Publications
We not only work independently but also collaborate closely with individuals from academia to advance our research.
*Participant name in bold works at KRAFTON
Filter
Secure Inference for Diffusion Models via Unconditional Scores
Secure Inference for Diffusion Models via Unconditional Scores
See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models
Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models
VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?
VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?
ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
Draft-based Approximate Inference for LLMs
Draft-based Approximate Inference for LLMs
T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models
T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models
Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
Emotion Manipulation for Talking-head Videos via Facial Landmarks
Emotion Manipulation for Talking-head Videos via Facial Landmarks
Distilling LLM Agent into Small Models with Retrieval and Code Tools
