arXiv subjects

Jisheng Dang

Publications and source records attributed to Jisheng Dang.

29 records · Page 2Linked to original sources

arXiv2026

SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning

Fine-grained video captioning aims to generate detailed, temporally coherent descriptions of video content. However, existing methods struggle to capture subtle video dynamics and rich detailed information. In this paper, we leverage preference learning to enhance the performance of vision-language models in fine-grained video captioning, while mitigating several limitations inherent to direct preference optimization (DPO). First, we propose a pipeline for constructing preference pairs that leverages the intrinsic properties of VLMs along with partial assistance from large language models, achieving an optimal balance between cost and data quality. Second, we propose Synergistic Preference Optimization (SynPO), a novel optimization method offering significant advantages over DPO and its variants. SynPO prevents negative preferences from dominating the optimization, explicitly preserves the model's language capability to avoid deviation of the optimization objective, and improves training efficiency by eliminating the need for the reference model. We extensively evaluate SynPO not only on video captioning benchmarks (e.g., VDC, VDD, VATEX) but also across well-established NLP tasks, including general language understanding and preference evaluation, using diverse pretrained models. Results demonstrate that SynPO consistently outperforms DPO variants while achieving 20\% improvement in training efficiency. Code is available at https://github.com/longmalongma/SynPO

cs.AI↗

arXiv2026

Scale-Aware UAV-to-Satellite Cross-View Geo-Localization: A Semantic Geometric Approach

Cross-View Geo-Localization (CVGL) between UAV imagery and satellite images plays a crucial role in target localization and UAV self-positioning. However, most existing methods rely on the idealized assumption of scale consistency between UAV queries and satellite galleries, overlooking the severe scale ambiguity commonly encountered in real-world scenarios. This discrepancy leads to field-of-view misalignment and feature mismatch, significantly degrading CVGL robustness. To address this issue, we propose a geometric framework that recovers the absolute metric scale from monocular UAV images using semantic anchors. Specifically, small vehicles (SVs), characterized by relatively stable prior size distributions and high detectability, are exploited as metric references. A Decoupled Stereoscopic Projection Model is introduced to estimate the absolute image scale from these semantic targets. By decomposing vehicle dimensions into radial and tangential components, the model compensates for perspective distortions in 2D detections of 3D vehicles, enabling more accurate scale estimation. To further reduce intra-class size variation and detection noise, a dual-dimension fusion strategy with Interquartile Range (IQR)-based robust aggregation is employed. The estimated global scale is then used as a physical constraint for scale-adaptive satellite image cropping, improving UAV-to-satellite feature alignment. Experiments on augmented DenseUAV and UAV-VisLoc datasets demonstrate that the proposed method significantly improves CVGL robustness under unknown UAV image scales. Additionally, the framework shows strong potential for downstream applications such as passive UAV altitude estimation and 3D model scale recovery.

cs.CV↗

arXiv2025

IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector

Large Language Models (LLMs) have attained human-level fluency in text generation, which complicates the distinguishing between human-written and LLM-generated texts. This increases the risk of misuse and highlights the need for reliable detectors. Yet, existing detectors exhibit poor robustness on out-of-distribution (OOD) data and attacked data, which is critical for real-world scenarios. Also, they struggle to provide interpretable evidence to support their decisions, thus undermining the reliability. In light of these challenges, we propose IPAD (Inverse Prompt for AI Detection), a novel framework consisting of a Prompt Inverter that identifies predicted prompts that could have generated the input text, and two Distinguishers that examine the probability that the input texts align with the predicted prompts. Empirical evaluations demonstrate that IPAD outperforms the strongest baselines by 9.05% (Average Recall) on in-distribution data, 12.93% (AUROC) on out-of-distribution data, and 5.48% (AUROC) on attacked data. IPAD also performs robustly on structured datasets. Furthermore, an interpretability assessment is conducted to illustrate that IPAD enhances the AI detection trustworthiness by allowing users to directly examine the decision-making evidence, which provides interpretable support for its state-of-the-art detection results.

cs.LG↗

arXiv2025

A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing

Event cameras are bio-inspired vision sensor that encode visual information with high dynamic range, high temporal resolution, and low latency.Current state-of-the-art event stream processing methods rely on end-to-end deep learning techniques. However, these models are heavily dependent on data structures, limiting their stability and generalization capabilities across tasks, thereby hindering their deployment in real-world scenarios. To address this issue, we propose a chaotic dynamics event signal processing framework inspired by the dorsal visual pathway of the brain. Specifically, we utilize Continuous-coupled Neural Network (CCNN) to encode the event stream. CCNN encodes polarity-invariant event sequences as periodic signals and polarity=changing event sequences as chaotic signals. We then use continuous wavelet transforms to analyze the dynamical states of CCNN neurons and establish the high-order mappings of the event stream. The effectiveness of our method is validated through integration with conventional classification networks, achieving state-of-the-art classification accuracy on the N-Caltech101 and N-CARS datasets, with results of 84.3% and 99.9%, respectively. Our method improves the accuracy of event camera-based object classification while significantly enhancing the generalization and stability of event representation. Our code is available in https://github.com/chenyu0193/ACDF.

q-bio.NC↗

arXiv2025

FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning

Group relative policy optimization (GRPO) has demonstrated significant potential in improving the reasoning capabilities of large language models (LLMs) via reinforcement learning. However, its practical deployment is impeded by an excessively slow training process, primarily attributed to the computationally intensive autoregressive generation of multiple responses per query, which makes the generation phase the primary performance bottleneck. Although speculative decoding presents a promising direction for acceleration, its direct application in GRPO achieves limited speedup under high-concurrency training conditions. To overcome this limitation, we propose a concurrency-aware speculative decoding framework that dynamically adjusts the drafting and verification strategy according to real-time concurrency levels, thereby maximizing the acceleration of the generation process. Furthermore, to address performance degradation arising from distributional drift between the evolving target model and the fixed draft model during training, we introduce an online draft learning mechanism that enables the draft model to continuously adapt using feedback signals from the target model. Experimental results across multiple mathematical reasoning datasets and models demonstrate that the proposed method achieves end-to-end speedups of 2.35x to 2.72x, significantly surpassing baseline approaches in efficiency. The code is available at https://github.com/yedaotian9/GRPO_speculative.

cs.LG↗

arXiv2025

SafeSteer: Adaptive Subspace Steering for Efficient Jailbreak Defense in Vision-Language Models

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the model's utility; and (2) many defense mechanisms significantly reduce the model's inference efficiency. To address these challenges, we propose SafeSteer, a lightweight, inference-time steering framework that effectively defends against diverse jailbreak attacks without modifying model weights. At the core of SafeSteer is the innovative use of Singular Value Decomposition to construct a low-dimensional "safety subspace." By projecting and reconstructing the raw steering vector into this subspace during inference, SafeSteer adaptively removes harmful generation signals while preserving the model's ability to handle benign inputs. The entire process is executed in a single inference pass, introducing negligible overhead. Extensive experiments show that SafeSteer reduces the attack success rate by over 60% and improves accuracy on normal tasks by 1-2%, without introducing significant inference latency. These results demonstrate that robust and practical jailbreak defense can be achieved through simple, efficient inference-time control.

cs.CR↗

arXiv2025

Boosting Temporal Sentence Grounding via Causal Inference

Temporal Sentence Grounding (TSG) aims to identify relevant moments in an untrimmed video that semantically correspond to a given textual query. Despite existing studies having made substantial progress, they often overlook the issue of spurious correlations between video and textual queries. These spurious correlations arise from two primary factors: (1) inherent biases in the textual data, such as frequent co-occurrences of specific verbs or phrases, and (2) the model's tendency to overfit to salient or repetitive patterns in video content. Such biases mislead the model into associating textual cues with incorrect visual moments, resulting in unreliable predictions and poor generalization to out-of-distribution examples. To overcome these limitations, we propose a novel TSG framework, causal intervention and counterfactual reasoning that utilizes causal inference to eliminate spurious correlations and enhance the model's robustness. Specifically, we first formulate the TSG task from a causal perspective with a structural causal model. Then, to address unobserved confounders reflecting textual biases toward specific verbs or phrases, a textual causal intervention is proposed, utilizing do-calculus to estimate the causal effects. Furthermore, visual counterfactual reasoning is performed by constructing a counterfactual scenario that focuses solely on video features, excluding the query and fused multi-modal features. This allows us to debias the model by isolating and removing the influence of the video from the overall effect. Experiments on public datasets demonstrate the superiority of the proposed method. The code is available at https://github.com/Tangkfan/CICR.

cs.CV↗

arXiv2025

MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering

Grounded Video Question Answering (Grounded VideoQA) requires aligning textual answers with explicit visual evidence. However, modern multimodal models often rely on linguistic priors and spurious correlations, resulting in poorly grounded predictions. In this work, we propose MUPA, a cooperative MUlti-Path Agentic approach that unifies video grounding, question answering, answer reflection and aggregation to tackle Grounded VideoQA. MUPA features three distinct reasoning paths on the interplay of grounding and QA agents in different chronological orders, along with a dedicated reflection agent to judge and aggregate the multi-path results to accomplish consistent QA and grounding. This design markedly improves grounding fidelity without sacrificing answer accuracy. Despite using only 2B parameters, our method outperforms all 7B-scale competitors. When scaled to 7B parameters, MUPA establishes new state-of-the-art results, with Acc@GQA of 30.3% and 47.4% on NExT-GQA and DeVE-QA respectively, demonstrating MUPA' effectiveness towards trustworthy video-language understanding. Our code is available in https://github.com/longmalongma/MUPA.

cs.CV↗

arXiv2025

Reinforcing Video Reasoning with Focused Thinking

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations persist: 1) they often produce unfocused, verbose reasoning chains that obscure salient spatiotemporal cues and 2) binary rewarding fails to account for partially correct answers, resulting in high reward variance and inefficient learning. In this paper, we propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity. Specifically, we employs a token weighting mechanism that prioritizes tokens with high informational density (estimated by intra-group information entropy), suppressing redundant tokens like generic reasoning prefixes. Furthermore, we reformulate RL training by shifting from single-choice to multi-choice QA tasks, where soft rewards enable finer-grained gradient estimation by distinguishing partial correctness. Additionally, we propose question-answer inversion, a data augmentation strategy to generate diverse multi-choice samples from existing benchmarks. Experiments demonstrate state-of-the-art performance on several video reasoning and general understanding benchmarks. Notably, TW-GRPO achieves 50.4\% accuracy on CLEVRER (18.8\% improvement over Video-R1) and 65.8\% on MMVU. Our codes are available at \href{https://github.com/longmalongma/TW-GRPO}.

cs.CV↗

arXiv2025

Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model

Recent advances in conditional diffusion models have shown promise for generating realistic TalkingFace videos, yet challenges persist in achieving consistent head movement, synchronized facial expressions, and accurate lip synchronization over extended generations. To address these, we introduce the \textbf{M}otion-priors \textbf{C}onditional \textbf{D}iffusion \textbf{M}odel (\textbf{MCDM}), which utilizes both archived and current clip motion priors to enhance motion prediction and ensure temporal consistency. The model consists of three key elements: (1) an archived-clip motion-prior that incorporates historical frames and a reference frame to preserve identity and context; (2) a present-clip motion-prior diffusion model that captures multimodal causality for accurate predictions of head movements, lip sync, and expressions; and (3) a memory-efficient temporal attention mechanism that mitigates error accumulation by dynamically storing and updating motion features. We also release the \textbf{TalkingFace-Wild} dataset, a multilingual collection of over 200 hours of footage across 10 languages. Experimental results demonstrate the effectiveness of MCDM in maintaining identity and motion continuity for long-term TalkingFace generation. Code, models, and datasets will be publicly available.

cs.CV↗

arXiv2024

Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales

The remarkable performance of Multimodal Large Language Models (MLLMs) has unequivocally demonstrated their proficient understanding capabilities in handling a wide array of visual tasks. Nevertheless, the opaque nature of their black-box reasoning processes persists as an enigma, rendering them uninterpretable and struggling with hallucination. Their ability to execute intricate compositional reasoning tasks is also constrained, culminating in a stagnation of learning progression for these models. In this work, we introduce Fact, a novel paradigm designed to generate multimodal rationales that are faithful, concise, and transferable for teaching MLLMs. This paradigm utilizes verifiable visual programming to generate executable code guaranteeing faithfulness and precision. Subsequently, through a series of operations including pruning, merging, and bridging, the rationale enhances its conciseness. Furthermore, we filter rationales that can be transferred to end-to-end paradigms from programming paradigms to guarantee transferability. Empirical evidence from experiments demonstrates the superiority of our method across models of varying parameter sizes, significantly enhancing their compositional reasoning and generalization ability. Our approach also reduces hallucinations owing to its high correlation between images and text.

cs.CV↗