8 papers
MViewRouter: Internalizing Geometric Equivariance via Multi-view Alternating Attention for Combinatorial Routing
Shiyan Liu, Bohan Tan, Yaoxin Wu +1
Combinatorial routing problems such as the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) are fundamental NP-hard problems with broad real-worl…
Test-Time Training for Zero-Resource Dense Retrieval Reranking
Shiyan Liu, Yichen Li
Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings. Existing approaches face a fundamental dilemma: cross-encoders de…
Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization
Shiyan Liu, Qifeng Xia, Qiyun Xia +3
Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering. Reflective APO methods such as GEPA iterativ…
DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation
Shiyan Liu, Jian Ma, Rui Qu
As Retrieval-Augmented Generation (RAG) systems evolve toward more sophisticated architectures, ensuring their trustworthiness through explainable and robust evaluation becomes cri…
VAGPO: Vision-augmented Asymmetric Group Preference Optimization for Graph Routing Problems
Shiyan Liu, Bohan Tan, Zhiguang Cao +1
Graph routing problems play a vital role in web-related networks, where finding optimal paths across graphs is essential for efficient data transmission and content delivery. Class…
FluentLip: A Phonemes-Based Two-stage Approach for Audio-Driven Lip Synthesis with Optical Flow Consistency
Shiyan Liu, Rui Qu, Yan Jin
Generating consecutive images of lip movements that align with a given speech in audio-driven lip synthesis is a challenging task. While previous studies have made strides in synch…
SNAP: Stopping Catastrophic Forgetting in Hebbian Learning with Sigmoidal Neuronal Adaptive Plasticity
Tianyi Xu, Patrick Zheng, Shiyan Liu +2
Artificial Neural Networks (ANNs) suffer from catastrophic forgetting, where the learning of new tasks causes the catastrophic forgetting of old tasks. Existing Machine Learning (M…
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
Muxi Diao, Rumei Li, Shiyang Liu +4
As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to…