Large language models (LLMs) increasingly rely on reinforcement learning (RL) to enhance their reasoning capabilities through feedback. A critical challenge is verifying the consistency of model-generated responses and reference answers, since these responses are often lengthy, diverse, and nuanced. Rule-based verifiers struggle with complexity, prompting the use of model-based verifiers. Existing research primarily focuses on building better verifiers, yet a systematic evaluation of different types of verifiers' performance across domains remains lacking, severely constraining the reliable development of Reinforcement Learning with Verifiable Reward (RLVR). To address this, we propose VerifyBench--a cross-domain comprehensive benchmark for systematically evaluating verifiers. We construct about 4,000 expert-level questions covering mathematics, physics, chemistry, and biology. Questions are equipped with reference answers and diverse responses. The reliability of the evaluation is ensured through a rigorous collection and annotation process conducted by a multidisciplinary expert team. We design a four-dimensional experimental framework to comprehensively compare the performance boundaries of specialized verifiers and general LLMs under combined conditions of extracted answers vs. complete responses, and short vs. long outputs. Our evaluation uncovers fundamental trade-offs in verifiers: while specialized verifiers achieve leading accuracy (the best model reaching 96.48% in chemistry), they exhibit deficiencies in recall; general models show stronger inclusivity but unstable accuracy. More importantly, we discover verifiers' high sensitivity to input structure and inherent limitations in cross-domain generalization, providing critical insights into the bottlenecks of current verifier technology.

Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and reasoning and allow models to exploit global context, failing to rigorously evaluate true causal and stepwise reasoning. We present CausalStep, a benchmark designed for explicit stepwise causal reasoning in videos. CausalStep segments videos into causally linked units and enforces a strict stepwise question-answer (QA) protocol, requiring sequential answers and preventing shortcut solutions. Each question includes carefully constructed distractors based on error type taxonomy to ensure diagnostic value. The benchmark features 100 videos across six categories and 1,852 multiple-choice QA pairs. We introduce seven diagnostic metrics for comprehensive evaluation, enabling precise diagnosis of causal reasoning capabilities. Experiments with leading proprietary and open-source models, as well as human baselines, reveal a significant gap between current models and human-level stepwise reasoning. CausalStep provides a rigorous benchmark to drive progress in robust and interpretable video reasoning.

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements.This is mainly due to information loss during image encoding or insufficient attention to critical regions.Recent work has shown promise by incorporating pixel-level visual information into the reasoning process, enabling VLMs to access high-resolution visual details during their thought process.However, this pixel-level information is often overused, leading to inefficiency and distraction from irrelevant visual details.To address these challenges, we propose the first framework for adaptive pixel reasoning that dynamically determines necessary pixel-level operations based on the input query.Specifically, we first apply operation-aware supervised fine-tuning to establish baseline competence in textual reasoning and visual operations, then design a novel rollout-guided reinforcement learning framework relying on feedback of the model's own responses, which enables the VLM to determine when pixel operations should be invoked based on query difficulty.Experiments on extensive multimodal reasoning benchmarks show that our model achieves superior performance while significantly reducing unnecessary visual operations.Impressively, our model achieves 73.4% accuracy on HR-Bench 4K while maintaining a tool usage ratio of only 20.1%, improving accuracy and simultaneously reducing tool usage by 66.5% compared to the previous methods.

Air-writing has emerged as a promising communication modality for AR/VR and metaverse environments, enabling quiet, non-contact text input by translating finger movements into natural language. However, existing approaches typically project in-air writing onto a virtual 2D plane and assume characters are formed with a single continuous stroke–an oversimplification that neglects the rich 3D structure inherent in natural handwriting. In this work, we challenge the “single-stroke 2D” paradigm and explore the role of depth cues in enhancing air-writing recognition. To this end, we present DAAWBench, the first large-scale Depth-Aware Air-Writing dataset, featuring 8.8 million RGB-D frames annotated with 3,755 Chinese characters from the GB2312-80 Level-1 set. Our analysis reveals consistent depth variations at stroke boundaries, indicating that stroke segmentation and character recognition can benefit from depth modeling. Based on these insights, we propose DARec, a novel 3D trajectory-based recognition model that effectively leverages depth-aware priors. Extensive experiments across in-domain and out-of-domain settings, including evaluations with vision-language models (e.g., GPT-4o, Qwen-VL) and human baselines, show that DARec significantly outperforms 2D-only counterparts, achieving 87.73% accuracy versus 9.05%. Our findings demonstrate the critical importance of depth modeling in human-computer co-creative interfaces, and we will publicly release our dataset and code at https://github.com/wmeiqi/DAAWBench.

Vision-Language Tracking (VLT) aims to localize a target in video sequences using a visual template and language description. While textual cues enhance tracking potential, current datasets typically contain much more image data than text, limiting the ability of VLT methods to align the two modalities effectively. To address this imbalance, we propose a novel plug-and-play method named CTVLT that leverages the strong text-image alignment capabilities of foundation grounding models. CTVLT converts textual cues into interpretable visual heatmaps, which are easier for trackers to process. Specifically, we design a textual cue mapping module that transforms textual cues into target distribution heatmaps, visually representing the location described by the text. Additionally, the heatmap guidance module fuses these heatmaps with the search image to guide tracking more effectively. Extensive experiments on mainstream benchmarks demonstrate the effectiveness of our approach, achieving state-of-the-art performance and validating the utility of our method for enhanced VLT.

Vision-language tracking aims to locate the target object in the video sequence using a template patch and a language description provided in the initial frame. To achieve robust tracking, especially in complex long-term scenarios that reflect real-world conditions as recently highlighted by MGIT, it is essential not only to characterize the target features but also to utilize the context features related to the target. However, the visual and textual target-context cues derived from the initial prompts generally align only with the initial target state. Due to their dynamic nature, target states are constantly changing, particularly in complex long-term sequences. It is intractable for these cues to continuously guide Vision-Language Trackers (VLTs). Furthermore, for the text prompts with diverse expressions, our experiments reveal that existing VLTs struggle to discern which words pertain to the target or the context, complicating the utilization of textual cues. In this work, we present a novel tracker named ATCTrack, which can obtain multimodal cues Aligned with the dynamic target states through comprehensive Target-Context feature modeling, thereby achieving robust tracking. Specifically, (1) for the visual modality, we propose an effective temporal visual target-context modeling approach that provides the tracker with timely visual cues. (2) For the textual modality, we achieve precise target words identification solely based on textual content, and design an innovative context words calibration method to adaptively utilize auxiliary context words. (3) We conduct extensive experiments on mainstream benchmarks and ATCTrack achieves a new SOTA performance. The code and models will be released at: https://github.com/XiaokunFeng/ATCTrack.

Effectively modeling and utilizing spatiotemporal features from RGB and other modalities (e.g., depth, thermal, and event data, denoted as X) is the core of RGB-X tracker design. Existing methods often employ two parallel branches to separately process the RGB and X input streams, requiring the model to simultaneously handle two dispersed feature spaces, which complicates both the model structure and computation process. More critically, intra-modality spatial modeling within each dispersed space incurs substantial computational overhead, limiting resources for inter-modality spatial modeling and temporal modeling. To address this, we propose a novel tracker, CSTrack, which focuses on modeling Compact Spatiotemporal features to achieve simple yet effective tracking. Specifically, we first introduce an innovative Spatial Compact Module that integrates the RGB-X dual input streams into a compact spatial feature, enabling thorough intra- and inter-modality spatial modeling. Additionally, we design an efficient Temporal Compact Module that compactly represents temporal features by constructing the refined target distribution heatmap. Extensive experiments validate the effectiveness of our compact spatiotemporal modeling method, with CSTrack achieving new SOTA results on mainstream RGB-X benchmarks. The code and models will be released at: https://github.com/XiaokunFeng/CSTrack.

Satellite technology has significantly influenced our daily lives, manifested in applications such as navigation and communication. With its development, a vast amount of multimodal satellite commonsense data has been generated, thus leading to an urgent demand for conversation about satellite data. However, existing large language models suffer from prevalent hallucinations and poor comprehensibility on multimodal satellite data due to their high professional content threshold and partial information opacity. To address these issues, we propose a multimodal satellite knowledge retrieval-augmented iterative alignment framework (Sat-RIA) for satellite commonsense conversation. We first construct multi-view retrieval expert knowledge to reduce hallucinations and enhance the interpretability of responses, which incorporates the satellite expert database, satellite rule, satellite image database, and a satellite knowledge graph. We next design commonsense conversation instructions to make the answers more legible and understandable. Furthermore, the retrieval-augmented iterative alignment module refines response precision by aligning outputs with task-specific standards through multi-stage evaluations. Finally, we construct satellite multi-turn dialogue and visual question-answer datasets for a more comprehensive evaluation of satellite commonsense conversation. Experimental results demonstrate that Sat-RIA outperforms existing large language models and provides more comprehensible answers with fewer hallucinations.

Nighttime UAV tracking presents significant challenges due to extreme illumination variations and viewpoint changes, which severely degrade tracking performance. Existing approaches either rely on light enhancers with high computational costs or introduce redundant domain adaptation mechanisms, failing to fully utilize the dynamic features in varying perspectives. To address these issues, we propose DARTer (Dynamic Adaptive Representation Tracker), an end-to-end tracking framework designed for nighttime UAV scenarios. DARTer leverages a Dynamic Feature Blender (DFB) to effectively fuse multi-perspective nighttime features from static and dynamic templates, enhancing representation robustness. Meanwhile, a Dynamic Feature Activator (DFA) adaptively activates Vision Transformer layers based on extracted features, significantly improving efficiency by reducing redundant computations. Our model eliminates the need for complex multi-task loss functions, enabling a streamlined training process. Extensive experiments on multiple nighttime UAV tracking benchmarks demonstrate the superiority of DARTer over state-of-the-art trackers. These results confirm that DARTer effectively balances tracking accuracy and efficiency, making it a promising solution for real-world nighttime UAV tracking applications.

Vision-language tracking (VLT) enhances traditional visual object tracking by integrating language descriptions, requiring the tracker to flexibly understand complex and diverse text in addition to visual information. However, most existing vision-language trackers still overly rely on initial fixed multimodal prompts, which struggle to provide effective guidance for dynamically changing targets. Fortunately, the Complementary Learning Systems (CLS) theory suggests that the human memory system can dynamically store and utilize multimodal perceptual information, thereby adapting to new scenarios. Inspired by this, (i) we propose a Memory-based Vision-Language Tracker (MemVLT). By incorporating memory modeling to adjust static prompts, our approach can provide adaptive prompts for tracking guidance. (ii) Specifically, the memory storage and memory interaction modules are designed in accordance with CLS theory. These modules facilitate the storage and flexible interaction between short-term and long-term memories, generating prompts that adapt to target variations. (iii) Finally, we conduct extensive experiments on mainstream VLT datasets (e.g., MGIT, TNL2K, LaSOT and LaSOT$_{ext}$). Experimental results show that MemVLT achieves new state-of-the-art performance. Impressively, it achieves 69.4% AUC on the MGIT and 63.3% AUC on the TNL2K, improving the existing best result by 8.4% and 4.7%, respectively.

Human visual search ability enables efficient and accurate tracking of an arbitrary moving target, which is a significant research interest in cognitive neuroscience. The recently proposed Central-Peripheral Dichotomy (CPD) theory sheds light on how humans effectively process visual information and track moving targets in complex environments. However, existing visual object tracking algorithms still fall short of matching human performance in maintaining tracking over time, particularly in complex scenarios requiring robust visual search skills. These scenarios often involve Spatio-Temporal Discontinuities (i.e., STDChallenge), prevalent in long-term tracking and global instance tracking. To address this issue, we conduct research from a human-like modeling perspective: (1) Inspired by the CPD, we pro- pose a new tracker named CPDTrack to achieve human-like visual search ability. The central vision of CPDTrack leverages the spatio-temporal continuity of videos to introduce priors and enhance localization precision, while the peripheral vision improves global awareness and detects object movements. (2) To further evaluate and analyze STDChallenge, we create the STDChallenge Benchmark. Besides, by incorporating human subjects, we establish a human baseline, creating a high- quality environment specifically designed to assess trackers’ visual search abilities in videos across STDChallenge. (3) Our extensive experiments demonstrate that the proposed CPDTrack not only achieves state-of-the-art (SOTA) performance in this challenge but also narrows the behavioral differences with humans. Additionally, CPDTrack exhibits strong generalizability across various challenging benchmarks. In summary, our research underscores the importance of human-like modeling and offers strategic insights for advancing intelligent visual target tracking. Code and models are available at https://github.com/ZhangDailing8/CPDTrack.

Tracking an arbitrary moving target in a video sequence is the foundation for high-level tasks like video understanding. Although existing visual-based trackers have demonstrated good tracking capabilities in short video sequences, they always perform poorly in complex environments, as represented by the recently proposed global instance tracking task, which consists of longer videos with more complicated narrative content. Recently, several works have introduced natural language into object tracking, desiring to address the limitations of relying only on a single visual modality. However, these selected videos are still short sequences with uncomplicated spatio-temporal and causal relationships, and the provided semantic descriptions are too simple to characterize video content.To address these issues, we (1) first propose a new multi-modal global instance tracking benchmark named MGIT. It consists of 150 long video sequences with a total of 2.03 million frames, aiming to fully represent the complex spatio-temporal and causal relationships coupled in longer narrative content. (2) Each video sequence is annotated with three semantic grains (i.e., action, activity, and story) to model the progressive process of human cognition. We expect this multi-granular annotation strategy can provide a favorable environment for multi-modal object tracking research and long video understanding. (3) Besides, we execute comparative experiments on existing multi-modal object tracking benchmarks, which not only explore the impact of different annotation methods, but also validate that our annotation method is a feasible solution for coupling human understanding into semantic labels. (4) Additionally, we conduct detailed experimental analyses on MGIT, and hope the explored performance bottlenecks of existing algorithms can support further research in multi-modal object tracking. The proposed benchmark, experimental results, and toolkit will be released gradually on http://videocube.aitestunion.com/.