arXiv subjects

Haoyang Xu

Publications and source records attributed to Haoyang Xu.

6 recordsLinked to original sources

arXiv2026

Distilling Game Code World Model Generation into Lightweight Large Language Models

Large Language Models (LLMs) have shown great ability in generating executable code from natural language, opening the possibility of automatically constructing environments for AI agents. Recent work on Code World Models (CWMs) demonstrates that LLMs can translate game rules into Python implementations compatible with solvers like Monte Carlo Tree Search. We study this problem in game settings, where generated environments must implement rules, legal actions, state transitions, observations, and rewards. We refer to these game-specific executable models as Game Code World Models (GameCWMs). However, current approaches to generating code world models rely on frontier models and inference-time refinement loops, limiting accessibility and scalability. This work investigates whether GameCWM generation capabilities can be distilled into smaller models through post-training. We introduce: (1) a curated dataset of 30 games spanning perfect and imperfect information games, (2) a verification framework that evaluates generated code against structural and semantic game properties, and (3) a post-training pipeline combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR). We experiment with Qwen2.5-3B-Instruct and find that SFT can increase syntactic correctness, while RLVR can improve execution-level adherence to game rules, thereby improving Qwen's ability to generate valid GameCWMs in both perfect and imperfect information games. Overall, our pipeline makes Qwen2.5-3B-Instruct more capable of generating valid GameCWMs, thereby offering a scalable path toward automatic environment generation from natural language.

cs.AI↗

arXiv2026

Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols

We study data curation for multimodal reasoning in a fixed-protocol fine-tuning regime, where the base model, optimizer, training schedule, and evaluation pipeline are held constant and the main degree of freedom is the training data. Using the NeurIPS 2025 Data Curation for Vision--Language Reasoning (DCVLR) challenge as a controlled testbed, we analyze how source-dataset alignment, model-relative difficulty, dataset size, diversity heuristics, and rewritten synthetic mixtures affect downstream reasoning accuracy. Among the tested interventions, difficulty filtering on an aligned source corpus provides the strongest gains at matched scale. The effect is not explained only by LiveXivTQA weighting: a per-benchmark decomposition shows that much of the improvement over random sampling comes from OlympiadBench, the largest non-LiveXivTQA benchmark. Qwen-derived difficulty scores also transfer to some additional model families, though the benefit is architecture-dependent. In contrast, increasing dataset size beyond roughly 1k aligned examples mainly reduces run-to-run variance under the fixed recipe, while the diversity and rewritten CoSyn mixtures we tested do not improve over the difficulty-filtered baseline. These results provide a scoped empirical recipe for data-constrained multimodal reasoning fine-tuning, rather than a universal claim about data selection across all training regimes.

cs.AI↗

arXiv2025

No Pulsar Detected in Reprocessed Archival Parkes Observations of SNR 1987A

We have reprocessed the available archival radio pulsar search observations of SNR 1987A taken with the Parkes 64-m telescope, some of which have not been previously published. We conducted a standard periodicity search on these data as well as a single pulse search at a range of dispersion measures. We found no convincing candidate signals, and we calculate flux density, luminosity, and single pulse fluence limits from these observations. The derived luminosity limits are comparable to the luminosities of three young, energetic pulsars (the Crab pulsar, PSR B0540$-$69, and PSR J0537$-$6910), and so we cannot rule out the existence of a pulsar in SNR 1987A with a similar radio luminosity.

astro-ph.HE↗

arXiv2025

Penalizing Boundary Activation for Object Completeness in Diffusion Models

Diffusion models have emerged as a powerful technique for text-to-image (T2I) generation, creating high-quality, diverse images across various domains. However, a common limitation in these models is the incomplete display of objects, where fragments or missing parts undermine the model's performance in downstream applications. In this study, we conduct an in-depth analysis of the incompleteness issue and reveal that the primary factor behind incomplete object generation is the usage of RandomCrop during model training. This widely used data augmentation method, though enhances model generalization ability, disrupts object continuity during training. To address this, we propose a training-free solution that penalizes activation values at image boundaries during the early denoising steps. Our method is easily applicable to pre-trained Stable Diffusion models with minimal modifications and negligible computational overhead. Extensive experiments demonstrate the effectiveness of our method, showing substantial improvements in object integrity and image quality.

cs.CV↗

arXiv2023

Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty

Task planning for embodied AI has been one of the most challenging problems where the community does not meet a consensus in terms of formulation. In this paper, we aim to tackle this problem with a unified framework consisting of an end-to-end trainable method and a planning algorithm. Particularly, we propose a task-agnostic method named 'planning as in-painting'. In this method, we use a Denoising Diffusion Model (DDM) for plan generation, conditioned on both language instructions and perceptual inputs under partially observable environments. Partial observation often leads to the model hallucinating the planning. Therefore, our diffusion-based method jointly models both state trajectory and goal estimation to improve the reliability of the generated plan, given the limited available information at each step. To better leverage newly discovered information along the plan execution for a higher success rate, we propose an on-the-fly planning algorithm to collaborate with the diffusion-based planner. The proposed framework achieves promising performances in various embodied AI tasks, including vision-language navigation, object manipulation, and task planning in a photorealistic virtual environment. The code is available at: https://github.com/joeyy5588/planning-as-inpainting.

cs.CV↗

arXiv2019

Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection

In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap can be bounded. Moreover, some recent works, such as the Bayesian GAN, can be re-interpreted based on our theoretical insight from privacy protection. Quantitatively, to evaluate the information leakage of well-trained GAN models, we perform various membership attacks on these models. The results show that previous Lipschitz regularization techniques are effective in not only reducing the generalization gap but also alleviating the information leakage of the training dataset.

cs.LG↗