicitly incorporates a hierarchical Chain-of-Thought (CoT) to model the correlation between specific dimensions and overall quality, mimicking the human visual system's reasoning process. The automated pipeline eliminates the reliance on expert-written quality descriptions and proprietary systems, ensuring data scalability and generation efficiency. To this end, the resulting Score2Instruct (S2I) dataset contains over 320K diverse instruction-response pairs, laying the basis for instruction tuning. Moreover, to advance video LMMs' quality scoring and justification abilities simultaneously, we devise a progressive tuning strategy to fully unleash the power of S2I. Built upon SIG, we further curate a benchmark termed S2I-Bench with 400 open-ended questions to better evaluate the quality justification capacity of video LMMs. Experimental results on the S2I-Bench and existing benchmarks indicate that our method consistently improves quality scoring and justification capabilities across multiple video LMMs.

HIT Model: A Hierarchical Interaction-Enhanced Two-Tower Model for Pre-Ranking Systems

Online display advertising platforms rely on pre-ranking systems to efficiently filter and prioritize candidate ads from large corpora, balancing relevance to users with strict computational constraints. The prevailing two-tower architecture, though highly efficient due to its decoupled design and pre-caching, suffers from cross-domain interaction and coarse similarity metrics, undermining its capacity to model complex user-ad relationships. In this study, we propose the Hierarchical Interaction-Enhanced Two-Tower (HIT) model, a new architecture that augments the two-tower paradigm with two key components: $\textit{generators}$ that pre-generate holistic vectors incorporating coarse-grained user-ad interactions through a dual-generator framework with a cosine-similarity-based generation loss as the training objective, and $\textit{multi-head representers}$ that project embeddings into multiple latent subspaces to capture fine-grained, multi-faceted user interests and multi-dimensional ad attributes. This design enhances modeling effectiveness without compromising inference efficiency. Extensive experiments on public datasets and large-scale online A/B testing on Tencent's advertising platform demonstrate that HIT significantly outperforms several baselines in relevance metrics, yielding a $1.66\%$ increase in Gross Merchandise Volume and a $1.55\%$ improvement in Return on Investment, alongside similar serving latency to the vanilla two-tower models. The HIT model has been successfully deployed in Tencent's online display advertising system, serving billions of impressions daily. The code is available at https://anonymous.4open.science/r/HIT_model-5C23.

Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial Sampling

Diffusion models have gained attention for their success in modeling complex distributions, achieving impressive perceptual quality in SR tasks. However, existing diffusion-based SR methods often suffer from high computational costs, requiring numerous iterative steps for training and inference. Existing acceleration techniques, such as distillation and solver optimization, are generally task-agnostic and do not fully leverage the specific characteristics of low-level tasks like super-resolution (SR). In this study, we analyze the frequency- and spatial-domain properties of diffusion-based SR methods, revealing key insights into the temporal and spatial dependencies of high-frequency signal recovery. Specifically, high-frequency details benefit from concentrated optimization during early and late diffusion iterations, while spatially textured regions demand adaptive denoising strategies. Building on these observations, we propose the Time-Spatial-aware Sampling strategy (TSS) for the acceleration of Diffusion SR without any extra training cost. TSS combines Time Dynamic Sampling (TDS), which allocates more iterations to refining textures, and Spatial Dynamic Sampling (SDS), which dynamically adjusts strategies based on image content. Extensive evaluations across multiple benchmarks demonstrate that TSS achieves state-of-the-art (SOTA) performance with significantly fewer iterations, improving MUSIQ scores by 0.2 - 3.0 and outperforming the current acceleration methods with only half the number of steps.

Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion

Existing multimodal large model-based image compression frameworks often rely on a fragmented integration of semantic retrieval, latent compression, and generative models, resulting in suboptimal performance in both reconstruction fidelity and coding efficiency. To address these challenges, we propose a residual-guided ultra lowrate image compression named ResULIC, which incorporates residual signals into both semantic retrieval and the diffusion-based generation process. Specifically, we introduce Semantic Residual Coding (SRC) to capture the semantic disparity between the original image and its compressed latent representation. A perceptual fidelity optimizer is further applied for superior reconstruction quality. Additionally, we present the Compression-aware Diffusion Model (CDM), which establishes an optimal alignment between bitrates and diffusion time steps, improving compression-reconstruction synergy. Extensive experiments demonstrate the effectiveness of ResULIC, achieving superior objective and subjective performance compared to state-of-the-art diffusion-based methods with - 80.7%, -66.3% BD-rate saving in terms of LPIPS and FID. Project page is available at https: //njuvision.github.io/ResULIC/.

An Underwater, Fault-Tolerant, Laser-Aided Robotic Multi-Modal Dense SLAM System for Continuous Underwater In-Situ Observation

Existing underwater SLAM systems are difficult to work effectively in texture-sparse and geometrically degraded underwater environments, resulting in intermittent tracking and sparse mapping. Therefore, we present Water-DSLAM, a novel laser-aided multi-sensor fusion system that can achieve uninterrupted, fault-tolerant dense SLAM capable of continuous in-situ observation in diverse complex underwater scenarios through three key innovations: Firstly, we develop Water-Scanner, a multi-sensor fusion robotic platform featuring a self-designed Underwater Binocular Structured Light (UBSL) module that enables high-precision 3D perception. Secondly, we propose a fault-tolerant triple-subsystem architecture combining: 1) DP-INS (DVL- and Pressure-aided Inertial Navigation System): fusing inertial measurement unit, doppler velocity log, and pressure sensor based Error-State Kalman Filter (ESKF) to provide high-frequency absolute odometry 2) Water-UBSL: a novel Iterated ESKF (IESKF)-based tight coupling between UBSL and DP-INS to mitigate UBSL's degeneration issues 3) Water-Stereo: a fusion of DP-INS and stereo camera for accurate initialization and tracking. Thirdly, we introduce a multi-modal factor graph back-end that dynamically fuses heterogeneous sensor data. The proposed multi-sensor factor graph maintenance strategy efficiently addresses issues caused by asynchronous sensor frequencies and partial data loss. Experimental results demonstrate Water-DSLAM achieves superior robustness (0.039 m trajectory RMSE and 100\% continuity ratio during partial sensor dropout) and dense mapping (6922.4 points/m^3 in 750 m^3 water volume, approximately 10 times denser than existing methods) in various challenging environments, including pools, dark underwater scenes, 16-meter-deep sinkholes, and field rivers. Our project is available at https://water-scanner.github.io/.

Deployment Optimization for XL-IRS Assisted Multi-User Communications

In this paper, we study the deployment optimization for an extremely large-scale intelligent reflecting surface (XL-IRS) assisted multi-user communication system, within which the channels between the XL-IRS and the BS (or user) are modeled by the near-field spherical wavefronts. To draw some valuable insights, we first consider the single-user case, where an alternating optimization (AO) based algorithm is devised to maximize the received signal-to-noise ratio (SNR) at the user. To address the high computational complexity issue incurred by the AO based algorithm, three approximate received SNR expressions are obtained to yield useful insights, corresponding to the upper bound, approximate expression, and closed-form. It is demonstrated that the XL-IRS ought to be positioned near the user (rather than the BS) to obtain a higher beamforming gain. Then, for the multi-user scenario, an efficient algorithm is proposed to obtain a high-quality XL-IRS placement solution by using the AO and successive convex approximation (SCA) techniques. Furthermore, the effective degree of freedom (DoF) of the BS-IRS channel is provided, which indicates that the additional effective DoF can be leveraged to improve multi-user spatial multiplexing. Last, numerical results confirm the existence of a trade-off between near-field beam-focusing gain and multiplexing gain.

A Tutorial on MIMO-OFDM ISAC: From Far-Field to Near-Field

Integrated sensing and communication (ISAC) is one of the key usage scenarios for future sixth-generation (6G) mobile communication networks, where communication and sensing (C&S) services are simultaneously provided through shared wireless spectrum, signal processing modules, hardware, and network infrastructure. Such an integration is strengthened by the technology trends in 6G, such as denser network nodes, larger antenna arrays, wider bandwidths, higher frequency bands, and more efficient utilization of spectrum and hardware resources, which incentivize and empower enhanced sensing capabilities. As the dominant waveform used in contemporary communication systems, orthogonal frequency division multiplexing (OFDM) is still expected to be a very competitive technology for 6G, rendering it necessary to thoroughly investigate the potential and challenges of OFDM ISAC. Thus, this paper aims to provide a comprehensive tutorial overview of ISAC systems enabled by large-scale multi-input multi-output (MIMO) and OFDM technologies and to discuss their fundamental principles, advantages, and enabling signal processing methods. To this end, a unified MIMO-OFDM ISAC system model is first introduced, followed by four frameworks for estimating parameters across the spatial, delay, and Doppler domains, including parallel one-domain, sequential one-domain, joint two-domain, and joint three-domain parameter estimation. Next, sensing algorithms and performance analyses are presented in detail for far-field scenarios where uniform plane wave (UPW) propagation is valid, followed by their extensions to near-field scenarios where uniform spherical wave (USW) characteristics need to be considered. Finally, this paper points out open challenges and outlines promising avenues for future research on MIMO-OFDM ISAC.

NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study

In this work, we build the first benchmark dataset for short-form UGC Image Super-resolution in the wild, termed KwaiSR, intending to advance the research on developing image super-resolution algorithms for short-form UGC platforms. This dataset is collected from the Kwai Platform, which is composed of two parts, i.e., synthetic and wild parts. Among them, the synthetic dataset, including 1,900 image pairs, is produced by simulating the degradation following the distribution of real-world low-quality short-form UGC images, aiming to provide the ground truth for training and objective comparison in the validation/testing. The wild dataset contains low-quality images collected directly from the Kwai Platform, which are filtered using the quality assessment method KVQ from the Kwai Platform. As a result, the KwaiSR dataset contains 1800 synthetic image pairs and 1900 wild images, which are divided into training, validation, and testing parts with a ratio of 8:1:1. Based on the KwaiSR dataset, we organize the NTIRE 2025 challenge on a second short-form UGC Video quality assessment and enhancement, which attracts lots of researchers to develop the algorithm for it. The results of this competition have revealed that our KwaiSR dataset is pretty challenging for existing Image SR methods, which is expected to lead to a new direction in the image super-resolution field. The dataset can be found from https://lixinustc.github.io/NTIRE2025-KVQE-KwaSR-KVQ.github.io/.

NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results

This paper provides a review of the NTIRE 2025 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural, realistic outputs while maintaining identity consistency. Its goal is to advance state-of-the-art solutions for perceptual quality and realism, without imposing constraints on computational resources or training data. The track of the challenge evaluates performance using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 141 registrants, with 13 teams submitting valid models, and ultimately, 10 teams achieved a valid score in the final ranking. This collaborative effort advances the performance of real-world face restoration while offering an in-depth overview of the latest trends in the field.