6 papers
MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference
Yu Li, Binxu Li, Tian Lan
Autoregressive decoding in Transformer-based language models relies on the KV cache, whose memory footprint grows linearly with sequence length and becomes the primary bottleneck f…
Divergence Minimization Preference Optimization for Diffusion Model Alignment
Binxu Li, Minkai Xu, Jiaqi Han +2
Diffusion models have achieved remarkable success in generating realistic and versatile images from text prompts. Inspired by the recent advancements of language models, there is a…
Closing the Modality Gap for Mixed Modality Search
Binxu Li, Yuhui Zhang, Xiaohan Wang +3
Mixed modality search -- retrieving information across a heterogeneous corpus composed of images, texts, and multimodal documents -- is an important yet underexplored real-world ap…
Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion
Yangfan He, Sida Li, Jianhui Wang +11
Recent advancements in text-to-image (T2I) generation using diffusion models have enabled cost-effective video-editing applications by leveraging pre-trained models, eliminating th…
LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiers
Shantanu Ghosh, Rayan Syed, Chenyu Wang +5
Error slice discovery is crucial to diagnose and mitigate model errors. Current clustering or discrete attribute-based slice discovery methods face key limitations: 1) clustering r…
Efficient Temporal Consistency in Diffusion-Based Video Editing with Adaptor Modules: A Theoretical Framework
Xinyuan Song, Yangfan He, Sida Li +10
Adapter-based methods are commonly used to enhance model performance with minimal additional complexity, especially in video editing tasks that require frame-to-frame consistency.…