2 citations · 3 across the 15 of their papers we have counts for
16 papers
KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing
Mufei Li, Shikun Liu, Dongqi Fu +5
Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached st…
Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
Shikun Liu, Mufei Li, Dongqi Fu +5
Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with…
PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
Xiaoyi Chen, Haoyuan Wang, Siyuan Tang +4
Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its…
Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction
Haoyu Wang, Yuxin Chen, Liang Luo +3
Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However,…
Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation
Mufei Li, Dongqi Fu, Limei Wang +10
Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased re…
Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings
Shikun Liu, Haoyu Wang, Mufei Li +1
Text embeddings from Large Language Models (LLMs) have become foundational for numerous applications. However, these models typically operate on raw text, overlooking the rich stru…
Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
Haoyu Wang, Peihao Wang, Mufei Li +4
Modern large language models (LLMs) are inherently auto-regressive, requiring input to be serialized into flat sequences regardless of their structural dependencies. This serializa…
Towards A Universal Graph Structural Encoder
Jialin Chen, Haolan Zuo, Haoyu Peter Wang +3
Recent advancements in large-scale pre-training have shown the potential to learn generalizable representations for downstream tasks. In the graph domain, however, capturing and tr…
Model Generalization on Text Attribute Graphs: Principles with Large Language Models
Haoyu Wang, Shikun Liu, Rongzhe Wei +1
Large language models (LLMs) have recently been introduced to graph learning, aiming to extend their zero-shot generalization success to tasks where labeled graph data is scarce. A…
A Benchmark on Directed Graph Representation Learning in Hardware Designs
Haoyu Wang, Yinan Huang, Nan Wu +1
To keep pace with the rapid advancements in design complexity within modern computing systems, directed graph representation learning (DGRL) has become crucial, particularly for en…
Sampling Transferable Graph Neural Networks with Limited Graph Information
Haoyu Wang, Renyuan Ma, Gonzalo Mateos +1
Graph neural networks (GNNs) achieve strong performance on graph learning tasks, but training on large-scale networks remains computationally challenging. Transferability results s…
What Are Good Positional Encodings for Directed Graphs?
Yinan Huang, Haoyu Wang, Pan Li
Positional encodings (PEs) are essential for building powerful and expressive graph neural networks and graph transformers, as they effectively capture the relative spatial relatio…
Certified Machine Unlearning via Noisy Stochastic Gradient Descent
Eli Chien, Haoyu Wang, Ziang Chen +1
``The right to be forgotten'' ensured by laws for user data privacy becomes increasingly important. Machine unlearning aims to efficiently remove the effect of certain data points…
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
Eli Chien, Haoyu Wang, Ziang Chen +1
Machine unlearning has raised significant interest with the adoption of laws ensuring the ``right to be forgotten''. Researchers have provided a probabilistic notion of approximate…
DIG-MILP: a Deep Instance Generator for Mixed-Integer Linear Programming with Feasibility Guarantee
Haoyu Wang, Jialin Liu, Xiaohan Chen +3
Mixed-integer linear programming (MILP) stands as a notable NP-hard problem pivotal to numerous crucial industrial applications. The development of effective algorithms, the tuning…
On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
Rongzhe Wei, Eleonora Kreačić, Haoyu Wang +4
Privacy concerns have led to a surge in the creation of synthetic datasets, with diffusion models emerging as a promising avenue. Although prior studies have performed empirical ev…