FedAPM: Federated Learning via ADMM with Partial Model Personalization

In federated learning (FL), the assumption that datasets from different devices are independent and identically distributed (i.i.d.) often does not hold due to user differences, and the presence of various data modalities across clients makes using a single model impractical. Personalizing certain parts of the model can effectively address these issues by allowing those parts to differ across clients, while the remaining parts serve as a shared model. However, we found that partial model personalization may exacerbate client drift (each client's local model diverges from the shared model), thereby reducing the effectiveness and efficiency of FL algorithms. We propose an FL framework based on the alternating direction method of multipliers (ADMM), referred to as FedAPM, to mitigate client drift. We construct the augmented Lagrangian function by incorporating first-order and second-order proximal terms into the objective, with the second-order term providing fixed correction and the first-order term offering compensatory correction between the local and shared models. Our analysis demonstrates that FedAPM, by using explicit estimates of the Lagrange multiplier, is more stable and efficient in terms of convergence compared to other FL frameworks. We establish the global convergence of FedAPM training from arbitrary initial points to a stationary point, achieving three types of rates: constant, linear, and sublinear, under mild assumptions. We conduct experiments using four heterogeneous and multimodal datasets with different metrics to validate the performance of FedAPM. Specifically, FedAPM achieves faster and more accurate convergence, outperforming the SOTA methods with average improvements of 12.3% in test accuracy, 16.4% in F1 score, and 18.0% in AUC while requiring fewer communication rounds.

TextVidBench: A Benchmark for Long Video Scene Text Understanding

Despite recent progress on the short-video Text-Visual Question Answering (ViteVQA) task - largely driven by benchmarks such as M4-ViteVQA - existing datasets still suffer from limited video duration and narrow evaluation scopes, making it difficult to adequately assess the growing capabilities of powerful multimodal large language models (MLLMs). To address these limitations, we introduce TextVidBench, the first benchmark specifically designed for long-video text question answering (>3 minutes). TextVidBench makes three key contributions: 1) Cross-domain long-video coverage: Spanning 9 categories (e.g., news, sports, gaming), with an average video length of 2306 seconds, enabling more realistic evaluation of long-video understanding. 2) A three-stage evaluation framework: "Text Needle-in-Haystack -> Temporal Grounding -> Text Dynamics Captioning". 3) High-quality fine-grained annotations: Containing over 5,000 question-answer pairs with detailed semantic labeling. Furthermore, we propose an efficient paradigm for improving large models through: (i) introducing the IT-Rope mechanism and temporal prompt engineering to enhance temporal perception, (ii) adopting non-uniform positional encoding to better handle long video sequences, and (iii) applying lightweight fine-tuning on video-text data. Extensive experiments on multiple public datasets as well as TextVidBench demonstrate that our new benchmark presents significant challenges to existing models, while our proposed method offers valuable insights into improving long-video scene text understanding capabilities.

Automated Model-Free Sorting of Single-Molecule Fluorescence Events Using a Deep Learning Based Hidden-State Model

Single-molecule fluorescence assays enable high-resolution analysis of biomolecular dynamics, but traditional analysis pipelines are labor-intensive and rely on users' experience, limiting scalability and reproducibility. Recent deep learning models have automated aspects of data processing, yet many still require manual thresholds, complex architectures, or extensive labeled data. Therefore, we present DASH, a fully streamlined architecture for trace classification, state assignment, and automatic sorting that requires no user input. DASH demonstrates robust performance across users and experimental conditions both in equilibrium and non-equilibrium systems such as Cas12a-mediated DNA cleavage. This paper proposes a novel strategy for the automatic and detailed sorting of single-molecule fluorescence events. The dynamic cleavage process of Cas12a is used as an example to provide a comprehensive analysis. This approach is crucial for studying biokinetic structural changes at the single-molecule level.

MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection

The recent Segment Anything Model 2 (SAM2) has demonstrated exceptional capabilities in interactive object segmentation for both images and videos. However, as a foundational model on interactive segmentation, SAM2 performs segmentation directly based on mask memory from the past six frames, leading to two significant challenges. Firstly, during inference in videos, objects may disappear since SAM2 relies solely on memory without accounting for object motion information, which limits its long-range object tracking capabilities. Secondly, its memory is constructed from fixed past frames, making it susceptible to challenges associated with object disappearance or occlusion, due to potentially inaccurate segmentation results in memory. To address these problems, we present MoSAM, incorporating two key strategies to integrate object motion cues into the model and establish more reliable feature memory. Firstly, we propose Motion-Guided Prompting (MGP), which represents the object motion in both sparse and dense manners, then injects them into SAM2 through a set of motion-guided prompts. MGP enables the model to adjust its focus towards the direction of motion, thereby enhancing the object tracking capabilities. Furthermore, acknowledging that past segmentation results may be inaccurate, we devise a Spatial-Temporal Memory Selection (ST-MS) mechanism that dynamically identifies frames likely to contain accurate segmentation in both pixel- and frame-level. By eliminating potentially inaccurate mask predictions from memory, we can leverage more reliable memory features to exploit similar regions for improving segmentation results. Extensive experiments on various benchmarks of video object segmentation and video instance segmentation demonstrate that our MoSAM achieves state-of-the-art results compared to other competitors.

Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation

Category-level object pose estimation aims to predict the 6D pose and size of previously unseen instances from predefined categories, requiring strong generalization across diverse object instances. Although many previous methods attempt to mitigate intra-class variations, they often struggle with instances exhibiting complex geometries or significant deviations from canonical shapes. To address this challenge, we propose INKL-Pose, a novel category-level object pose estimation framework that enables INstance-adaptive Keypoint Learning with local-to-global geometric aggregation. Specifically, our approach first predicts semantically consistent and geometric informative keypoints through an Instance-Adaptive Keypoint Generator, then refines them with: (1) a Local Keypoint Feature Aggregator capturing fine-grained geometries, and (2) a Global Keypoint Feature Aggregator using bidirectional Mamba for structural consistency. To enable bidirectional modeling in Mamba, we introduce a Feature Sequence Flipping strategy that preserves spatial coherence while constructing backward feature sequences. Additionally, we design a surface loss and a separation loss to enforce uniform coverage and spatial diversity in keypoint distribution. The generated keypoints are finally mapped to a canonical space for regressing the object's 6D pose and size. Extensive experiments on CAMERA25, REAL275, and HouseCat6D demonstrate that INKL-Pose achieves state-of-the-art performance and significantly outperforms existing methods.

An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes

Large Multimodal Models (LMMs) uniformly perceive video frames, creating computational inefficiency for videos with inherently varying temporal information density. This paper present \textbf{Quicksviewer}, an LMM with new perceiving paradigm that partitions a video of nonuniform density into varying cubes using Gumbel Softmax, followed by a unified resampling for each cube to achieve efficient video understanding. This simple and intuitive approach dynamically compress video online based on its temporal density, significantly reducing spatiotemporal redundancy (overall 45$\times$ compression rate), while enabling efficient training with large receptive field. We train the model from a language backbone through three progressive stages, each incorporating lengthy videos on average of 420s/1fps thanks to the perceiving efficiency. With only 0.8M total video-text samples for training, our model outperforms the direct baseline employing a fixed partitioning strategy by a maximum of 8.72 in accuracy, demonstrating the effectiveness in performance. On Video-MME, Quicksviewer achieves SOTA under modest sequence lengths using just up to 5\% of tokens per frame required by baselines. With this paradigm, scaling up the number of input frames reveals a clear power law of the model capabilities. It is also empirically verified that the segments generated by the cubing network can help for analyzing continuous events in videos.

V-MAGE: A Game Evaluation Framework for Assessing Visual-Centric Capabilities in Multimodal Large Language Models

Recent advancements in Multimodal Large Language Models (MLLMs) have led to significant improvements across various multimodal benchmarks. However, as evaluations shift from static datasets to open-world, dynamic environments, current game-based benchmarks remain inadequate because they lack visual-centric tasks and fail to assess the diverse reasoning skills required for real-world decision-making. To address this, we introduce Visual-centric Multiple Abilities Game Evaluation (V-MAGE), a game-based evaluation framework designed to assess visual reasoning capabilities of MLLMs. V-MAGE features five diverse games with 30+ handcrafted levels, testing models on core visual skills such as positioning, trajectory tracking, timing, and visual memory, alongside higher-level reasoning like long-term planning and deliberation. We use V-MAGE to evaluate leading MLLMs, revealing significant challenges in their visual perception and reasoning. In all game environments, the top-performing MLLMs, as determined by Elo rating comparisons, exhibit a substantial performance gap compared to humans. Our findings highlight critical limitations, including various types of perceptual errors made by the models, and suggest potential avenues for improvement from an agent-centric perspective, such as refining agent strategies and addressing perceptual inaccuracies. Code is available at https://github.com/CSU-JPG/V-MAGE.

Coca-Splat: Collaborative Optimization for Camera Parameters and 3D Gaussians

In this work, we introduce Coca-Splat, a novel approach to addressing the challenges of sparse view pose-free scene reconstruction and novel view synthesis (NVS) by jointly optimizing camera parameters with 3D Gaussians. Inspired by deformable DEtection TRansformer, we design separate queries for 3D Gaussians and camera parameters and update them layer by layer through deformable Transformer layers, enabling joint optimization in a single network. This design demonstrates better performance because to accurately render views that closely approximate ground-truth images relies on precise estimation of both 3D Gaussians and camera parameters. In such a design, the centers of 3D Gaussians are projected onto each view by camera parameters to get projected points, which are regarded as 2D reference points in deformable cross-attention. With camera-aware multi-view deformable cross-attention (CaMDFA), 3D Gaussians and camera parameters are intrinsically connected by sharing the 2D reference points. Additionally, 2D reference point determined rays (RayRef) defined from camera centers to the reference points assist in modeling relationship between 3D Gaussians and camera parameters through RQ-decomposition on an overdetermined system of equations derived from the rays, enhancing the relationship between 3D Gaussians and camera parameters. Extensive evaluation shows that our approach outperforms previous methods, both pose-required and pose-free, on RealEstate10K and ACID within the same pose-free setting.

GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior

Text-guided 3D human generation has advanced with the development of efficient 3D representations and 2D-lifting methods like Score Distillation Sampling (SDS). However, current methods suffer from prolonged training times and often produce results that lack fine facial and garment details. In this paper, we propose GaussianIP, an effective two-stage framework for generating identity-preserving realistic 3D humans from text and image prompts. Our core insight is to leverage human-centric knowledge to facilitate the generation process. In stage 1, we propose a novel Adaptive Human Distillation Sampling (AHDS) method to rapidly generate a 3D human that maintains high identity consistency with the image prompt and achieves a realistic appearance. Compared to traditional SDS methods, AHDS better aligns with the human-centric generation process, enhancing visual quality with notably fewer training steps. To further improve the visual quality of the face and clothes regions, we design a View-Consistent Refinement (VCR) strategy in stage 2. Specifically, it produces detail-enhanced results of the multi-view images from stage 1 iteratively, ensuring the 3D texture consistency across views via mutual attention and distance-guided attention fusion. Then a polished version of the 3D human can be achieved by directly perform reconstruction with the refined images. Extensive experiments demonstrate that GaussianIP outperforms existing methods in both visual quality and training efficiency, particularly in generating identity-preserving results. Our code is available at: https://github.com/silence-tang/GaussianIP.

Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning

Large language models (LLMs) can prove mathematical theorems formally by generating proof steps (\textit{a.k.a.} tactics) within a proof system. However, the space of possible tactics is vast and complex, while the available training data for formal proofs is limited, posing a significant challenge to LLM-based tactic generation. To address this, we introduce a neuro-symbolic tactic generator that synergizes the mathematical intuition learned by LLMs with domain-specific insights encoded by symbolic methods. The key aspect of this integration is identifying which parts of mathematical reasoning are best suited to LLMs and which to symbolic methods. While the high-level idea of neuro-symbolic integration is broadly applicable to various mathematical problems, in this paper, we focus specifically on Olympiad inequalities (Figure~1). We analyze how humans solve these problems and distill the techniques into two types of tactics: (1) scaling, handled by symbolic methods, and (2) rewriting, handled by LLMs. In addition, we combine symbolic tools with LLMs to prune and rank the proof goals for efficient proof search. We evaluate our framework on 161 challenging inequalities from multiple mathematics competitions, achieving state-of-the-art performance and significantly outperforming existing LLM and symbolic approaches without requiring additional training data.