4 papers
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
Zhen Zhang, Changyi Yang, Zijie Xia +11
Tokens are the fundamental units of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite it…
LVSum: A Benchmark for Timestamp-Aware Long Video Summarization
Alkesh Patel, Melis Ozyildirim, Ying-Chang Cheng +1
Long video summarization presents significant challenges for multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and pro…
Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
Deepak Nathani, Cheng Zhang, Chang Huan +7
Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assistants, yet the lack of realistic user simulation frameworks hinders th…
Advancing Egocentric Video Question Answering with Multimodal Large Language Models
Alkesh Patel, Vibhav Chitalia, Yinfei Yang
Egocentric Video Question Answering (QA) requires models to handle long-horizon temporal reasoning, first-person perspectives, and specialized challenges like frequent camera movem…