Author name cluster

Zihan Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

17 papers

2 author rows

AAAI Conference 2026 Conference Paper

ResMAS: Resilience Optimization in LLM-based Multi-agent Systems

Zhilun Zhou
Zihan Liu
Jiahe Liu
Qingyu Shao
Yihan Wang
Kun Shao
Depeng Jin
Fengli Xu

Large Language Model-based Multi-Agent Systems (LLM-based MAS), where multiple LLM agents collaborate to solve complex tasks, have shown impressive performance in many areas. However, MAS are typically distributed across different devices or environments, making them vulnerable to perturbations such as agent failures. While existing works have studied the adversarial attacks and corresponding defense strategies, they mainly focus on reactively detecting and mitigating attacks after they occur rather than proactively designing inherently resilient systems. In this work, we study the resilience of LLM-based MAS under perturbations and find that both the communication topology and prompt design significantly influence system resilience. Motivated by these findings, we propose ResMAS: a two-stage framework for enhancing MAS resilience. First, we train a reward model to predict the MAS’s resilience, based on which we train a topology generator to automatically design resilient topology for specific tasks through reinforcement learning. Second, we introduce a topology-aware prompt optimization method that refines each agent’s prompt based on its connections and interactions with other agents. Extensive experiments across a range of tasks show that our approach substantially improves MAS resilience under various constraints. Moreover, our framework demonstrates strong generalization ability to new tasks and models, highlighting its potential for building resilient MASs.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Yang Chen
Zhuolin Yang
Zihan Liu
Chankyu Lee
Peng Xu
Mohammad Shoeybi
Bryan Catanzaro
Wei Ping

Despite recent progress in large-scale reinforcement learning (RL) for reasoning, the training recipe for building high-performing reasoning models remains elusive. Key implementation details of frontier models, such as DeepSeek-R1, including data curation strategies and RL training recipe, are often omitted. Moreover, recent research indicates distillation remains more effective than RL for smaller models. In this work, we demonstrate that large-scale RL can significantly enhance the reasoning capabilities of strong, small- and mid-sized models, achieving results that surpass those of state-of-the-art distillation-based models. We systematically study the RL training process through extensive ablations and propose a simple yet effective approach: first training on math-only prompts, then on code-only prompts. Notably, we find that math-only RL not only significantly enhances the performance of strong distilled models on math benchmarks (e. g. , +14. 6\% / +17. 2\% on AIME 2025 for the 7B / 14B models), but also code reasoning tasks (e. g. , +6. 8\% / +5. 8\% on LiveCodeBench for the 7B / 14B models). In addition, extended code-only RL further improves code benchmark performance while causing minimal degradation in math results. We develop a robust data curation pipeline to collect challenging prompts with high-quality, verifiable answers and test cases to enable verification-based RL across both domains. The dataset will be released to support open research. Finally, we identify key experimental insights, including curriculum learning with progressively increasing response lengths and the stabilizing effect of on-policy parameter updates. We find that RL not only elicits the foundational reasoning capabilities acquired during pretraining and supervised fine-tuning (SFT), but also pushes the limits of the model’s reasoning ability, enabling it to solve problems that were previously unsolvable.

PDF Details

NeurIPS Conference 2025 Conference Paper

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Zekai Zhao
Qi Liu
Kun Zhou
Zihan Liu
Yifei Shao
Zhiting Hu
Biwei Huang

Despite the remarkable reasoning performance, eliciting the long chain-of-thought(CoT) ability in large language models(LLMs) typically requires costly reinforcement learning or supervised fine-tuning on high-quality distilled data. We investigate the internal mechanisms behind this capability and show that a small set of high-impact activations in the last few layers, greatly govern the long-form reasoning attributes, e. g. output length and self-reflection. Through simply amplifying these activations and adding ``wait'' tokens, the long CoT ability can be invoked without training, leading to significantly increased self-reflection rate and accuracy. In addition, we also find that the activation changes follow predictable trajectories, i. e. a sharp rise after special tokens and a subsequent exponential decay. Based on these insights, we introduce a general training-free activation control technique. It utilizes a few contrastive examples to identify the relevant activations, and then incorporates simple analytic functions to adjust their values at inference time to elicit long CoTs. Extensive experiments have verified the effectiveness of our methods in efficiently eliciting the long CoT ability of LLMs and improving the performance. Besides, we further propose a parameter-efficient fine-tuning method that trains only the last-layer activation amplification module and a few LoRA layers, outperforming LoRA on reasoning benchmarks with much fewer parameters. Our code and data will be fully public released.

PDF Details

NeurIPS Conference 2025 Conference Paper

ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive

Xinhao Luo
Zihan Liu
Yangjie Zhou
Shihan Fang
Ziyu Huang
Yu Feng
Chen Zhang
Shixuan Sun

Large language model (LLM) decoding suffers from high latency due to fragmented execution across operators and heavy reliance on off-chip memory for data exchange and reduction. This execution model limits opportunities for fusion and incurs significant memory traffic and kernel launch overhead. While modern architectures such as NVIDIA Hopper provide distributed shared memory and low-latency intra-cluster interconnects, they expose only low-level data movement instructions, lacking structured abstractions for collective on-chip communication. To bridge this software-hardware gap, we introduce two cluster-level communication primitives, ClusterReduce and ClusterGather, which abstract common communication patterns and enable structured, high-speed data exchange and reduction between thread blocks within a cluster, allowing intermediate results to be on-chip without involving off-chip memory. Building on these abstractions, we design ClusterFusion, an execution framework that schedules communication and computation jointly to expand operator fusion scope by composing decoding stages such as QKV Projection, Attention, and Output Projection into a single fused kernels. Evaluations on H100 GPUs show that ClusterFusion outperforms state-of-the-art inference frameworks by $1. 61\times$ on average in end-to-end latency across different models and configurations.

PDF Details

ICRA Conference 2025 Conference Paper

Learning to Predict the Future from Monocular Vision for Efficient Human-Aware Navigation

Yushuang Huang
Hao Jiang
Zihan Liu
Wanli Ouyang
Zhaoqi Wang

Human-aware navigation (HAN) aims to build autonomous agents that robustly and naturally navigate in human-centered environments. Due to the complex and dynamic nature of this task, existing approaches typically rely on sophisticated pipelines that separately process perception and decision-making to solve it. In this work, we propose an Obstruction Distance Vector based End-to-End Model (ODVEEM), using monocular vision for navigation around humans. The Obstruction Distance Vector (ODV) is an intermediate representation in our model, leveraged to describe the Obstruction Distance to the first future collision in all possible directions in the horizontal field of view. As ODV cannot be calculated directly in the real world, we design a neural network for ODV estimation, formulating it as a classification problem with auxiliary proxy tasks, which play a key role in effectively predicting the implicit future motion of nearby humans. Taking advantage of ODV, ODVEEM supervised by human behavioral heuristics is employed to guide the agent to reach a goal efficiently and avoid potential collisions. Several challenging experiments show our method's substantial improvement over a number of baseline methods, attaining solid performance with zero-shot transfer to unseen simulated and real-world environments.

Details

IROS Conference 2025 Conference Paper

Learning-Based Passive Fault-Tolerant Control of a Quadrotor with Rotor Failure

Jiehao Chen
Kaidong Zhao
Zihan Liu
YanJie Li
Yunjiang Lou

This paper proposes a learning-based passive fault-tolerant control (PFTC) method for quadrotor capable of handling arbitrary single-rotor failures, including conditions ranging from fault-free to complete rotor failure, without requiring any rotor fault information or controller switching. Unlike existing methods that treat rotor faults as disturbances and rely on a single controller for multiple fault scenarios, our approach introduces a novel Selector-Controller network structure. This architecture integrates fault detection module and the controller into a unified policy network, effectively combining the adaptability to multiple fault scenarios of PFTC with the superior control performance of active fault-tolerant control (AFTC). To optimize performance, the policy network is trained using a hybrid framework that synergizes reinforcement learning (RL), behavior cloning (BC), and supervised learning with fault information. Extensive simulations and real-world experiments validate the proposed method, demonstrating significant improvements in fault response speed and position tracking performance compared to state-of-the-art PFTC and AFTC approaches. Video and code will be available at https://github.com/HITSZcjh/uav_ftc.

Details

ICML Conference 2025 Conference Paper

SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation

Zihan Liu
Shuangrui Ding
Zhixiong Zhang
Xiaoyi Dong
Pan Zhang 0001
Yuhang Zang
Yuhang Cao
Dahua Lin

Text-to-song generation, the task of creating vocals and accompaniment from textual inputs, poses significant challenges due to domain complexity and data scarcity. Existing approaches often employ multi-stage generation procedures, leading to cumbersome training and inference pipelines, as well as suboptimal overall generation quality due to error accumulation across stages. In this paper, we propose SongGen, a fully open-source, single-stage auto-regressive transformer designed for controllable song generation. The proposed model facilitates fine-grained control over diverse musical attributes, including lyrics and textual descriptions of instrumentation, genre, mood, and timbre, while also offering an optional three-second reference clip for voice cloning. Within a unified auto-regressive framework, SongGen supports two output modes: mixed mode, which generates a mixture of vocals and accompaniment directly, and dual-track mode, which synthesizes them separately for greater flexibility in downstream applications. We explore diverse token pattern strategies for each mode, leading to notable improvements and valuable insights. Furthermore, we design an automated data preprocessing pipeline with effective quality control. To foster community engagement and future research, we will release our model weights, training code, annotated data, and preprocessing pipeline. The code is available at https: //github. com/LiuZH-19/SongGen.

Details

NeurIPS Conference 2025 Conference Paper

Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding

Yue Guan
Changming Yu
Shihan Fang
Weiming Hu
Zaifeng Pan
Zheng Wang
Zihan Liu
Yangjie Zhou

Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch between dynamic speculation and static runtime assumptions. We present Yggdrasil, a co-designed system that enables latency-optimal speculative decoding through context-aware tree drafting and compiler-friendly execution. Yggdrasil introduces an equal-growth tree structure for static graph compatibility, a latency-aware optimization objective for draft selection, and stage-based scheduling to reduce overhead. Yggdrasil supports unmodified LLMs and achieves up to $3. 98\times$ speedup over state-of-the-art baselines across multiple hardware setups.

PDF Details

IJCAI Conference 2024 Conference Paper

An NCDE-based Framework for Universal Representation Learning of Time Series

Zihan Liu
Bowen Du
Junchen Ye
Xianqing Wen
Leilei Sun

Exploiting self-supervised learning (SSL) to extract the universal representations of time series could not only capture the natural properties of time series but also offer huge help to the downstream tasks. Nevertheless, existing time series representation learning (TSRL) methods face challenges in attaining universality. Indeed, existing methods relying solely on one SSL strategy (either contrastive learning (CL) or generative) often fall short in capturing rich semantic information for various downstream tasks. Moreover, time series exhibit diverse distributions and inherent characteristics, particularly with the common occurrence of missing values, posing a notable challenge for existing backbones in effectively handling such diverse time series data. To bridge these gaps, we propose CTRL, a framework for universal TSRL. For the first time, we employ Neural Controlled Differential Equation (NCDE) as the backbone for TSRL, which captures the continuous processes and exhibits robustness to missing data. Additionally, a dual-task SSL strategy, integrating both reconstruction and contrasting tasks, is proposed to enrich the semantic information of the learned representations. Furthermore, novel hard negative construction and false negative elimination mechanisms are proposed to improve sampling efficiency and reduce sampling bias in CL. Finally, extensive experiments demonstrate the superiority of CTRL in forecasting, classification, and imputation tasks, particularly its outstanding robustness to missing data.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

ChatQA: Surpassing GPT-4 on Conversational QA and RAG

Zihan Liu
Wei Ping
Rajarshi Roy
Peng Xu
Chankyu Lee
Mohammad Shoeybi
Bryan Catanzaro

In this work, we introduce ChatQA, a suite of models that outperform GPT-4 on retrieval-augmented generation (RAG) and conversational question answering (QA). To enhance generation, we propose a two-stage instruction tuning method that significantly boosts the performance of RAG. For effective retrieval, we introduce a dense retriever optimized for conversational QA, which yields results comparable to the alternative state-of-the-art query rewriting models, while substantially reducing deployment costs. We also present the ChatRAG Bench, which encompasses ten datasets covering comprehensive evaluations on RAG, table-related QA, arithmetic calculations, and scenarios involving unanswerable questions. Our ChatQA-1. 0-70B (score: 54. 14), built on Llama2, a weaker foundation model than GPT-4, can slightly outperform GPT-4-0613 (score: 53. 90) and GPT-4-Turbo-2024-04-09 (score: 54. 03) on the ChatRAG Bench, without relying on any synthetic data from OpenAI GPT models. Notably, Llama3-ChatQA-1. 5-70B model surpasses the accuracy of GPT-4-Turbo-2024-04-09 by a margin. These results demonstrate the exceptional quality of the proposed ChatQA recipe. To advance research in this field, we open-sourced the model weights, instruction tuning data, ChatRAG Bench, and retriever for the community.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Protein 3D Graph Structure Learning for Robust Structure-Based Protein Property Prediction

Yufei Huang
Siyuan Li
Lirong Wu
Jin Su
Haitao Lin
Odin Zhang
Zihan Liu
Zhangyang Gao

Protein structure-based property prediction has emerged as a promising approach for various biological tasks, such as protein function prediction and sub-cellular location estimation. The existing methods highly rely on experimental protein structure data and fail in scenarios where these data are unavailable. Predicted protein structures from AI tools (e.g., AlphaFold2) were utilized as alternatives. However, we observed that current practices, which simply employ accurately predicted structures during inference, suffer from notable degradation in prediction accuracy. While similar phenomena have been extensively studied in general fields (e.g., Computer Vision) as model robustness, their impact on protein property prediction remains unexplored. In this paper, we first investigate the reason behind the performance decrease when utilizing predicted structures, attributing it to the structure embedding bias from the perspective of structure representation learning. To study this problem, we identify a Protein 3D Graph Structure Learning Problem for Robust Protein Property Prediction (PGSL-RP3), collect benchmark datasets, and present a protein Structure embedding Alignment Optimization framework (SAO) to mitigate the problem of structure embedding bias between the predicted and experimental protein structures. Extensive experiments have shown that our framework is model-agnostic and effective in improving the property prediction of both predicted structures and experimental structures.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs

Yue Yu
Wei Ping
Zihan Liu
Boxin Wang
Jiaxuan You
Chao Zhang
Mohammad Shoeybi
Bryan Catanzaro

Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). In this work, we propose a novel method called RankRAG, which instruction-tunes a single LLM for both context ranking and answer generation in RAG. In particular, the instruction-tuned LLMs work surprisingly well by adding a small fraction of ranking data into the training blend, and outperform existing expert ranking models, including the same LLM exclusively fine-tuned on a large amount of ranking data. For generation, we compare our model with many strong baselines, including ChatQA-1. 5, an open-sourced model with the state-of-the-art performance on RAG benchmarks. Specifically, our Llama3-RankRAG-8B and Llama3-RankRAG-70B significantly outperform Llama3-ChatQA-1. 5-8B and Llama3-ChatQA-1. 5-70B, respectively, on nine general knowledge-intensive benchmarks for RAG. In addition, it also performs comparably to GPT-4 on five RAG benchmarks in the biomedical domain without instruction fine-tuning on biomedical data, demonstrating its superb capability for generalization to new domains.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias

Zihan Liu
Yun Luo
Lirong Wu
Zicheng Liu
Stan Z. Li

It has become cognitive inertia to employ cross-entropy loss function in classification related tasks. In the untargeted attacks on graph structure, the gradients derived from the attack objective are the attacker's basis for evaluating a perturbation scheme. Previous methods use negative cross-entropy loss as the attack objective in attacking node-level classification models. However, the suitability of the cross-entropy function for constructing the untargeted attack objective has yet been discussed in previous works. This paper argues about the previous unreasonable attack objective from the perspective of budget allocation. We demonstrate theoretically and empirically that negative cross-entropy tends to produce more significant gradients from nodes with lower confidence in the labeled classes, even if the predicted classes of these nodes have been misled. To free up these inefficient attack budgets, we propose a simple attack model for untargeted attacks on graph structure based on a novel attack objective which generates unweighted gradients on graph structures that are not affected by the node confidence. By conducting experiments in gray-box poisoning attack scenarios, we demonstrate that a reasonable budget allocation can significantly improve the effectiveness of gradient-based edge perturbations without any extra hyper-parameter.

PDF Details

AAAI Conference 2021 Conference Paper

CrossNER: Evaluating Cross-Domain Named Entity Recognition

Zihan Liu
Yan Xu
Tiezheng Yu
Wenliang Dai
Ziwei Ji
Samuel Cahyawijaya
Andrea Madotto
Pascale Fung

Cross-domain named entity recognition (NER) models are able to cope with the scarcity issue of NER samples in target domains. However, most of the existing NER benchmarks lack domain-specialized entity types or do not focus on a certain domain, leading to a less effective cross-domain evaluation. To address these obstacles, we introduce a cross-domain NER dataset (CrossNER), a fully-labeled collection of NER data spanning over five diverse domains with specialized entity categories for different domains. Additionally, we also provide a domain-related corpus since using it to continue pre-training language models (domain-adaptive pre-training) is effective for the domain adaptation. We then conduct comprehensive experiments to explore the effectiveness of leveraging different levels of the domain corpus and pre-training strategies to do domain-adaptive pre-training for the crossdomain task. Results show that focusing on the fractional corpus containing domain-specialized entities and utilizing a more challenging pre-training strategy in domain-adaptive pre-training are beneficial for the NER domain adaptation, and our proposed method can consistently outperform existing cross-domain NER baselines. Nevertheless, experiments also illustrate the challenge of this cross-domain NER task. We hope that our dataset and baselines will catalyze research in the NER domain adaptation area. The code and data are available at https: //github. com/zliucr/CrossNER.

PDF Details

AAAI Conference 2021 Conference Paper

On the Importance of Word Order Information in Cross-lingual Sequence Labeling

Zihan Liu
Genta I Winata
Samuel Cahyawijaya
Andrea Madotto
Zhaojiang Lin
Pascale Fung

Cross-lingual models trained on source language tasks possess the capability to transfer to target languages directly. However, since word order variances generally exist in different languages, cross-lingual models that overfit into the word order of the source language could have sub-optimal performance in target languages. In this paper, we hypothesize that reducing the word order information fitted into the models can improve the adaptation performance in target languages. To verify this hypothesis, we introduce several methods to make models encode less word order information of the source language and test them based on cross-lingual word embeddings and the pre-trained multilingual model. Experimental results on three sequence labeling tasks (i. e. , partof-speech tagging, named entity recognition, and slot filling tasks) show that reducing word order information injected into the model can achieve better zero-shot cross-lingual performance. Further analysis illustrates that fitting excessive or insufficient word order information into the model results in inferior cross-lingual performance. Moreover, our proposed methods can also be applied to strong cross-lingual models and further improve their performance.

PDF Details

AAAI Conference 2020 Conference Paper

Attention-Informed Mixed-Language Training for Zero-Shot Cross-Lingual Task-Oriented Dialogue Systems

Zihan Liu
Genta Indra Winata
Zhaojiang Lin
Peng Xu
Pascale Fung

Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of highquality data. In order to circumvent the expensive and timeconsuming data collection, we introduce Attention-Informed Mixed-Language Training (MLT), a novel zero-shot adaptation method for cross-lingual task-oriented dialogue systems. It leverages very few task-related parallel word pairs to generate code-switching sentences for learning the interlingual semantics across languages. Instead of manually selecting the word pairs, we propose to extract source words based on the scores computed by the attention layer of a trained English task-related model and then generate word pairs using existing bilingual dictionaries. Furthermore, intensive experiments with different cross-lingual embeddings demonstrate the effectiveness of our approach. Finally, with very few word pairs, our model achieves signiﬁcant zero-shot adaptation performance improvements in both cross-lingual dialogue state tracking and natural language understanding (i. e. , intent detection and slot ﬁlling) tasks compared to the current state-of-the-art approaches, which utilize a much larger amount of bilingual data.

PDF Details

AAAI Conference 2020 System Paper

CAiRE: An End-to-End Empathetic Chatbot

Zhaojiang Lin
Peng Xu
Genta Indra Winata
Farhad Bin Siddique
Zihan Liu
Jamin Shin
Pascale Fung

We present CAiRE, an end-to-end generative empathetic chatbot designed to recognize user emotions and respond in an empathetic manner. Our system adapts the Generative Pretrained Transformer (GPT) to empathetic response generation task via transfer learning. CAiRE is built primarily to focus on empathy integration in fully data-driven generative dialogue systems. We create a web-based user interface which allows multiple users to asynchronously chat with CAiRE. CAiRE also collects user feedback and continues to improve its response quality by discarding undesirable generations via active learning and negative training.

PDF Details