Institution profile

KRAFTON Inc.

Industry researchasia · kr
Official website
Research library55linked papers
Opportunities0open roles
Selected work

Representative Papers

Imperceptible Protection against Style Imitation from Diffusion Models

Mar 28, 2024arXiv.org

To address copyright infringement and artistic style appropriation risks posed by diffusion models, this paper proposes a visually lossless copyright protection method. The approach comprises three key contributions: (1) perception-sensitive map-guided instance-aware fine-tuning, enabling fine-grained stylistic perturbation; (2) difficulty-aware dynamic intensity modulation, which adaptively adjusts perturbation magnitude based on the sample’s stylistic mimicability; and (3) a multi-scale perceptual constraint library, jointly optimizing defense robustness and image fidelity. Without introducing perceptible visual artifacts, the method achieves over 92% style imitation suppression, reduces LPIPS by 41%, and improves FID by 27%, significantly outperforming existing state-of-the-art methods.

7 citationsRead paper

A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?

Sep 30, 2026

This study addresses the limitation of existing benchmarks in evaluating the ability of coding agents to faithfully implement interdependent requirements spanning logic, rendering, and interaction within long-form game design documents (GDDs). To this end, we construct a benchmark comprising 100 long GDDs and propose a dependency-aware contract-based evaluation framework. This framework translates requirements into formal contracts and integrates static code analysis with adaptive testing, enabling consistent cross-agent comparisons under fixed contractual specifications. Our experiments reveal that current agents struggle to jointly satisfy interdependent requirements. Furthermore, introducing a requirement-specific feedback mechanism yields a 10.9% relative improvement in GDD fidelity compared to a self-revision baseline.

0 citationsRead paper

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Jun 30, 2026

Existing latent chain-of-thought (Latent CoT) methods significantly underperform explicit CoT when model size exceeds 1 billion parameters, with the performance gap widening as scale increases. This work proposes a recurrent deep Transformer architecture that enhances computational depth through weight sharing and applies explicit CoT supervision via cross-entropy loss in parallel across multiple latent state positions. For the first time at the 3B parameter scale, this approach closes the performance gap between latent and explicit CoT, achieving comparable accuracy while reducing inference latency by 2.5–6.9×. Experiments demonstrate the critical roles of recurrence and parallel supervision in latent reasoning, revealing that latent states are interpretable and well-aligned with CoT: a base language model head can recover both correct and alternative intermediate reasoning steps from these representations.

0 citationsRead paper
Recent publications

Latest Papers

A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?

Sep 30, 2026

This study addresses the limitation of existing benchmarks in evaluating the ability of coding agents to faithfully implement interdependent requirements spanning logic, rendering, and interaction within long-form game design documents (GDDs). To this end, we construct a benchmark comprising 100 long GDDs and propose a dependency-aware contract-based evaluation framework. This framework translates requirements into formal contracts and integrates static code analysis with adaptive testing, enabling consistent cross-agent comparisons under fixed contractual specifications. Our experiments reveal that current agents struggle to jointly satisfy interdependent requirements. Furthermore, introducing a requirement-specific feedback mechanism yields a 10.9% relative improvement in GDD fidelity compared to a self-revision baseline.

0 citationsRead paper

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Jun 30, 2026

Existing latent chain-of-thought (Latent CoT) methods significantly underperform explicit CoT when model size exceeds 1 billion parameters, with the performance gap widening as scale increases. This work proposes a recurrent deep Transformer architecture that enhances computational depth through weight sharing and applies explicit CoT supervision via cross-entropy loss in parallel across multiple latent state positions. For the first time at the 3B parameter scale, this approach closes the performance gap between latent and explicit CoT, achieving comparable accuracy while reducing inference latency by 2.5–6.9×. Experiments demonstrate the critical roles of recurrence and parallel supervision in latent reasoning, revealing that latent states are interpretable and well-aligned with CoT: a base language model head can recover both correct and alternative intermediate reasoning steps from these representations.

0 citationsRead paper

AsyncOPD: How Stale Can On-Policy Distillation Be?

Jun 23, 2026

This work addresses the instability and performance degradation in asynchronous online policy distillation (OPD) caused by training on stale policy data. It is the first to demonstrate that the reverse KL divergence is highly sensitive to outdated data, whereas the forward KL divergence exhibits greater robustness. Building on this insight, the authors propose an efficient alternative that recomputes the KL signal using the current student model and introduces a multi-sample Monte Carlo estimator to balance bias and variance. The resulting open-source AsyncOPD framework achieves comparable accuracy to synchronous training while improving throughput by 1.6–3.8×.

0 citationsRead paper