12 papers
Drifting Preference Optimization for One-Step Generative Models
Zhou Jiang, Yandong Wen, Zhen Liu
One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standar…
CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Web Cloud-Edge Systems
Yannan Wang, Longli Yang, Zhen Liu +2
LLM-based Web agents are increasingly deployed on edge servers to carry out long-horizon tasks on behalf of users with low latency. However, the lightweight models that fit on edge…
EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
Ruixiang Wang, Qingming Liu, Yueci Deng +3
Video generative models offer a promising basis for robotic planning by predicting future visual rollouts from observations and task instructions. However, their training objective…
GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation
Wei Zeng, Fengwei An, Zhen Liu +1
Game UI design requires consistent visual assets across rarity tiers yet remains a predominantly manual process. We present GameUIAgent, an LLM-powered agentic framework that trans…
Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance
Zhou Jiang, Yandong Wen, Zhen Liu
Aligning large-scale text-to-image diffusion models with nuanced human preferences remains challenging. While direct preference optimization (DPO) is simple and effective, large-sc…
Scalable Generative Game Engine: Breaking the Resolution Wall via Hardware-Algorithm Co-Design
Wei Zeng, Xuchen Li, Ruili Feng +3
Real-time generative game engines represent a paradigm shift in interactive simulation, promising to replace traditional graphics pipelines with neural world models. However, exist…
Value Gradient Guidance for Flow Matching Alignment
Zhen Liu, Tim Z. Xiao, Carles Domingo-Enrich +2
While methods exist for aligning flow matching models--a popular and effective class of generative models--with human preferences, existing approaches fail to achieve both adaptati…
AutoNeural: Co-Designing Vision-Language Models for NPU Inference
Wei Chen, Liangmin Wu, Yunhai Hu +9
While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrat…
Compositional Machine Design as Program Synthesis with LLMs
Wenqian Zhang, Yangyi Huang, Weiyang Liu +1
Large language models (LLMs) have shown strong abilities in writing and revising programs, yet many program-synthesis benchmarks still evaluate programs in symbolic or digital envi…
Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
Qingming Liu, Zhen Liu, Dinghuai Zhang +1
Generating high-quality and photorealistic 3D assets remains a longstanding challenge in 3D vision and computer graphics. Although state-of-the-art generative models, such as diffu…
Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling
Tim Z. Xiao, Johannes Zenn, Zhen Liu +3
Large language models (LLMs) can often accurately describe probability distributions using natural language, yet they still struggle to generate faithful samples from them. This mi…
Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
Zhen Liu, Tim Z. Xiao, Weiyang Liu +2
While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetune pretrained diffusion models with some…