Hanqian Li

Yibo Shi, Jungang Li, Linghao Zhang et al.

Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability. We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents. Its core benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65). We evaluate agents with TCR (Task Complete Rate), focusing on tasks whose completion requires carrying forward critical intermediate state; AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions and centering interaction memory in evaluation. Across open- and closed-source GUI agents, we observe a consistent pattern: as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes. Guided by this diagnosis, we propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making. Across multiple settings and 12 evaluated GUI agents, ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%, indicating that anchored, structured memory effectively mitigates the interaction-memory bottleneck in long-horizon GUI tasks. The code, benchmark, and related resources are publicly available at [https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).

Ye Pan, Chi Kit Wong, Yuanhuiyi Lyu et al.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable video reasoning capabilities across diverse tasks. However, their ability to understand human intent at a fine-grained level in egocentric videos remains largely unexplored. Existing benchmarks focus primarily on episode-level intent reasoning, overlooking the finer granularity of step-level intent understanding. Yet applications such as intelligent assistants, robotic imitation learning, and augmented reality guidance require understanding not only what a person is doing at each step, but also why and what comes next, in order to provide timely and context-aware support. To this end, we introduce EgoIntent, a step-level intent understanding benchmark for egocentric videos. It comprises 3,014 steps spanning 15 diverse indoor and outdoor daily-life scenarios, and evaluates models on three complementary dimensions: local intent (What), global intent (Why), and next-step plan (Next). Crucially, each clip is truncated immediately before the key outcome of the queried step (e.g., contact or grasp) occurs and contains no frames from subsequent steps, preventing future-frame leakage and enabling a clean evaluation of anticipatory step understanding and next-step planning. We evaluate 15 MLLMs, including both state-of-the-art closed-source and open-source models. Even the best-performing model achieves an average score of only 33.31 across the three intent dimensions, underscoring that step-level intent understanding in egocentric videos remains a highly challenging problem that calls for further investigation.

Hanqian Li, Ruinan Zhang, Ye Pan et al.

Remote sensing target detection aims to identify and locate critical targets within remote sensing images, finding extensive applications in agriculture and urban planning. Feature pyramid networks (FPNs) are commonly used to extract multi-scale features. However, existing FPNs often overlook extracting low-level positional information and fine-grained context interaction. To address this, we propose a novel location refined feature pyramid network (LR-FPN) to enhance the extraction of shallow positional information and facilitate fine-grained context interaction. The LR-FPN consists of two primary modules: the shallow position information extraction module (SPIEM) and the contextual interaction module (CIM). Specifically, SPIEM first maximizes the retention of solid location information of the target by simultaneously extracting positional and saliency information from the low-level feature map. Subsequently, CIM injects this robust location information into different layers of the original FPN through spatial and channel interaction, explicitly enhancing the object area. Moreover, in spatial interaction, we introduce a simple local and non-local interaction strategy to learn and retain the saliency information of the object. Lastly, the LR-FPN can be readily integrated into common object detection frameworks to improve performance significantly. Extensive experiments on two large-scale remote sensing datasets (i.e., DOTAV1.0 and HRSC2016) demonstrate that the proposed LR-FPN is superior to state-of-the-art object detection approaches. Our code and models will be publicly available.

Yupei Li, Qiyang Sun, Hanqian Li et al.

Machine-generated music (MGM) has become a groundbreaking innovation with wide-ranging applications, such as music therapy, personalised editing, and creative inspiration within the music industry. However, the unregulated proliferation of MGM presents considerable challenges to the entertainment, education, and arts sectors by potentially undermining the value of high-quality human compositions. Consequently, MGM detection (MGMD) is crucial for preserving the integrity of these fields. Despite its significance, MGMD domain lacks comprehensive systematic evaluation results necessary to drive meaningful progress. To address this gap, we conduct experiments on existing large-scale datasets using a range of foundational models for audio processing, establishing systematic evaluation results tailored to the MGMD task. Our selection includes traditional machine learning models, deep neural networks, Transformer-based architectures, and State space models (SSM). Recognising the inherently multimodal nature of music, which integrates both melody and lyrics, we also explore fundamental multimodal models in our experiments. Beyond providing basic binary classification outcomes, we delve deeper into model behaviour using multiple explainable Artificial Intelligence (XAI) tools, offering insights into their decision-making processes. Our analysis reveals that ResNet18 performs the best according to in-domain and out-of-domain tests. By providing a comprehensive comparison of systematic evaluation results and their interpretability, we propose several directions to inspire future research to develop more robust and effective detection methods for MGM. We provide our codes and some samples on Github repository.

Qi Zheng, Shuliang Liu, Yu Huang et al.

Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in Large Vision-Language Models (LVLMs). However, vision-agnostic watermarks introduce visually irrelevant tokens and disrupt visual grounding by enforcing indiscriminate pseudo-random biases, while some semantic-aware methods incur prohibitive inference latency due to rejection sampling. In this paper, we propose the VIsual Semantic Adaptive Watermark (VISA-Mark), a novel framework that embeds detectable signals while strictly preserving visual fidelity. Our approach employs a lightweight, efficiently trained prefix-tuner to extract dynamic Visual-Evidence Weights, which quantify the evidentiary support for candidate tokens based on the visual input. These weights guide an adaptive vocabulary partitioning and logits perturbation mechanism, concentrating watermark strength specifically on visually-supported tokens. By actively aligning the watermark with visual evidence, VISA-Mark effectively maintains visual fidelity. Empirical results confirm that VISA-Mark outperforms conventional methods with a 7.8% improvement in visual consistency (Chair-I) and superior semantic fidelity. The framework maintains highly competitive detection accuracy (96.88% AUC) and robust attack resilience (99.3%) without sacrificing inference efficiency, effectively establishing a new standard for reliability-preserving multimodal watermarking.

Linghao Zhang, Jungang Li, Yonghua Hei et al.

Multimodal large language models (MLLMs) are typically trained in multiple stages, with video-based supervised fine-tuning (Video-SFT) serving as a key step for improving visual understanding. Yet its effect on the fine-grained evolution of visual capabilities, particularly the balance between spatial and temporal understanding, remains poorly understood. In this paper, we systematically study how Video-SFT reshapes visual capabilities in MLLMs. Across architectures, parameter scales, and frame sampling settings, we observe a consistent pattern: Video-SFT reliably improves video performance, but often yields limited gains or even degradation on static image benchmarks. We further show that this trade-off is closely tied to temporal budget: increasing the number of sampled frames generally improves video performance, but does not reliably improve static image performance. Motivated by this finding, we study an instruction-aware Hybrid-Frame strategy that adaptively allocates frame counts and partially mitigates the image-video trade-off. Our results indicate that Video-SFT is not a free lunch for MLLMs, and preserving spatial understanding remains a central challenge in joint image-video training.

Shuhang Xun, Sicheng Tao, Jungang Li et al.

Multimodal Large Language Models (MLLMs) increasingly excel at perception, understanding, and reasoning. However, current benchmarks inadequately evaluate their ability to perform these tasks continuously in dynamic, real-world environments. To bridge this gap, we introduce RTV-Bench, a fine-grained benchmark for MLLM real-time video analysis. RTV-Bench uses three key principles: (1) Multi-Timestamp Question Answering (MTQA), where answers evolve with scene changes; (2) Hierarchical Question Structure, combining basic and advanced queries; and (3) Multi-dimensional Evaluation, assessing the ability of continuous perception, understanding, and reasoning. RTV-Bench contains 552 diverse videos (167.2 hours) and 4,631 high-quality QA pairs. We evaluated leading MLLMs, including proprietary (GPT-4o, Gemini 2.0), open-source offline (Qwen2.5-VL, VideoLLaMA3), and open-source real-time (VITA-1.5, InternLM-XComposer2.5-OmniLive) models. Experiment results show open-source real-time models largely outperform offline ones but still trail top proprietary models. Our analysis also reveals that larger model size or higher frame sampling rates do not significantly boost RTV-Bench performance, sometimes causing slight decreases. This underscores the need for better model architectures optimized for video stream processing and long sequences to advance real-time video analysis with MLLMs. Our benchmark toolkit is available at: https://github.com/LJungang/RTV-Bench.

Junhao Chen, Yu Huang, Siyuan Li et al.

Multi-Turn Long-Form Question Answering (MT-LFQA) is a key application paradigm of Large Language Models (LLMs) in knowledge-intensive domains. However, existing benchmarks are limited to single-turn dialogue, while multi-turn dialogue benchmarks typically assess other orthogonal capabilities rather than knowledge-intensive factuality. To bridge this critical gap, we introduce \textbf{KnowMT-Bench}, the \textit{first-ever} benchmark designed to systematically evaluate MT-LFQA for LLMs across knowledge-intensive fields, including medicine, finance, and law. To faithfully assess the model's real-world performance, KnowMT-Bench employs a dynamic evaluation setting where models generate their own multi-turn dialogue histories given logically progressive question sequences. The factual capability and information delivery efficiency of the \textit{final-turn} answer are then evaluated using a human-validated automated pipeline. Our experiments reveal that multi-turn contexts degrade performance: factual capability declines due to the contextual noise from self-generated histories, while information efficiency drops as models become more verbose with increasing dialogue length. We then investigate mitigation strategies, demonstrating that retrieval-augmented generation (RAG) can effectively alleviate and even reverse this factual degradation. These findings underscore the importance of our benchmark in evaluating and enhancing the conversational factual capabilities of LLMs in real-world knowledge-intensive applications. Code is available at \href{https://github.com/hardenyu21/KnowMT-Bench}{\textcolor{cyan}{\texttt{KnowMT-Bench}}}.

Leyi Pan, Sheng Guan, Zheyu Fu et al. · tsinghua

We introduce MarkDiffusion, an open-source Python toolkit for generative watermarking of latent diffusion models. It comprises three key components: a unified implementation framework for streamlined watermarking algorithm integrations and user-friendly interfaces; a mechanism visualization suite that intuitively showcases added and extracted watermark patterns to aid public understanding; and a comprehensive evaluation module offering standard implementations of 24 tools across three essential aspects - detectability, robustness, and output quality - plus 8 automated evaluation pipelines. Through MarkDiffusion, we seek to assist researchers, enhance public awareness and engagement in generative watermarking, and promote consensus while advancing research and applications.

Sicheng Tao, Jungang Li, Yibo Yan et al.

Video reasoning has emerged as a critical capability for multimodal large language models (MLLMs), requiring models to move beyond static perception toward coherent understanding of temporal dynamics in complex scenes. Yet existing MLLMs often exhibit process inconsistency, where intermediate reasoning drifts from video dynamics even when the final answer is correct, undermining interpretability and robustness. To address this issue, we introduce MOSS-ChatV, a reinforcement learning framework with a Dynamic Time Warping (DTW)-based process reward. This rule-based reward aligns reasoning traces with temporally grounded references, enabling efficient process supervision without auxiliary reward models. We further identify dynamic state prediction as a key measure of video reasoning and construct MOSS-Video, a benchmark with annotated reasoning traces, where the training split is used to fine-tune MOSS-ChatV and the held-out split is reserved for evaluation. MOSS-ChatV achieves 87.2\% on MOSS-Video (test) and improves performance on general video benchmarks such as MVBench and MMVU. The framework consistently yields gains across different architectures, including Qwen2.5-VL and Phi-2, confirming its broad applicability. Evaluations with GPT-4o-as-judge further show that MOSS-ChatV produces more consistent and stable reasoning traces.

Sirui Huang, Hanqian Li, Yanggan Gu et al.

Given that substantial amounts of domain-specific knowledge are stored in structured formats, such as web data organized through HTML, Large Language Models (LLMs) are expected to fully comprehend this structured information to broaden their applications in various real-world downstream tasks. Current approaches for applying LLMs to structured data fall into two main categories: serialization-based and operation-based methods. Both approaches, whether relying on serialization or using SQL-like operations as an intermediary, encounter difficulties in fully capturing structural relationships and effectively handling sparse data. To address these unique characteristics of structured data, we propose HyperG, a hypergraph-based generation framework aimed at enhancing LLMs' ability to process structured knowledge. Specifically, HyperG first augment sparse data with contextual information, leveraging the generative power of LLMs, and incorporate a prompt-attentive hypergraph learning (PHL) network to encode both the augmented information and the intricate structural relationships within the data. To validate the effectiveness and generalization of HyperG, we conduct extensive experiments across two different downstream tasks requiring structured knowledge.

Yu Huang, Junhao Chen, Shuliang Liu et al. · tsinghua

The rapid development of Artificial Intelligence Generated Content (AIGC) has led to significant progress in video generation, but also raises serious concerns about intellectual property protection and reliable content tracing. Watermarking is a widely adopted solution to this issue, yet existing methods for video generation mainly follow a post-generation paradigm, which often fails to effectively balance the trade-off between video quality and watermark extraction. Meanwhile, current in-generation methods that embed the watermark into the initial Gaussian noise usually incur substantial additional computation. To address these issues, we propose \textbf{Video Signature} (\textsc{VidSig}), an implicit watermarking method for video diffusion models that enables imperceptible and adaptive watermark integration during video generation with almost no extra latency. Specifically, we partially fine-tune the latent decoder, where \textbf{Perturbation-Aware Suppression} (PAS) pre-identifies and freezes perceptually sensitive layers to preserve visual quality. Beyond spatial fidelity, we further enhance temporal consistency by introducing a lightweight \textbf{Temporal Alignment} module that guides the decoder to generate coherent frame sequences during fine-tuning. Experimental results show that \textsc{VidSig} achieves the best trade-off among watermark extraction accuracy, video quality, and watermark latency. It also demonstrates strong robustness against both spatial and temporal tamper, and remains stable across different video lengths and resolutions, highlighting its practicality in real-world scenarios.