12 papers
Kwai Summary Attention V2 Technical Report
OneRec Team, Chenglong Chu, Guohong Mu +30
Summary-token architectures such as Kwai Summary Attention (KSA) compress distant context into learnable Summary token per chunk, and hybrid variants interleave these layers with f…
From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation
Tianlu Xie, Xin Ku, Mingjie Sun +8
Generative recommendation represents each item with a sequence of discrete Semantic IDs (SIDs) and predicts the sequence to retrieve the next item. Typical systems use multi-level…
OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
Mingxian Lin, Shengju Qian, Yuqi Liu +9
Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a single first-attempt score per…
UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence
Hongwei Zhang, Qiqiang Zhong, Jiangxia Cao +8
Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-specific search or item-agnostic…
V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models
Xinying Lin, Xuyang Liu, Yiyu Wang +2
Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefi…
Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models
Yuhang Han, Yuyang Wu, Zhengbo Jiao +6
Reinforcement Learning from Verifiable Rewards (RLVR) has substantially enhanced the reasoning capabilities of large language models in abstract reasoning tasks. However, its appli…
Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
Yiyu Wang, Xuyang Liu, Xiyan Gui +5
Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-ti…
AI for Service: Proactive Assistance with AI Glasses
Zichen Wen, Yiyu Wang, Chenfei Liao +10
In an era where AI is evolving from a passive tool into an active and adaptive companion, we introduce AI for Service (AI4Service), a new paradigm that enables proactive and real-t…
Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods
Chenfei Liao, Wensong Wang, Zichen Wen +10
Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectiveness of these methods is commonly…
Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
Junjie Chen, Xuyang Liu, Zichen Wen +3
Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks. However, the increasing demand for high-resolution image and long-…
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Xuyang Liu, Zichen Wen, Shaobo Wang +14
The advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on scaling model parameters. However, as hardware limits constrain further mode…
Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
Xuyang Liu, Yiyu Wang, Junpeng Ma +1
Video large language models (VideoLLM) excel at video understanding, but face efficiency challenges due to the quadratic complexity of abundant visual tokens. Our systematic analys…