4 citations · 10 across the 23 of their papers we have counts for
24 papers
Cavity-tunable Pseudospin-Hall Topology and Edge Transport
Minghui Niu, Yan Meng, Chengle Fan +5
Topological edge states are a hallmark of topological phases, with their existence tied to bulk band topology through bulk-edge correspondence. In photonic pseudospin-Hall systems,…
The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training
Hongtao Zhang, Wenjie Zhou, Chenxi Jia +2
Large language model pre-training typically exhibits a two-phase trajectory: a fast initial loss drop followed by a prolonged slow improvement. We identify an underlying spectral p…
Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
Wenjie Zhou, Bohan Wang, Hongtao Zhang +3
Model merging has emerged as a lightweight paradigm for enhancing Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. In this work, we analyze lat…
Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs
Wanli Yang, Hongyu Zang, Junwei Zhang +5
Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge remains an open question. We stu…
PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding
Baolong Bi, Yuyao Ge, Shenghua Liu +9
Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at trai…
Gated Differentiable Working Memory for Long-Context Language Modeling
Lingrui Mei, Shenghua Liu, Yiwei Wang +7
Long contexts challenge transformers: attention scores dilute across thousands of tokens, critical information is often lost in the middle, and models struggle to adapt to novel pa…
Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
Baolong Bi, Shenghua Liu, Yiwei Wang +6
Recent advances in reinforcement learning (RL) have significantly improved the complex reasoning capabilities of large language models (LLMs). Despite these successes, existing met…
Not in Sync: Unveiling Temporal Bias in Audio Chat Models
Jiayu Yao, Shenghua Liu, Yiwei Wang +5
Large Audio Language Models (LALMs) are increasingly applied to audio understanding and multimodal reasoning, yet their ability to locate when events occur remains underexplored. W…
A Survey of Vibe Coding with Large Language Models
Yuyao Ge, Lingrui Mei, Zenghao Duan +12
The advancement of large language models (LLMs) has catalyzed a paradigm shift from code generation assistance to autonomous coding agents, enabling a novel development methodology…
Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation
Jiayu Yao, Shenghua Liu, Yiwei Wang +5
Multimodal Retrieval-Augmented Generation (RAG) systems have become essential in knowledge-intensive and open-domain tasks. As retrieval complexity increases, ensuring the robustne…
a1: Steep Test-time Scaling Law via Environment Augmented Generation
Lingrui Mei, Shenghua Liu, Yiwei Wang +5
Large Language Models (LLMs) have made remarkable breakthroughs in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during com…
Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
Yuyao Ge, Shenghua Liu, Yiwei Wang +4
Recent advances in Large Language Models (LLMs) have introduced Reasoning Large Language Models (RLLMs), which employ extended thinking processes with reflection and self-correctio…
Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models
Baolong Bi, Shenghua Liu, Yiwei Wang +4
Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by integrating external knowledge. However, conflicts between parametric knowledge and…
HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router
Lingrui Mei, Shenghua Liu, Yiwei Wang +3
As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge. Ideally, LLMs should provide informa…
StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models
Baolong Bi, Shenghua Liu, Yiwei Wang +4
As the modern tool of choice for question answering, large language models (LLMs) are expected to deliver answers with up-to-date knowledge. To achieve such ideal question-answerin…
Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities
Baolong Bi, Shenghua Liu, Yiwei Wang +4
The parametric knowledge memorized by large language models (LLMs) becomes outdated quickly. In-context editing (ICE) is currently the most effective method for updating the knowle…
"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak
Lingrui Mei, Shenghua Liu, Yiwei Wang +3
"Jailbreak" is a major safety concern of Large Language Models (LLMs), which occurs when malicious prompts lead LLMs to produce harmful outputs, raising issues about the reliabilit…
Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts
Baolong Bi, Shenghua Liu, Lingrui Mei +3
The knowledge within large language models (LLMs) may become outdated quickly. While in-context editing (ICE) is currently the most effective method for knowledge editing (KE), it…
Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
Baolong Bi, Shenghua Liu, Yiwei Wang +5
As the modern tools of choice for text understanding and generation, large language models (LLMs) are expected to accurately output answers by leveraging the input context. This re…
LPNL: Scalable Link Prediction with Large Language Models
Baolong Bi, Shenghua Liu, Yiwei Wang +2
Exploring the application of large language models (LLMs) to graph learning is a emerging endeavor. However, the vast amount of information inherent in large graphs poses significa…
Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?
Yuyao Ge, Shenghua Liu, Baolong Bi +5
Large language models (LLMs) have achieved significant success in reasoning tasks, including mathematical reasoning and logical deduction. Among these reasoning tasks, graph proble…
A Topological Perspective on Demystifying GNN-Based Link Prediction Performance
Yu Wang, Tong Zhao, Yuying Zhao +4
Graph Neural Networks (GNNs) have shown great promise in learning node embeddings for link prediction (LP). While numerous studies aim to improve the overall LP performance of GNNs…
A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications
Yi Zhang, Yuying Zhao, Zhaoqing Li +5
Graph Neural Networks (GNNs) have gained significant attention owing to their ability to handle graph-structured data and the improvement in practical applications. However, many o…
Fast Searching The Densest Subgraph And Decomposition With Local Optimality
Yugao Zhu, Shenghua Liu, Wenjie Feng +1
Densest Subgraph Problem (DSP) is an important primitive problem with a wide range of applications, including fraud detection, community detection and DNA motif discovery. Edge-bas…