VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward formulation, which leverages tasks with deterministic ground-truth answers to enable precise and stable reward computation. In the visual domain, we similarly observe that a wide range of visual understanding tasks are inherently equipped with well-defined ground-truth annotations. This property makes them naturally compatible with rule-based reward mechanisms. Motivated by this observation, we investigate the extension of R1-style reinforcement learning to Vision-Language Models (VLMs), aiming to enhance their visual reasoning capabilities. To this end, we develop VLM-R1, a dedicated framework designed to harness RL for improving VLMs' performance on general vision-language tasks. Using this framework, we further explore the feasibility of applying RL to visual domain. Experimental results indicate that the RL-based model not only delivers competitive performance on visual understanding tasks but also surpasses Supervised Fine-Tuning (SFT) in generalization ability. Furthermore, we conduct comprehensive ablation studies that uncover a series of noteworthy insights, including the presence of reward hacking in object detection, the emergence of the "OD aha moment", the impact of training data quality, and the scaling behavior of RL across different model sizes. Through these analyses, we aim to deepen the understanding of how reinforcement learning enhances the capabilities of vision-language models, and we hope our findings and open-source contributions will support continued progress in the vision-language RL community. Our code and model are available at https://github.com/om-ai-lab/VLM-R1

RCCFormer: A Robust Crowd Counting Network Based on Transformer

Crowd counting, which is a key computer vision task, has emerged as a fundamental technology in crowd analysis and public safety management. However, challenges such as scale variations and complex backgrounds significantly impact the accuracy of crowd counting. To mitigate these issues, this paper proposes a robust Transformer-based crowd counting network, termed RCCFormer, specifically designed for background suppression and scale awareness. The proposed method incorporates a Multi-level Feature Fusion Module (MFFM), which meticulously integrates features extracted at diverse stages of the backbone architecture. It establishes a strong baseline capable of capturing intricate and comprehensive feature representations, surpassing traditional baselines. Furthermore, the introduced Detail-Embedded Attention Block (DEAB) captures contextual information and local details through global self-attention and local attention along with a learnable manner for efficient fusion. This enhances the model's ability to focus on foreground regions while effectively mitigating background noise interference. Additionally, we develop an Adaptive Scale-Aware Module (ASAM), with our novel Input-dependent Deformable Convolution (IDConv) as its fundamental building block. This module dynamically adapts to changes in head target shapes and scales, significantly improving the network's capability to accommodate large-scale variations. The effectiveness of the proposed method is validated on the ShanghaiTech Part_A and Part_B, NWPU-Crowd, and QNRF datasets. The results demonstrate that our RCCFormer achieves excellent performance across all four datasets, showcasing state-of-the-art outcomes.

Embedding Reliability Verification Constraints into Generation Expansion Planning

Generation planning approaches face challenges in managing the incompatible mathematical structures between stochastic production simulations for reliability assessment and optimization models for generation planning, which hinders the integration of reliability constraints. This study proposes an approach to embedding reliability verification constraints into generation expansion planning by leveraging a weighted oblique decision tree (WODT) technique. For each planning year, a generation mix dataset, labeled with reliability assessment simulations, is generated. An WODT model is trained using this dataset. Reliability-feasible regions are extracted via depth-first search technique and formulated as disjunctive constraints. These constraints are then transformed into mixed-integer linear form using a convex hull modeling technique and embedded into a unit commitment-integrated generation expansion planning model. The proposed approach is validated through a long-term generation planning case study for the Electric Reliability Council of Texas (ERCOT) region, demonstrating its effectiveness in achieving reliable and optimal planning solutions.

Overcoming the Identity Mapping Problem in Self-Supervised Hyperspectral Anomaly Detection

The surge of deep learning has catalyzed considerable progress in self-supervised Hyperspectral Anomaly Detection (HAD). The core premise for self-supervised HAD is that anomalous pixels are inherently more challenging to reconstruct, resulting in larger errors compared to the background. However, owing to the powerful nonlinear fitting capabilities of neural networks, self-supervised models often suffer from the Identity Mapping Problem (IMP). The IMP manifests as a tendency for the model to overfit to the entire image, particularly with increasing network complexity or prolonged training iterations. Consequently, the whole image can be precisely reconstructed, and even the anomalous pixels exhibit imperceptible errors, making them difficult to detect. Despite the proposal of several models aimed at addressing the IMP-related issues, a unified descriptive framework and validation of solutions for IMP remain lacking. In this paper, we conduct an in-depth exploration to IMP, and summarize a unified framework that describes IMP from the perspective of network optimization, which encompasses three aspects: perturbation, reconstruction, and regularization. Correspondingly, we introduce three solutions: superpixel pooling and uppooling for perturbation, error-adaptive convolution for reconstruction, and online background pixel mining for regularization. With extensive experiments being conducted to validate the effectiveness, it is hoped that our work will provide valuable insights and inspire further research for self-supervised HAD. Code: \url{https://github.com/yc-cui/Super-AD}.

A Decade of Deep Learning for Remote Sensing Spatiotemporal Fusion: Advances, Challenges, and Opportunities

Hardware limitations and satellite launch costs make direct acquisition of high temporal-spatial resolution remote sensing imagery challenging. Remote sensing spatiotemporal fusion (STF) technology addresses this problem by merging high temporal but low spatial resolution imagery with high spatial but low temporal resolution imagery to efficiently generate high spatiotemporal resolution satellite images. STF provides unprecedented observational capabilities for land surface change monitoring, agricultural management, and environmental research. Deep learning (DL) methods have revolutionized the remote sensing spatiotemporal fusion field over the past decade through powerful automatic feature extraction and nonlinear modeling capabilities, significantly outperforming traditional methods in handling complex spatiotemporal data. Despite the rapid development of DL-based remote sensing STF, the community lacks a systematic review of this quickly evolving field. This paper comprehensively reviews DL developments in remote sensing STF over the last decade, analyzing key research trends, method classifications, commonly used datasets, and evaluation metrics. It discusses major challenges in existing research and identifies promising future research directions as references for researchers in this field to inspire new ideas. The specific models, datasets, and other information mentioned in this article have been collected in: https://github.com/yc-cui/Deep-Learning-Spatiotemporal-Fusion-Survey.

H2VU-Benchmark: A Comprehensive Benchmark for Hierarchical Holistic Video Understanding

With the rapid development of multimodal models, the demand for assessing video understanding capabilities has been steadily increasing. However, existing benchmarks for evaluating video understanding exhibit significant limitations in coverage, task diversity, and scene adaptability. These shortcomings hinder the accurate assessment of models' comprehensive video understanding capabilities. To tackle this challenge, we propose a hierarchical and holistic video understanding (H2VU) benchmark designed to evaluate both general video and online streaming video comprehension. This benchmark contributes three key features: Extended video duration: Spanning videos from brief 3-second clips to comprehensive 1.5-hour recordings, thereby bridging the temporal gaps found in current benchmarks. Comprehensive assessment tasks: Beyond traditional perceptual and reasoning tasks, we have introduced modules for countercommonsense comprehension and trajectory state tracking. These additions test the models' deep understanding capabilities beyond mere prior knowledge. Enriched video data: To keep pace with the rapid evolution of current AI agents, we have expanded first-person streaming video datasets. This expansion allows for the exploration of multimodal models' performance in understanding streaming videos from a first-person perspective. Extensive results from H2VU reveal that existing multimodal large language models (MLLMs) possess substantial potential for improvement in our newly proposed evaluation tasks. We expect that H2VU will facilitate advancements in video understanding research by offering a comprehensive and in-depth analysis of MLLMs.

Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction

Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in voice data collection, weakness in dynamic control, and limited intelligence. To address these challenges, this paper introduces Step-Audio, the first production-ready open-source solution. Key contributions include: 1) a 130B-parameter unified speech-text multi-modal model that achieves unified understanding and generation, with the Step-Audio-Chat version open-sourced; 2) a generative speech data engine that establishes an affordable voice cloning framework and produces the open-sourced lightweight Step-Audio-TTS-3B model through distillation; 3) an instruction-driven fine control system enabling dynamic adjustments across dialects, emotions, singing, and RAP; 4) an enhanced cognitive architecture augmented with tool calling and role-playing abilities to manage complex tasks effectively. Based on our new StepEval-Audio-360 evaluation benchmark, Step-Audio achieves state-of-the-art performance in human evaluations, especially in terms of instruction following. On open-source benchmarks like LLaMA Question, shows 9.3% average performance improvement, demonstrating our commitment to advancing the development of open-source multi-modal language technologies. Our code and models are available at https://github.com/stepfun-ai/Step-Audio.

Relational Norms for Human-AI Cooperation

How we should design and interact with social artificial intelligence depends on the socio-relational role the AI is meant to emulate or occupy. In human society, relationships such as teacher-student, parent-child, neighbors, siblings, or employer-employee are governed by specific norms that prescribe or proscribe cooperative functions including hierarchy, care, transaction, and mating. These norms shape our judgments of what is appropriate for each partner. For example, workplace norms may allow a boss to give orders to an employee, but not vice versa, reflecting hierarchical and transactional expectations. As AI agents and chatbots powered by large language models are increasingly designed to serve roles analogous to human positions - such as assistant, mental health provider, tutor, or romantic partner - it is imperative to examine whether and how human relational norms should extend to human-AI interactions. Our analysis explores how differences between AI systems and humans, such as the absence of conscious experience and immunity to fatigue, may affect an AI's capacity to fulfill relationship-specific functions and adhere to corresponding norms. This analysis, which is a collaborative effort by philosophers, psychologists, relationship scientists, ethicists, legal experts, and AI researchers, carries important implications for AI systems design, user behavior, and regulation. While we accept that AI systems can offer significant benefits such as increased availability and consistency in certain socio-relational roles, they also risk fostering unhealthy dependencies or unrealistic expectations that could spill over into human-human relationships. We propose that understanding and thoughtfully shaping (or implementing) suitable human-AI relational norms will be crucial for ensuring that human-AI interactions are ethical, trustworthy, and favorable to human well-being.

Mamba-MOC: A Multicategory Remote Object Counting via State Space Model

Multicategory remote object counting is a fundamental task in computer vision, aimed at accurately estimating the number of objects of various categories in remote images. Existing methods rely on CNNs and Transformers, but CNNs struggle to capture global dependencies, and Transformers are computationally expensive, which limits their effectiveness in remote applications. Recently, Mamba has emerged as a promising solution in the field of computer vision, offering a linear complexity for modeling global dependencies. To this end, we propose Mamba-MOC, a mamba-based network designed for multi-category remote object counting, which represents the first application of Mamba to remote sensing object counting. Specifically, we propose a cross-scale interaction module to facilitate the deep integration of hierarchical features. Then we design a context state space model to capture both global and local contextual information and provide local neighborhood information during the scan process. Experimental results in large-scale realistic scenarios demonstrate that our proposed method achieves state-of-the-art performance compared with some mainstream counting algorithms.

Explainable Neural Networks with Guarantees: A Sparse Estimation Approach

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model, termed SparXnet, is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily complex relationships, our neural network architecture enables automatic selection of a sparse set of important features, with the final prediction being a linear combination of rescaled versions of these features. We demonstrate the ability to select significant features while maintaining comparable predictive performance and direct interpretability through extensive experiments on synthetic and real-world datasets. We also provide theoretical analysis on the generalization bounds of our framework, which is favorably linear in the number of selected features and only logarithmic in the number of input features. We further lift any dependence of sample complexity on the number of parameters or the architectural details under very mild conditions. Our research paves the way for further research on sparse and explainable neural networks with guarantee.