7 papers
Nixie: Efficient, Transparent Temporal Multiplexing for Consumer GPUs
Yechen Xu, Yifei Wang, Nathanael Ren +2
Consumer machines are increasingly running large ML workloads such as large language models (LLMs), text-to-image generation, and interactive image editing. Unlike datacenter GPUs,…
StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios
Yifei Wang, Zhenkai Li, Tianwen Qian +4
As embodied intelligence advances toward real-world deployment, the ability to continuously perceive and reason over streaming visual inputs becomes essential. In such settings, an…
Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
Cai Zhou, Chenyu Wang, Dinghuai Zhang +4
In this paper we introduce Hierarchical Diffusion Language Models (HDLM) -- a novel family of discrete diffusion models for language modeling. HDLM builds on a hierarchical vocabul…
DyKen-Hyena: Dynamic Kernel Generation via Cross-Modal Attention for Multimodal Intent Recognition
Yifei Wang, Wenbin Wang, Yong Luo
Though Multimodal Intent Recognition (MIR) proves effective by utilizing rich information from multiple sources (e.g., language, video, and audio), the potential for intent-irrelev…
Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding
Yifei Wang
Reasoning distillation has emerged as an effective approach to enhance the reasoning capabilities of smaller language models. However, the impact of large-scale reasoning distillat…
Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?
Yifei Wang, Yu Sheng, Linjing Li +1
Recent advances in handling long sequences have facilitated the exploration of long-context in-context learning (ICL). While much of the existing research emphasizes performance im…