Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jian Liu

Jian Liu

10 indexed papers

Recent (6 mo)
8
With code
0
Influential cites
0
Benchmarked
0

Publications per year

10
26

Top categories

ML×4Optimization and Control×2Stats ML×2AI×2Crypto×2Robotics×1Audio and Speech Processing×1Architecture×1

Frequent co-authors

Di Wu2×
Weiqiang Wang2×
Zijian Liu2×
Xiao Zhang1×
Jiaxuan Li1×
Renzhen Le1×

Research Timeline

2026
Ordering Power is Sanctioning Power: Sanction Evasion-MEV and the Limits of On-Chain Enforcement

The paper demonstrates that on public blockchains, the ability to dictate transaction order (ordering power) is the true source of sanctioning power, as block producers can extract value (SE-MEV) by prioritizing transactions that evade sanctions.

FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs

FedSpy-LLM introduces a scalable and generalizable data reconstruction attack that can extract private training data from shared gradients of large language models, even when using Parameter-Efficient Fine-Tuning (PEFT) methods.

EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents

The paper introduces EgoBench, the first interactive multimodal benchmark designed to jointly evaluate advanced AI agents' capabilities in visual perception, multi-hop reasoning, and dynamic tool usage in real-world, egocentric scenarios.

Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial Intelligence

The paper proposes HetMedAgent, a multi-agent framework, demonstrating that combining generalist LLMs with domain-specific specialist models significantly improves medical AI performance by enabling structured collaboration.

Symmetry-Aware 9D Pose Estimation with Sim(3)-Consistent Feature and Spherical Inception Convolution

The paper proposes a novel symmetry-aware, category-level method for 9D object pose estimation that accurately estimates translation and size first, followed by rotation, achieving state-of-the-art results on diverse objects.

Adam Converges in Nonsmooth Nonconvex Optimization

The paper provides a finite-time analysis of the Adam optimizer for nonsmooth nonconvex optimization, proving a convergence rate of $1/T^{2/13}$ with a randomly scaled learning rate.

COSM: A Cooperative Scheduling Framework for Concurrent PIM and CPU Execution on Mobile Devices

The paper introduces COSM, a cooperative scheduling framework to facilitate concurrent operation of Processing-in-Memory (PIM) and CPU tasks on mobile platforms, improving PIM throughput by up to 2.8x with less than 2.0% CPU performance loss.

Random Reshuffling Dominates Stochastic Gradient Descent

This paper proves that Random Reshuffling in Shuffling Stochastic Gradient Descent dominates vanilla SGD in smooth convex optimization after any finite number of epochs.

Summary of DCASE 2026 Task 5: Audio-Dependent Question Answering

This paper introduces Audio-Dependency Filtering (ADF) pipeline for Audio-Dependent Question Answering (ADQA) task in DCASE~2026, achieving top overall and sub-10B accuracy.

RL-MACRO: A Cybernetic Closed-Loop Intelligence Framework for Multimodal Adaptive Robotic Craniotomy

This paper proposes RL-MACRO, a cybernetic closed-loop intelligence framework for autonomous robotic craniotomy, which includes a CNN-LSTM observer for temperature reconstruction, an offline Implicit Q-Learning policy, and a novel dual-head Actor for coordinating cutting parameters.

Highlighted terms show continued research focus across papers

Papers

cs.ROEmpiricalRecentJul 23, 2026

RL-MACRO: A Cybernetic Closed-Loop Intelligence Framework for Multimodal Adaptive Robotic Craniotomy

Xiao Zhang, Jiaxuan Li, Renzhen Le, Di Wu +8 more

This paper proposes RL-MACRO, a cybernetic closed-loop intelligence framework for autonomous robotic craniotomy, which includes a CNN-LSTM observer for temperature reconstruction, an offline Implicit…

View →
eess.ASEmpiricalRecent
Jul 21, 2026

Summary of DCASE 2026 Task 5: Audio-Dependent Question Answering

Haolin He, Renhe Sun, Zheqi Dai, Xingjian Du +15 more

This paper introduces Audio-Dependency Filtering (ADF) pipeline for Audio-Dependent Question Answering (ADQA) task in DCASE~2026, achieving top overall and sub-10B accuracy.

View →
math.OCcs.LGstat.MLTheoreticalRecentJun 30, 2026

Random Reshuffling Dominates Stochastic Gradient Descent

Zijian Liu

This paper proves that Random Reshuffling in Shuffling Stochastic Gradient Descent dominates vanilla SGD in smooth convex optimization after any finite number of epochs.

View →
cs.ARcs.DCEmpiricalRecentJun 29, 2026

COSM: A Cooperative Scheduling Framework for Concurrent PIM and CPU Execution on Mobile Devices

Yilong Zhao, Fangxin Liu, Onur Mutlu, Mingyu Gao +3 more

The paper introduces COSM, a cooperative scheduling framework to facilitate concurrent operation of Processing-in-Memory (PIM) and CPU tasks on mobile platforms, improving PIM throughput by up to 2.8x…

View →
math.OCcs.LGstat.MLTheoreticalRecentJun 21, 2026

Adam Converges in Nonsmooth Nonconvex Optimization

Zijian Liu

The paper provides a finite-time analysis of the Adam optimizer for nonsmooth nonconvex optimization, proving a convergence rate of $1/T^{2/13}$ with a randomly scaled learning rate.

View →
cs.CVRecentJun 1, 2026

Symmetry-Aware 9D Pose Estimation with Sim(3)-Consistent Feature and Spherical Inception Convolution

Panfei Cheng, Hongshan Yu, Wenrui Chen, Xiaojun Tang +2 more

The paper proposes a novel symmetry-aware, category-level method for 9D object pose estimation that accurately estimates translation and size first, followed by rotation, achieving state-of-the-art re…

View →
cs.AIcs.CLcs.LGRecentMay 28, 2026

Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial Intelligence

Yanan Wang, Shuaicong Hu, Jian Liu, Guohui Zhou +2 more

The paper proposes HetMedAgent, a multi-agent framework, demonstrating that combining generalist LLMs with domain-specific specialist models significantly improves medical AI performance by enabling s…

View →
cs.AIRecentMay 27, 2026

EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents

Yunqi Liu, Tong Niu, Zitong Wang, Zhenlong Dai +3 more

The paper introduces EgoBench, the first interactive multimodal benchmark designed to jointly evaluate advanced AI agents' capabilities in visual perception, multi-hop reasoning, and dynamic tool usag…

View →
cs.CRcs.LGApr 7, 2026

FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs

Syed Irfan Ali Meerza, Feiyi Wang, Jian Liu

FedSpy-LLM introduces a scalable and generalizable data reconstruction attack that can extract private training data from shared gradients of large language models, even when using Parameter-Efficient…

View →
cs.CRMar 29, 2026

Ordering Power is Sanctioning Power: Sanction Evasion-MEV and the Limits of On-Chain Enforcement

Di Wu, Yuman Bai, Shoupeng Ren, Xinyu Zhang +4 more

The paper demonstrates that on public blockchains, the ability to dictate transaction order (ordering power) is the true source of sanctioning power, as block producers can extract value (SE-MEV) by p…

View →