12 papers
Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving
Zhaoxin Fan, Tianbao Zhang, Wenjun Wu +5
World models offer a promising paradigm for autonomous driving by predicting how traffic scenes may evolve and using such predictions to support action generation. However, existin…
ChainClaw: A Layered Agent Framework for Reliable On-Chain Execution
Jiacheng Wei, Zhaoxin Fan, Xin Wen +5
General-purpose large language model agents have achieved strong performance on tool-augmented tasks, yet they rely on assumptions break down in blockchain environments. On-chain e…
HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
Boshui Chen, Zhaoxin Fan, Ke Wang +5
Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection…
Lyapunov Probes for Hallucination Detection in Large Foundation Models
Bozhi Luan, Gen Li, Yalan Qin +6
We address hallucination detection in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) by framing the problem through the lens of dynamical systems stabili…
Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
Nanxiang Jiang, Zhaoxin Fan, Baisen Wang +8
Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures…
EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization
Zhaoxin Fan, Nanxiang Jiang, Daiheng Gao +2
Removing undesired concepts from large-scale text-to-image (T2I) and text-to-video (T2V) diffusion models while preserving overall generative quality remains a major challenge, par…
Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
Nanxiang Jiang, Zhaoxin Fan, Enhan Kang +6
Recent advances in text-to-image (T2I) diffusion models have enabled impressive generative capabilities, but they also raise significant safety concerns due to the potential to pro…
Can Structured Templates Facilitate LLMs in Tackling Harder Tasks? : An Exploration of Scaling Laws by Difficulty
Zhichao Yang, Zhaoxin Fan, Gen Li +6
Structured, procedural reasoning is essential for Large Language Models (LLMs), especially in mathematics. While post-training methods have improved LLM performance, they still fal…
TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
Yuanze Hu, Zhaoxin Fan, Xinyu Wang +8
Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications. The prevailing approach to aligning vision and language models involves freezing…
RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks
Shiying Duan, Pei Ren, Nanxiang Jiang +5
Dual-arm robots play a crucial role in improving efficiency and flexibility in complex multitasking scenarios. While existing methods have achieved promising results in task planni…
HF-VTON: High-Fidelity Virtual Try-On via Consistent Geometric and Semantic Alignment
Ming Meng, Qi Dong, Jiajie Li +5
Virtual try-on technology has become increasingly important in the fashion and retail industries, enabling the generation of high-fidelity garment images that adapt seamlessly to t…
AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars
Tianbao Zhang, Jian Zhao, Yuer Li +5
Whole-body audio-driven avatar pose and expression generation is a critical task for creating lifelike digital humans and enhancing the capabilities of interactive virtual agents,…