arXiv subjects

Juntao Hu

Publications and source records attributed to Juntao Hu.

6 recordsLinked to original sources

arXiv2026

GEIS: A Generation-Evaluation-Improvement Loop of Agent Skills for Long-Form Article Generation

Long-form article generation remains difficult for large language models because it combines long context, long instructions, and long outputs. Existing multi-agent pipelines such as STORM improve information coverage by simulating role-specialized agents, but their capabilities are often entangled in prompts and fixed procedures, making them hard to inspect, reuse, or iteratively improve. This paper presents GEIS (Generation-Evaluation-Improvement loop of agent Skills), a loop of named and declarative skills for Wikipedia-style long-form article generation. Implemented and evaluated in Tasi Harness, GEIS composes skills for article writing, browser-based evidence and image collection, diagram rendering, PDF-aware pairwise evaluation, and rule-level skill improvement. Its core writing skill follows Request, Plan, Draft, Audit, Refine, and Deliver; the pairwise evaluation skill produces structured quality reports; and the improvement skill maps recurrent findings into permanent patches to the writing skill in our 20-topic experiment. We evaluate GEIS on 20 Wikipedia Featured Article topics. Under the same generation backend, GEIS improves over the Tasi Harness default writer by 8.0 points on a 100-point PDF quality rubric and outperforms STORM on the two comparable writing dimensions, structural quality and content quality. In the 20-topic improvement experiment, the patched writing skill raises the average score from 82.90 to 86.95, with 17 out of 20 topics improved and the gain mainly coming from content quality. These results show that long-form generation can be reframed from a fixed workflow into an inspectable, modular, and evaluation-guided improvement loop.

cs.CL↗

arXiv2026

Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?

Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a "Paradox of Simplicity": models that can render complex scenes often fail at trivial, low-entropy tasks, such as generating a uniform pure color image. We argue this is a systemic failure related to uncontrollable emergent abilities. As models scale, strong priors for aesthetics and complexity override deterministic simplicity, creating an "aesthetic bias" that hinders the model's transition from data simulation to true intellectual abstraction. To better investigate this problem, we formalize the concept of AI Obedience, a hierarchical framework that grades a model's ability to transition from probabilistic approximation to pixel-level determinism (Levels 1 to 5). We introduce Violin, the first systematic benchmark designed to evaluate Level 4 Obedience through three deterministic tasks: color purity, image masking, and geometric shape generation. Using Violin, we evaluate several state-of-the-art models and reveal that closed-source models generally outperform open-source ones in deterministic precision. Interestingly, performance on our benchmark correlates with the benchmark in natural image generation. Our work provides a foundational framework and tools for achieving better alignment between human instructions and model outputs.

cs.CV↗

arXiv2026

Gated Rotary-Enhanced Linear Attention with Rank Modulation for Long-term Sequential Recommendation

In Sequential Recommendation Systems (SRSs), Transformer models have demonstrated remarkable performance but face computational and memory cost challenges, especially when modeling long-term user behavior sequences. Due to its quadratic complexity, the dot-product attention mechanism in Transformers becomes expensive for processing long sequences. By approximating the dot-product attention using elaborate mapping functions, linear attention provides a more efficient option with linear complexity. However, existing linear attention methods face three limitations: 1) they often use learnable position encodings, which incur extra computational costs in long-term sequence scenarios, 2) limited by the low-rank deficiency, they may not sufficiently account for user's fine-grained local preferences (short-lived burst of interest), and 3) they try to capture some temporary activities, but often confuse these with stable and long-term interests. This can result in unclear or less effective recommendations. To remedy these drawbacks, we propose a long-term sequential Recommendation model with Gated Rotary Enhanced Linear Attention (RecGRELA). Specifically, we first propose a Rotary-Enhanced Linear Attention (RELA) module to efficiently model long-range dependency within the user's historical information using rotary position encodings. Then, to address the low-rank deficiency of linear attention, we introduce an Adaptive Rank Modulator. It incorporates a rank augmentation branch to explicitly inject local token mixing and a Gated Rank Selector to dynamically balance stable long-term preferences and transient short-term interests. Experimental results on four public benchmark datasets show that our RecGRELA achieves state-of-the-art performance compared with existing SRSs based on Recurrent Neural Networks, Transformer, and Mamba while keeping low memory overhead.

cs.IR↗

arXiv2024

EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts

Recent advancements in image generation have enabled the creation of high-quality images from text conditions. However, when facing multi-modal conditions, such as text combined with reference appearances, existing methods struggle to balance multiple conditions effectively, typically showing a preference for one modality over others. To address this challenge, we introduce EMMA, a novel image generation model accepting multi-modal prompts built upon the state-of-the-art text-to-image (T2I) diffusion model, ELLA. EMMA seamlessly incorporates additional modalities alongside text to guide image generation through an innovative Multi-modal Feature Connector design, which effectively integrates textual and supplementary modal information using a special attention mechanism. By freezing all parameters in the original T2I diffusion model and only adjusting some additional layers, we reveal an interesting finding that the pre-trained T2I diffusion model can secretly accept multi-modal prompts. This interesting property facilitates easy adaptation to different existing frameworks, making EMMA a flexible and effective tool for producing personalized and context-aware images and even videos. Additionally, we introduce a strategy to assemble learned EMMA modules to produce images conditioned on multiple modalities simultaneously, eliminating the need for additional training with mixed multi-modal prompts. Extensive experiments demonstrate the effectiveness of EMMA in maintaining high fidelity and detail in generated images, showcasing its potential as a robust solution for advanced multi-modal conditional image generation tasks.

cs.CV↗

arXiv2024

You Only Need Half: Boosting Data Augmentation by Using Partial Content

We propose a novel data augmentation method termed You Only Need hAlf (YONA), which simplifies the augmentation process. YONA bisects an image, substitutes one half with noise, and applies data augmentation techniques to the remaining half. This method reduces the redundant information in the original image, encourages neural networks to recognize objects from incomplete views, and significantly enhances neural networks' robustness. YONA is distinguished by its properties of parameter-free, straightforward application, enhancing various existing data augmentation strategies, and thereby bolstering neural networks' robustness without additional computational cost. To demonstrate YONA's efficacy, extensive experiments were carried out. These experiments confirm YONA's compatibility with diverse data augmentation methods and neural network architectures, yielding substantial improvements in CIFAR classification tasks, sometimes outperforming conventional image-level data augmentation methods. Furthermore, YONA markedly increases the resilience of neural networks to adversarial attacks. Additional experiments exploring YONA's variants conclusively show that masking half of an image optimizes performance. The code is available at https://github.com/HansMoe/YONA.

cs.CV↗

arXiv2023

Regularized Conditional Alignment for Multi-Domain Text Classification

The most successful multi-domain text classification (MDTC) approaches employ the shared-private paradigm to facilitate the enhancement of domain-invariant features through domain-specific attributes. Additionally, they employ adversarial training to align marginal feature distributions. Nevertheless, these methodologies encounter two primary challenges: (1) Neglecting class-aware information during adversarial alignment poses a risk of misalignment; (2) The limited availability of labeled data across multiple domains fails to ensure adequate discriminative capacity for the model. To tackle these issues, we propose a method called Regularized Conditional Alignment (RCA) to align the joint distributions of domains and classes, thus matching features within the same category and amplifying the discriminative qualities of acquired features. Moreover, we employ entropy minimization and virtual adversarial training to constrain the uncertainty of predictions pertaining to unlabeled data and enhance the model's robustness. Empirical results on two benchmark datasets demonstrate that our RCA approach outperforms state-of-the-art MDTC techniques.

cs.CL↗