7 papers
Not All Visual Tokens Are Equally Safe to Remove:Consequence-Sensitive Visual Token Compression
Jingbo Wen, Liang He, Mingyu Cao +4
Visual token compression for vision--language models (VLMs) has largely relied on criteria such as attention, redundancy, and uncertainty to maximize average accuracy under a fixed…
From Relevance to Execution Utility: Reward-Aware Dynamic Execution Gating for Skill-Based LLM Agents
Liang He, Jingbo Wen, Hongyu Gu +5
Agent skills are increasingly used to equip large language model (LLM) agents with reusable procedural knowledge. Although recent work has substantially improved skill retrieval du…
Framing Migration News with LLMs: Structured CoT as a Support for Human Interpretation
David Alonso del Barrio, Jing Wen, Daniel Gatica-Perez
Frame analysis of migration news is a socially consequential task: media scholars and researchers who study how migration is narrated need tools that are not only accurate, but tra…
BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding
Liang He, Jingbo Wen, Qishi Zhan +4
Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple tokens that a verifier validates in parallel. In resource-constrained deployments, the…
Timing Matters: How Using LLMs at Different Timings Influences Writers' Perceptions and Ideation Outcomes in AI-Assisted Ideation
Peinuan Qin, Chi-Lan Yang, Jingshu Li +2
Large Language Models (LLMs) have been widely used to support ideation in the writing process. However, whether generating ideas with the help of LLMs leads to idea fixation or ide…
AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning
Jiaxi Cui, Wentao Zhang, Jing Tang +6
The pervasive deployment of Large Language Models-LLMs in various sectors often neglects the nuanced requirements of individuals and small organizations, who benefit more from mode…