Zhengjian Kang

Zhengjian Kang, Jun Zhuang, Kangtong Mo et al.

Detection Transformer (DETR) has redefined object detection by casting it as a set prediction task within an end-to-end framework. Despite its elegance, DETR and its variants still rely on fixed learnable queries and suffer from severe query utilization imbalance, which limits adaptability and leaves the model capacity underused. We propose PaQ-DETR (Pattern and Quality-Aware DETR), a unified framework that enhances both query adaptivity and supervision balance. It learns a compact set of shared latent patterns capturing global semantics and dynamically generates image-specific queries through content-conditioned weighting. In parallel, a quality-aware one-to-many assignment strategy adaptively selects positive samples based on localizatio-classification consistency, enriching supervision and promoting balanced query optimization. Experiments on COCO, CityScapes, and other benchmarks show consistent gains of 1.5%-4.2% mAP across DETR backbones, including ResNet and Swin-Transformer. Beyond accuracy improvement, our method provides interpretable insights into how dynamic patterns cluster semantically across object categories.

Zhengjian Kang, Qi Chen, Rui Liu et al.

Recent Video Large Language Models (Video-LLMs) have shown strong multimodal reasoning capabilities, yet remain challenged by video understanding tasks that require consistent temporal ordering and causal coherence. Many parameter-efficient Video-LLMs rely on unconstrained bidirectional projectors to model inter-frame interactions, which can blur temporal ordering by allowing later frames to influence earlier representations, without explicit architectural mechanisms to respect the directional nature of video reasoning. To address this limitation, we propose V-CORE, a parameter-efficient framework that introduces explicit temporal ordering constraints for video understanding. V-CORE consists of two key components: (1) Learnable Spatial Aggregation (LSA), which adaptively selects salient spatial tokens to reduce redundancy, and (2) a Causality-Aware Temporal Projector (CATP), which enforces structured unidirectional information flow via block-causal attention and a terminal dynamic summary token acting as a causal sink. This design preserves intra-frame spatial interactions while ensuring that temporal information is aggregated in a strictly ordered manner. With 4-bit QLoRA and a frozen LLM backbone, V-CORE can be trained efficiently on a single consumer GPU. Experiments show that V-CORE achieves strong performance on the challenging NExT-QA benchmark, reaching 61.2% accuracy, and remains competitive across MSVD-QA, MSRVTT-QA, and TGIF-QA, with gains concentrated in temporal and causal reasoning subcategories (+3.5% and +5.2% respectively), directly validating the importance of explicit temporal ordering constraints.

Ye Zhang, Qi Chen, Wenyou Huang et al.

Detection Transformer (DETR) offers an end-to-end solution for object detection by eliminating hand-crafted components like non-maximum suppression. However, DETR suffers from inefficient query competition where multiple queries converge to similar positions, leading to redundant computations. We present Route-DETR, which addresses these issues through adaptive pairwise routing in decoder self-attention layers. Our key insight is distinguishing between competing queries (targeting the same object) versus complementary queries (targeting different objects) using inter-query similarity, confidence scores, and geometry. We introduce dual routing mechanisms: suppressor routes that modulate attention between competing queries to reduce duplication, and delegator routes that encourage exploration of different regions. These are implemented via learnable low-rank attention biases enabling asymmetric query interactions. A dual-branch training strategy incorporates routing biases only during training while preserving standard attention for inference, ensuring no additional computational cost. Experiments on COCO and Cityscapes demonstrate consistent improvements across multiple DETR baselines, achieving +1.7% mAP gain over DINO on ResNet-50 and reaching 57.6% mAP on Swin-L, surpassing prior state-of-the-art models.

Zhengjian Kang, Ye Zhang, Xiaoyu Deng et al.

This paper presents LP-DETR (Layer-wise Progressive DETR), a novel approach that enhances DETR-based object detection through multi-scale relation modeling. Our method introduces learnable spatial relationships between object queries through a relation-aware self-attention mechanism, which adaptively learns to balance different scales of relations (local, medium and global) across decoder layers. This progressive design enables the model to effectively capture evolving spatial dependencies throughout the detection pipeline. Extensive experiments on COCO 2017 dataset demonstrate that our method improves both convergence speed and detection accuracy compared to standard self-attention module. The proposed method achieves competitive results, reaching 52.3\% AP with 12 epochs and 52.5\% AP with 24 epochs using ResNet-50 backbone, and further improving to 58.0\% AP with Swin-L backbone. Furthermore, our analysis reveals an interesting pattern: the model naturally learns to prioritize local spatial relations in early decoder layers while gradually shifting attention to broader contexts in deeper layers, providing valuable insights for future research in object detection.

Jun Zhuang, Haibo Jin, Ye Zhang et al.

Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work has applied intent detection to enhance LLMs' moderation guardrails, showing a significant success against content-level jailbreaks, the robustness of these intent-aware guardrails under malicious manipulations remains under-explored. In this work, we investigate the vulnerability of intent-aware guardrails and demonstrate that LLMs exhibit implicit intent detection capabilities. We propose a two-stage intent-based prompt-refinement framework, IntentPrompt, that first transforms harmful inquiries into structured outlines and further reframes them into declarative-style narratives by iteratively optimizing prompts via feedback loops to enhance jailbreak success for red-teaming purposes. Extensive experiments across four public benchmarks and various black-box LLMs indicate that our framework consistently outperforms several cutting-edge jailbreak methods and evades even advanced Intent Analysis (IA) and Chain-of-Thought (CoT)-based defenses. Specifically, our "FSTR+SPIN" variant achieves attack success rates ranging from 88.25% to 96.54% against CoT-based defenses on the o1 model, and from 86.75% to 97.12% on the GPT-4o model under IA-based defenses. These findings highlight a critical weakness in LLMs' safety mechanisms and suggest that intent manipulation poses a growing challenge to content moderation guardrails.

Xiaoyu Deng, Ye Zhang, Tianmin Guo et al.

The astonishing performance of large language models (LLMs) and their remarkable achievements in production and daily life have led to their widespread application in collaborative tasks. However, current large models face challenges such as hallucination and lack of specificity in content generation in vertical domain tasks. Inspired by the contrast and classification mechanisms in human cognitive processes, this paper constructs an adversarial learning-based prompt framework named ChallengeMe, which includes three cascaded solutions: generation prompts, evaluation prompts, and feedback optimization. In this process, we designed seven core optimization dimensions and set the threshold for adversarial learning. The results of mixed case studies on the text summarization task show that the proposed framework can generate more accurate and fluent text summaries compared to the current advanced mainstream LLMs.

Xiaoyu Deng, Zhengjian Kang, Xintao Li et al.

Graphic visual content helps in promoting information communication and inspiration divergence. However, the interpretation of visual content currently relies mainly on humans' personal knowledge background, thereby affecting the quality and efficiency of information acquisition and understanding. To improve the quality and efficiency of visual information transmission and avoid the limitation of the observer due to the information cocoon, we propose CoVis, a collaborative framework for fine-grained visual understanding. By designing and implementing a cascaded dual-layer segmentation network coupled with a large-language-model (LLM) based content generator, the framework extracts as much knowledge as possible from an image. Then, it generates visual analytics for images, assisting observers in comprehending imagery from a more holistic perspective. Quantitative experiments and qualitative experiments based on 32 human participants indicate that the CoVis has better performance than current methods in feature extraction and can generate more comprehensive and detailed visual descriptions than current general-purpose large models.