SYSiqi Yang

Siqi Yang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Siqi Yang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    V-FAT: Benchmarking Visual Fidelity Against Text-bias

    by Ziteng Wang, Yujie He, Guanliang Li, Siqi Yang, Jiaqi Xiong, Songxiang Liu

    Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on standard visual reasoning benchmarks. However, there is growing concern that these models rely excessively on linguistic shortcuts rather than genuine visual grounding, a phenomenon we term Text Bias. In this paper, we investigate the fundamental tension between visual perception and linguistic priors. We decouple the sources of this bias into two dimensions: Internal Corpus Bias, stemming from statistical correlations in pretraining, and External Instruction Bias, arising from the alignment-induced tendency toward sycophancy. To quantify this effect, we introduce V-FAT (Visual Fidelity Against Text-bias), a diagnostic benchmark comprising 4,026 VQA instances across six semantic domains. V-FAT employs a Three-Level Evaluation Framework that systematically increases the conflict between visual evidence and textual information: (L1) internal bias from atypical images, (L2) external bias from misleading instructions, and (L3) synergistic bias where both coincide. We introduce the Visual Robustness Score (VRS), a metric designed to penalize "lucky" linguistic guesses and reward true visual fidelity. Our evaluation of 12 frontier MLLMs reveals that while models excel in existing benchmarks, they experience significant visual collapse under high linguistic dominance.

  • Open Access

    Learning When to Look: A Disentangled Curriculum for Strategic Perception in Multimodal Reasoning

    by Siqi Yang, Zilve Gao, Haibo Qiu, Fanfan Liu, Peng Shi, Zhixiong Zeng, Qingmin Liao, Lin Ma

    Multimodal Large Language Models (MLLMs) demonstrate significant potential but remain brittle in complex, long-chain visual reasoning tasks. A critical failure mode is "visual forgetting", where models progressively lose visual grounding as reasoning extends, a phenomenon aptly described as "think longer, see less". We posit this failure stems from current training paradigms prematurely entangling two distinct cognitive skills: (1) abstract logical reasoning "how-to-think") and (2) strategic visual perception ("when-to-look"). This creates a foundational cold-start deficiency -- weakening abstract reasoning -- and a strategic perception deficit, as models lack a policy for when to perceive. In this paper, we propose a novel curriculum-based framework to disentangle these skills. First, we introduce a disentangled Supervised Fine-Tuning (SFT) curriculum that builds a robust abstract reasoning backbone on text-only data before anchoring it to vision with a novel Perception-Grounded Chain-of-Thought (PG-CoT) paradigm. Second, we resolve the strategic perception deficit by formulating timing as a reinforcement learning problem. We design a Pivotal Perception Reward that teaches the model when to look by coupling perceptual actions to linguistic markers of cognitive uncertainty (e.g., "wait", "verify"), thereby learning an autonomous grounding policy. Our contributions include the formalization of these two deficiencies and the development of a principled, two-stage framework to address them, transforming the model from a heuristic-driven observer to a strategic, grounded reasoner. \textbf{Code}: \url{https://github.com/gaozilve-max/learning-when-to-look}.

  • Open Access

    STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation

    by Xiaoxiao Ma, Haibo Qiu, Guohui Zhang, Zhixiong Zeng, Siqi Yang, Lin Ma, Feng Zhao

    Reinforcement learning has recently been explored to improve text-to-image generation, yet applying existing GRPO algorithms to autoregressive (AR) image models remains challenging. The instability of the training process easily disrupts the pretrained model capability during long runs, resulting in marginal gains, degraded image quality, and poor generalization. In this work, we revisit GRPO for AR image generation and identify two key issues: contradictory gradients from unnecessary tokens and unstable policy entropy dynamics. To address these, we introduce STAGE, a stable and generalizable framework that leverages two targeted solutions: 1) Advantage/KL reweighting. Similarity-aware reweighting to alleviate conflicting updates; and 2) Entropy reward. An entropy-based reward corresponding to reference model to stabilize learning. With the help of alleviating conflicts between tokens and an entropy reward for stabilizing training, we reduce disruption of the pretrained distribution and mitigate reward hacking, which in turn improves generalization and transfer better to other benchmarks. Experiments across multiple benchmarks show that STAGE consistently improves visual quality, stability, and cross-task generalization compared to baseline GRPO.


  • Open Access

    Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation

    by Siqi Yang, Lin Wu, Arnold Wiliem, Brian C. Lovell

    We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on minimizing domain discrepancy via marginal feature distributions alignment. However, aligning the marginal feature distributions does not guarantee the alignment of class conditional distributions. This limitation is more evident when adapting object detectors as the domain discrepancy is larger compared to the image classification task, e.g. various number of objects exist in one image and the majority of content in an image is the background. This motivates us to learn domain invariance for category level semantics via gradient alignment. Intuitively, if the gradients of two domains point in similar directions, then the learning of one domain can improve that of another domain. To achieve gradient alignment, we propose Forward-Backward Cyclic Adaptation, which iteratively computes adaptation from source to target via backward hopping and from target to source via forward passing. In addition, we align low-level features for adapting holistic color/texture via adversarial training. However, the detector performs well on both domains is not ideal for target domain. As such, in each cycle, domain diversity is enforced by maximum entropy regularization on the source domain to penalize confident source-specific learning and minimum entropy regularization on target domain to intrigue target-specific learning. Theoretical analysis of the training process is provided, and extensive experiments on challenging cross-domain object detection datasets have shown the superiority of our approach over the state-of-the-art.

  • Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks

    by Siqi Yang, Arnold Wiliem, Shaokang Chen, Brian C. Lovell