7 citations · 9 across the 21 of their papers we have counts for
22 papers
Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
Guanghui Min, Liang Wu, Mingjia Shi +4
Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. Existing pr…
S^3martCirc: Self-supervised Smart Circuit Discovery
Wendy Zheng, Yinhan He, Liang Wu +1
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks, from text summarization to question answering. Despite these capabilities, their black-b…
Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought Compression
Tianyi Zhao, Yinhan He, Wendy Zheng +2
Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression reduces this cost by pruning ful…
Implicit Reasoning for Large Language Model-based Generative Recommendation
Yinhan He, Liam Collins, Bhuvesh Kumar +3
Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR), promising access to pretrained world knowledge. Yet reliably invoking this kn…
Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
Yaochen Zhu, Harald Steck, James McInerney +4
Direct preference optimization (DPO) is a simple and effective alignment strategy for large language models (LLMs) based on pairwise preferences. In recommender systems, however, u…
Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
Tianyi Zhao, Yinhan He, Wendy Zheng +2
Large language models are often not just wrong, but \emph{confidently wrong}: when they produce factually incorrect answers, they tend to verbalize overly high confidence rather th…
Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping
Zhenyu Lei, Qiong Wu, Jianxiong Dong +4
Large language models (LLMs) often exhibit flawed reasoning ability that undermines reliability. Existing approaches to improving reasoning typically treat it as a general and mono…
Saliency-Aware Multi-Route Thinking: Revisiting Vision-Language Reasoning
Mingjia Shi, Yinhan He, Yaochen Zhu +1
Vision-language models (VLMs) aim to reason by jointly leveraging visual and textual modalities. While allocating additional inference-time computation has proven effective for lar…
PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling
Kavana Venkatesh, Yinhan He, Jundong Li +1
Large language model (LLM)-based multi-agent systems enable expressive agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned state-transition simula…
IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
Yinhan He, Yaochen Zhu, Mingjia Shi +5
Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-tr…
MolEdit: Knowledge Editing for Multimodal Molecule Language Models
Zhenyu Lei, Patrick Soga, Yaochen Zhu +3
Understanding and continuously refining multimodal molecular knowledge is crucial for advancing biomedicine, chemistry, and materials science. Molecule language models (MoLMs) have…
SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
Yinhan He, Wendy Zheng, Yaochen Zhu +6
The verbosity of Chain-of-Thought (CoT) reasoning hinders its mass deployment in efficiency-critical applications. Recently, implicit CoT approaches have emerged, which encode reas…
Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
Yaochen Zhu, Harald Steck, Dawen Liang +4
Large language models (LLMs) are reshaping the recommender system paradigm by enabling users to express preferences and receive recommendations through conversations. Yet, aligning…
Energy-Based Models for Predicting Mutational Effects on Proteins
Patrick Soga, Zhenyu Lei, Yinhan He +2
Predicting changes in binding free energy () is a vital task in protein engineering and protein-protein interaction (PPI) engineering for drug discovery. Previous works have o…
Edge Prompt Tuning for Graph Neural Networks
Xingbo Fu, Yinhan He, Jundong Li
Pre-training powerful Graph Neural Networks (GNNs) with unlabeled graph data in a self-supervised manner has emerged as a prominent technique in recent years. However, inevitable o…
Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
Yushun Dong, Patrick Soga, Yinhan He +2
Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based learning tasks. While their performance is often attributed to the powerful neighborhood aggreg…
Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning
Xingbo Fu, Zihan Chen, Yinhan He +4
Federated Graph Learning (FGL) enables multiple clients to jointly train powerful graph learning models, e.g., Graph Neural Networks (GNNs), without sharing their local graph data…
Global Graph Counterfactual Explanation: A Subgraph Mapping Approach
Yinhan He, Wendy Zheng, Yaochen Zhu +5
Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain G…
Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective for Molecular Property Prediction
Yinhan He, Zaiyi Zheng, Patrick Soga +3
In recent years, Graph Neural Networks (GNNs) have become successful in molecular property prediction tasks such as toxicity analysis. However, due to the black-box nature of GNNs,…
Causal Inference with Latent Variables: Recent Advances and Future Prospectives
Yaochen Zhu, Yinhan He, Jing Ma +3
Causality lays the foundation for the trajectory of our world. Causal inference (CI), which aims to infer intrinsic causal relations among variables of interest, has emerged as a c…
Spectral Greedy Coresets for Graph Neural Networks
Mucong Ding, Yinhan He, Jundong Li +1
The ubiquity of large-scale graphs in node-classification tasks significantly hinders the real-world applications of Graph Neural Networks (GNNs). Node sampling, graph coarsening,…
Safety in Graph Machine Learning: Threats and Safeguards
Song Wang, Yushun Dong, Binchi Zhang +7
Graph Machine Learning (Graph ML) has witnessed substantial advancements in recent years. With their remarkable ability to process graph-structured data, Graph ML techniques have b…