arXiv subjects

Hongjie Zhang

Publications and source records attributed to Hongjie Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations

Video temporal grounding (VTG) aims to locate precise segments in videos based on language queries, which is a fundamental challenge in video understanding. While recent Multimodal Large Language Models (MLLMs) have shown promise in tackling VTG through reinforcement learning (RL), they overlook the challenges arising from both the quality and difficulty of training samples. (1) Partially annotated samples. Many samples contain relevant segments beyond the annotated interval, introducing ambiguous supervision. (2) Hard-to-ground samples. Samples with poor zero-shot performance produce consistently low and indistinguishable rewards during RL training, exhibiting no clear preference among multiple outputs and thus hindering learning efficiency. To address these challenges, we propose VideoTG-R1, a novel curriculum RL framework with reflected boundary annotations, enabling data-efficient training. Specifically, we propose a Boundary Reflection Agent that utilizes MLLMs to predict query-relevant timestamps outside the annotated intervals, allowing us to identify and filter out partially annotated samples, thereby reducing ambiguity. Furthermore, we introduce a Difficulty Estimation Agent to assess the training difficulty of each sample and design a curriculum RL strategy that dynamically masks the videos of hard-to-ground samples according to the training steps, easing the training difficulty and providing clearer preference. Experiments on the VTG and grounded VideoQA tasks demonstrate the effectiveness of our method. Remarkably, with only 10% of the training samples and 21% of the computational budget, VideoTG-R1 outperforms full-data counterparts under both group relative policy optimization (GRPO) and supervised fine-tuning (SFT). The code is available at https://github.com/ldong1111/VideoTG-R1.

cs.CV↗

arXiv2025

Rotation, Scale, and Translation Resilient Black-box Fingerprinting for Intellectual Property Protection of EaaS Models

Feature embedding has become a cornerstone technology for processing high-dimensional and complex data, which results in that Embedding as a Service (EaaS) models have been widely deployed in the cloud. To protect the intellectual property of EaaS models, existing methods apply digital watermarking to inject specific backdoor triggers into EaaS models by modifying training samples or network parameters. However, these methods inevitably produce detectable patterns through semantic analysis and exhibit susceptibility to geometric transformations including rotation, scaling, and translation (RST). To address this problem, we propose a fingerprinting framework for EaaS models, rather than merely refining existing watermarking techniques. Different from watermarking techniques, the proposed method establishes EaaS model ownership through geometric analysis of embedding space's topological structure, rather than relying on the modified training samples or triggers. The key innovation lies in modeling the victim and suspicious embeddings as point clouds, allowing us to perform robust spatial alignment and similarity measurement, which inherently resists RST attacks. Experimental results evaluated on visual and textual embedding tasks verify the superiority and applicability. This research reveals inherent characteristics of EaaS models and provides a promising solution for ownership verification of EaaS models under the black-box scenario.

cs.CR↗

arXiv2025

Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings

We study the task of panoptic symbol spotting, which involves identifying both individual instances of countable things and the semantic regions of uncountable stuff in computer-aided design (CAD) drawings composed of vector graphical primitives. Existing methods typically rely on image rasterization, graph construction, or point-based representation, but these approaches often suffer from high computational costs, limited generality, and loss of geometric structural information. In this paper, we propose VecFormer, a novel method that addresses these challenges through line-based representation of primitives. This design preserves the geometric continuity of the original primitive, enabling more accurate shape representation while maintaining a computation-friendly structure, making it well-suited for vector graphic understanding tasks. To further enhance prediction reliability, we introduce a Branch Fusion Refinement module that effectively integrates instance and semantic predictions, resolving their inconsistencies for more coherent panoptic outputs. Extensive experiments demonstrate that our method establishes a new state-of-the-art, achieving 91.1 PQ, with Stuff-PQ improved by 9.6 and 21.2 points over the second-best results under settings with and without prior information, respectively, highlighting the strong potential of line-based representation as a foundation for vector graphic understanding.

cs.CV↗

arXiv2025

MTOS: A LLM-Driven Multi-topic Opinion Simulation Framework for Exploring Echo Chamber Dynamics

The polarization of opinions, information segregation, and cognitive biases on social media have attracted significant academic attention. In real-world networks, information often spans multiple interrelated topics, posing challenges for opinion evolution and highlighting the need for frameworks that simulate interactions among topics. Existing studies based on large language models (LLMs) focus largely on single topics, limiting the capture of cognitive transfer in multi-topic, cross-domain contexts. Traditional numerical models, meanwhile, simplify complex linguistic attitudes into discrete values, lacking interpretability, behavioral consistency, and the ability to integrate multiple topics. To address these issues, we propose Multi-topic Opinion Simulation (MTOS), a social simulation framework integrating multi-topic contexts with LLMs. MTOS leverages LLMs alongside short-term and long-term memory, incorporates multiple user-selection interaction mechanisms and dynamic topic-selection strategies, and employs a belief decay mechanism to enable perspective updates across topics. We conduct extensive experiments on MTOS, varying topic numbers, correlation types, and performing ablation studies to assess features such as group polarization and local consistency. Results show that multi-topic settings significantly alter polarization trends: positively correlated topics amplify echo chambers, negatively correlated topics inhibit them, and irrelevant topics also mitigate echo chamber effects through resource competition. Compared with numerical models, LLM-based agents realistically simulate dynamic opinion changes, reproduce linguistic features of news texts, and capture complex human reasoning, improving simulation interpretability and system stability.

cs.AI↗

arXiv2025

Theoretical investigation of real-fluid effects on the oxidation of hydrogen and syngas in high-pressure flow reactors

Investigating the high-pressure pyrolysis and oxidation of hydrogen and syngas is essential for developing accurate combustion models under real engine conditions. Accordingly, flow reactors have been increasingly used in these fundamental combustion research at high-pressure conditions to achieve chemical kinetic modeling. However, these previous chemical kinetic modeling for pyrolysis and oxidation has almost been completely conducted based on ideal gas assumption, which might fail at high-pressure conditions when real-fluid behaviors become pronounced. Elucidating whether this is the case is urgent given the high demand for high-pressure combustion and propulsion technologies. Toward this, this study establishes a first-of-its-kind real-fluid modelling framework for high-pressure flow reactors, where the physical molecular interactions in real fluids are represented via coupling ab initio intermolecular potentials with high-order Virial equation of state and further with real-fluid thermochemistry, real-fluid chemical equilibrium, and real-fluid conservation laws of species, mass, and momentum. Using the developed framework, real-fluid effects in high-pressure flow reactors are quantified through case studies of hydrogen and syngas oxidation, covering pressure of 10-500 bar, temperature of 601-946 K, equivalence ratio of 0.0009-12.07, and dilution ratio of 5.9%-99.5%. The results reveal the strong real-fluid effects in high-pressure flow reactors, where ignoring them can lead to considerable errors in the simulated mole fractions, which are higher than typical levels of measurements uncertainty in flow reactors. These errors can lead to misinterpretation of the fundamental oxidation chemistry in high-pressure flow reactors and pose significant errors in the developed chemistry models, which should be adequately accounted for in future high-pressure flow reactor studies.

physics.chem-ph↗

arXiv2025

HiPrFlame-An ab initio based real-fluid modeling approach for high-pressure combustion-I. Rationale, methodology, and application to laminar premixed flames

High-pressure combustion is central to modern propulsion and power-generation systems, where operating pressures often exceed the critical point of working fluids, resulting in pronounced real-fluid effects that fundamentally alter thermodynamic and transport properties. High-pressure combustion is central to modern propulsion and power-generation systems, where operating pressures often exceed the critical point of working fluids, resulting in pronounced real-fluid effects that fundamentally alter thermodynamic and transport properties. Existing methods for quantifying real-fluid behaviors typically rely on empirical correlations, fitted potentials, and cubic equations of state, which lack the accuracy required for species coverage and extreme conditions encountered in combustion processes. As such, this study introduces HiPrFlame, a novel ab initio-based modeling framework for high-pressure combustion, designed to deliver unprecedented fidelity in real-fluid property prediction in high-pressure combustion modeling. HiPrFlame integrates third-order Virial EoS derived from ab initio intermolecular potentials, thereby real-fluid departure functions for real-fluid thermodynamics and Enskog theory for real-fluid transport properties, with all implemented within a versatile OpenFOAM architecture that can be used for 0-D to 3-D real-fluid modeling. To accelerate multidimensional simulations, artificial neural network surrogate models are trained on a comprehensive property database, enabling efficient real-fluid property updating. The framework is demonstrated through case studies of high-pressure hydrogen combustion, including homogeneous autoignition and one-dimensional laminar premixed flames. Results demonstrate that HiPrFlame accurately captures experimental data for both thermodynamic and transport properties, significantly outperforming traditional methods.

physics.flu-dyn↗

arXiv2025

PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training

Multi-agent reinforcement learning (MARL) has achieved significant progress in solving complex multi-player games through self-play. However, training effective adversarial policies requires millions of experience samples and substantial computational resources. Moreover, these policies lack interpretability, hindering their practical deployment. Recently, researchers have successfully leveraged Large Language Models (LLMs) to generate programmatic policies for single-agent tasks, transforming neural network-based policies into interpretable rule-based code with high execution efficiency. Inspired by this, we propose PolicyEvolve, a general framework for generating programmatic policies in multi-player games. PolicyEvolve significantly reduces reliance on manually crafted policy code, achieving high-performance policies with minimal environmental interactions. The framework comprises four modules: Global Pool, Local Pool, Policy Planner, and Trajectory Critic. The Global Pool preserves elite policies accumulated during iterative training. The Local Pool stores temporary policies for the current iteration; only sufficiently high-performing policies from this pool are promoted to the Global Pool. The Policy Planner serves as the core policy generation module. It samples the top three policies from the Global Pool, generates an initial policy for the current iteration based on environmental information, and refines this policy using feedback from the Trajectory Critic. Refined policies are then deposited into the Local Pool. This iterative process continues until the policy achieves a sufficiently high average win rate against the Global Pool, at which point it is integrated into the Global Pool. The Trajectory Critic analyzes interaction data from the current policy, identifies vulnerabilities, and proposes directional improvements to guide the Policy Planner

cs.LG↗

arXiv2025

LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering

Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance on limited-length sub-clips as clues to answer those questions. Meanwhile, previous datasets have limited focus on question type and modality. To remedy this, we introduce LvBench, a Long-form video understanding benchmark for versatile multi-modal question-answering. Our LvBench stands out from existing long-form VideoQA datasets through three key characteristics: 1) Extended temporal durations: We consider videos ranging from 70 seconds to 4 hours, covering single-scene, multi-scene, and full-scene contexts. This design accounts for both video and clue lengths, capturing diverse contextual dynamics. 2) Diverse question types and modalities: LvBench introduces six distinct question types that evaluate various perceptual and cognitive capabilities, utilizing both video frames and subtitles. 3) High-quality annotations: We employ rigorous manual labeling by human annotators. Our dataset comprises 20,061 question-answer pairs sourced from 100 carefully selected movies across diverse genres, annotated collaboratively by multiple individuals. Analysis involving various baselines reveals a consistent trend: the performance of all existing methods significantly deteriorates when video and clue length increases. We expect LvBench to serve as a valuable resource for future works on long-form video understanding.

cs.CV↗

arXiv2025

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

We introduce InternVL 3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0\% gain in overall reasoning performance and a 4.05$\times$ inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks -- narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

cs.CV↗

arXiv2025

InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models

Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversity, and instruction expressiveness. In this work, we introduce InternSpatial, the largest open-source dataset for spatial reasoning in VLMs, along with InternSpatial-Bench, a corresponding evaluation benchmark designed to assess spatial understanding under diverse instruction formats. InternSpatial comprises 12 million QA pairs spanning both single-view and multi-view settings, drawn from diverse visual environments and supporting 19 instruction formats that reflect varied query styles. For evaluation, we propose InternSpatial-Bench for single-view tasks and expand multi-view reasoning by introducing a novel rotation angle prediction task that has not been explored in prior work. Experimental results show that models trained on InternSpatial achieve 12.1% improvement on InternSpatial-Bench and 10.7% on VSI-Bench, while maintaining strong performance on general-purpose benchmarks. We hope these resources will support the development of spatially capable VLMs in practical applications such as robotics and embodied AI.

cs.CV↗

arXiv2025

Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining

The task of weakly supervised temporal sentence grounding (WSTSG) aims to detect temporal intervals corresponding to a language description from untrimmed videos with only video-level video-language correspondence. For an anchor sample, most existing approaches generate negative samples either from other videos or within the same video for contrastive learning. However, some training samples are highly similar to the anchor sample, directly regarding them as negative samples leads to difficulties for optimization and ignores the correlations between these similar samples and the anchor sample. To address this, we propose Positive Sample Mining (PSM), a novel framework that mines positive samples from the training set to provide more discriminative supervision. Specifically, for a given anchor sample, we partition the remaining training set into semantically similar and dissimilar subsets based on the similarity of their text queries. To effectively leverage these correlations, we introduce a PSM-guided contrastive loss to ensure that the anchor proposal is closer to similar samples and further from dissimilar ones. Additionally, we design a PSM-guided rank loss to ensure that similar samples are closer to the anchor proposal than to the negative intra-video proposal, aiming to distinguish the anchor proposal and the negative intra-video proposal. Experiments on the WSTSG and grounded VideoQA tasks demonstrate the effectiveness and superiority of our method.

cs.CV↗

arXiv2025

Can LLM be a Good Path Planner based on Prompt Engineering? Mitigating the Hallucination for Path Planning

Spatial reasoning in Large Language Models (LLMs) is the foundation for embodied intelligence. However, even in simple maze environments, LLMs still encounter challenges in long-term path-planning, primarily influenced by their spatial hallucination and context inconsistency hallucination by long-term reasoning. To address this challenge, this study proposes an innovative model, Spatial-to-Relational Transformation and Curriculum Q-Learning (S2RCQL). To address the spatial hallucination of LLMs, we propose the Spatial-to-Relational approach, which transforms spatial prompts into entity relations and paths representing entity relation chains. This approach fully taps the potential of LLMs in terms of sequential thinking. As a result, we design a path-planning algorithm based on Q-learning to mitigate the context inconsistency hallucination, which enhances the reasoning ability of LLMs. Using the Q-value of state-action as auxiliary information for prompts, we correct the hallucinations of LLMs, thereby guiding LLMs to learn the optimal path. Finally, we propose a reverse curriculum learning technique based on LLMs to further mitigate the context inconsistency hallucination. LLMs can rapidly accumulate successful experiences by reducing task difficulty and leveraging them to tackle more complex tasks. We performed comprehensive experiments based on Baidu's self-developed LLM: ERNIE-Bot 4.0. The results showed that our S2RCQL achieved a 23%--40% improvement in both success and optimality rates compared with advanced prompt engineering.

cs.CL↗

arXiv2025

Social Opinions Prediction Utilizes Fusing Dynamics Equation with LLM-based Agents

In the context where social media emerges as a pivotal platform for social movements and shaping public opinion, accurately simulating and predicting the dynamics of user opinions is of significant importance. Such insights are vital for understanding social phenomena, informing policy decisions, and guiding public opinion. Unfortunately, traditional algorithms based on idealized models and disregarding social data often fail to capture the complexity and nuance of real-world social interactions. This study proposes the Fusing Dynamics Equation-Large Language Model (FDE-LLM) algorithm. This innovative approach aligns the actions and evolution of opinions in Large Language Models (LLMs) with the real-world data on social networks. The FDE-LLM devides users into two roles: opinion leaders and followers. Opinion leaders use LLM for role-playing and employ Cellular Automata(CA) to constrain opinion changes. In contrast, opinion followers are integrated into a dynamic system that combines the CA model with the Susceptible-Infectious-Recovered (SIR) model. This innovative design significantly improves the accuracy of the simulation. Our experiments utilized four real-world datasets from Weibo. The result demonstrates that the FDE-LLM significantly outperforms traditional Agent-Based Modeling (ABM) algorithms and LLM-based algorithms. Additionally, our algorithm accurately simulates the decay and recovery of opinions over time, underscoring LLMs potential to revolutionize the understanding of social media dynamics.

cs.SI↗

arXiv2025

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

We introduce InternVL3, a significant advancement in the InternVL series featuring a native multimodal pre-training paradigm. Rather than adapting a text-only large language model (LLM) into a multimodal large language model (MLLM) that supports visual inputs, InternVL3 jointly acquires multimodal and linguistic capabilities from both diverse multimodal data and pure-text corpora during a single pre-training stage. This unified training paradigm effectively addresses the complexities and alignment challenges commonly encountered in conventional post-hoc training pipelines for MLLMs. To further improve performance and scalability, InternVL3 incorporates variable visual position encoding (V2PE) to support extended multimodal contexts, employs advanced post-training techniques such as supervised fine-tuning (SFT) and mixed preference optimization (MPO), and adopts test-time scaling strategies alongside an optimized training infrastructure. Extensive empirical evaluations demonstrate that InternVL3 delivers superior performance across a wide range of multi-modal tasks. In particular, InternVL3-78B achieves a score of 72.2 on the MMMU benchmark, setting a new state-of-the-art among open-source MLLMs. Its capabilities remain highly competitive with leading proprietary models, including ChatGPT-4o, Claude 3.5 Sonnet, and Gemini 2.5 Pro, while also maintaining strong pure-language proficiency. In pursuit of open-science principles, we will publicly release both the training data and model weights to foster further research and development in next-generation MLLMs.

cs.CV↗

arXiv2025

EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World

Being able to map the activities of others into one's own point of view is one fundamental human skill even from a very early age. Taking a step toward understanding this human ability, we introduce EgoExoLearn, a large-scale dataset that emulates the human demonstration following process, in which individuals record egocentric videos as they execute tasks guided by demonstration videos. Focusing on the potential applications in daily assistance and professional support, EgoExoLearn contains egocentric and demonstration video data spanning 120 hours captured in daily life scenarios and specialized laboratories. Along with the videos we record high-quality gaze data and provide detailed multimodal annotations, formulating a playground for modeling the human ability to bridge asynchronous procedural actions from different viewpoints. To this end, we present benchmarks such as cross-view association, cross-view action planning, and cross-view referenced skill assessment, along with detailed analysis. We expect EgoExoLearn can serve as an important resource for bridging the actions across views, thus paving the way for creating AI agents capable of seamlessly learning by observing humans in the real world. Code and data can be found at: https://github.com/OpenGVLab/EgoExoLearn

cs.CV↗

arXiv2024

On the H-atom abstractions from C1-C4 alcohols, aldehydes, and ethers by NO2: ab initio and comprehensive kinetic modeling

As crucial additives and intermediate, alcohols, ethers, and aldehydes play a significant role in the combustion process. However, the chemistry of NOXhydrocarbon interactions and the rate rules governing these interactions remain largely unexplored in this combustion system. To address this gap, this study provides a comprehensive investigation of H-atom abstraction by NO2 from C1-C4 alcohols, aldehydes and ethers that leads to the formation of 3 HNO2 isomers (i.e., transHONO, HNO2, and cisHONO), encompassing 9 hydrocarbons and 45 reactions. Utilizing the DLPNO CCSD(T)cc pVDZ M06 2X 6 311g d,p method, the electronic structures, single point energies, C H bond dissociation energies and 1 D hindered rotor potentials of the reactants, transition states, complexes and products in each reaction are computed. Adding these H atom abstractions to the chemical kinetic model improves the model reactivity and advances the ignition, as indicated by the reduction in ignition delay time for species that initially lacked these reactions. Further sensitivity and flux analyses highlight the crucial role of H atom abstraction by NO2. The findings underscore the importance of accurately incorporating these kinetic parameters into newly developed chemical models for alcohols, aldehydes, and ethers. Additionally, the study highlights the need for future experimental efforts to investigate the effects of NO2 on the combustion systems of these compounds.

physics.chem-ph↗

arXiv2024

InternVideo2: Scaling Foundation Models for Multimodal Video Understanding

We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our core design is a progressive training approach that unifies the masked video modeling, crossmodal contrastive learning, and next token prediction, scaling up the video encoder size to 6B parameters. At the data level, we prioritize spatiotemporal consistency by semantically segmenting videos and generating video-audio-speech captions. This improves the alignment between video and text. Through extensive experiments, we validate our designs and demonstrate superior performance on over 60 video and audio tasks. Notably, our model outperforms others on various video-related dialogue and long video understanding benchmarks, highlighting its ability to reason and comprehend longer contexts. Code and models are available at https://github.com/OpenGVLab/InternVideo/tree/main/InternVideo2/.

cs.CV↗

arXiv2024

The impact of non-equilibrium plasma distributions on solar wind measurements by Vigil's Plasma Analyser

In order to protect society from space weather impacts, we must monitor space weather and obtain early warnings for extreme events if possible. For this purpose, the European Space Agency is currently preparing to launch the Vigil mission towards the end of this decade as a space-weather monitor at the fifth Lagrange point of the Sun--Earth system. Vigil will carry, amongst other instruments, the Plasma Analyzer (PLA) to provide quasi-continuous measurements of solar wind ions. We model the performance of the PLA instrument, considering typical solar wind plasma conditions, to compare the expected observations of PLA with the assumed input conditions of the solar wind. We evaluate the instrument performance under realistic, non-equilibrium plasma conditions, accounting for temperature anisotropies, proton beams, and the contributions from drifting $α$-particles. We examine the accuracy of the instrument's performance over a range of input solar wind moments. We identify sources of potential errors due to non-equilibrium plasma conditions and link these to instrument characteristics such as its angular and energy resolution and its field of view. We demonstrate the limitations of the instrument and potential improvements such as applying ground-based fitting techniques to obtain more accurate measurements of the solar wind even under non-equilibrium plasma conditions. The use of ground processing of plasma moments instead of on-board processing is crucial for the extraction of reliable measurements.

physics.space-ph↗