7 papers
CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation
Enhan Li, Junhao He, Hongyang Du
On-policy distillation (OPD) supervises a student language model on trajectories sampled from its current policy, but assigns equal credit to response tokens with unequal supervisi…
AudioKV: KV Cache Eviction in Efficient Large Audio Language Models
Yuxuan Wang, Peize He, Xiyan Gui +5
Large Audio-Language Models (LALMs) have set new benchmarks in speech processing, yet their deployment is hindered by the memory footprint of the Key-Value (KV) cache during long-c…
StarSD: One-for-Many Speculative Decoding
Junhao He, Feiran You, Hongyang Du
Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution and d…
K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling
Yongrui Chen, Yi Huang, Yunchang Liu +5
Continual Structured Knowledge Reasoning (CSKR) focuses on training models to handle sequential tasks, where each task involves translating natural language questions into structur…
MM-FusionNet: Context-Aware Dynamic Fusion for Multi-modal Fake News Detection with Large Vision-Language Models
Junhao He, Tianyu Liu, Jingyuan Zhao +1
The proliferation of multi-modal fake news on social media poses a significant threat to public trust and social stability. Traditional detection methods, primarily text-based, oft…
Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning
Yongrui Chen, Junhao He, Linbo Fu +10
Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions by using structured sources such as tables, databases, and knowledge graphs in a unified way…
Pandora: A Code-Driven Large Language Model Agent for Unified Reasoning Across Diverse Structured Knowledge
Yongrui Chen, Junhao He, Linbo Fu +10
Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions (NLQs) by using structured sources such as tables, databases, and knowledge graphs in a unif…