4 citations · 4 across the 4 of their papers we have counts for
4 papers
Self-Augmenting Retrieval for Diffusion Language Models
Paul Jünger, Justin Lovelace, Linxi Zhao +2
Diffusion language models generate text by iteratively denoising an entire response in parallel, holding a noisy draft of the answer at every step. We show that these intermediate…
Flash-WAM: Modality-Aware Distillation for World Action Models
Arman Akbari, Ci Zhang, Arash Akbari +6
World-action models (WAMs) jointly generate future video and robot actions through iterative diffusion, achieving strong performance on manipulation benchmarks but requiring tens o…
OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
Lin Zhao, Yushu Wu, Yifan Gong +2
Autoregressive (AR) video generation extends videos by producing latent chunks sequentially, but scaling to long videos requires repeated access to a growing historical KV cache. E…
Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
Linxi Zhao, Yihe Deng, Weitong Zhang +1
The advancement of Large Vision-Language Models (LVLMs) has increasingly highlighted the critical issue of their tendency to hallucinate non-existing objects in the images. To addr…