papers

Publications (199)

cond-mat.mtrl-sci2015

Thermal Oxidation of WSe2 Nano-sheets Adhered on SiO2/Si Substrates

Yingnan Liu, Cheng Tan, Harry Chou +11

Due to the drastically different intralayer versus interlayer bonding strengths, the mechanical, thermal, and electrical properties of two-dimensional (2D) materials are highly ani…

cond-mat.mes-hall2019

Antisymmetric magnetoresistance in van der Waals Fe3GeTe2/graphite/Fe3GeTe2 tri-layer heterostructures

Sultan Albarakati, Cheng Tan, Zhong-Jia Chen +15

Van der Waals (vdW) ferromagnetic materials are rapidly establishing themselves as effective building blocks for next generation spintronic devices. When layered with non-magnetic…

cs.AR2026

MACO: A Multi-Agent LLM Framework for Automated CGRA Hardware/Software Co-Design

Zesong Jiang, Yuqi Sun, Qing Zhong +4

Designing optimal Coarse-Grained Reconfigurable Arrays (CGRAs) requires navigating a vast, interdependent hardware/software space bottlenecked by costly manual iteration. We presen…

cs.CV2024

Masked Modeling for Self-supervised Representation Learning on Vision and Beyond

Siyuan Li, Luyuan Zhang, Zedong Wang +8

As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and…

cond-mat.mtrl-sci2020

Gate-controlled magnetic phase transition in a van der Waals magnet FeGeTe

Cheng Tan, Wen-Qiang Xie, Guolin Zheng +12

Magnetic van der Waals (vdW) materials, including ferromagnets (FM) and antiferromagnets (AFM), have given access to the investigation of magnetism in two-dimensional (2D) limit an…

cs.DB2020

Detecting Incorrect Behavior of Cloud Databases as an Outsider

Cheng Tan, Changgeng Zhao, Shuai Mu +1

Cloud DBs offer strong properties, including serializability, sometimes called the gold standard database correctness property. But cloud DBs are complicated black boxes, running i…

cs.SE2026

Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora

Chenkai Pan, Xinglong Xu, Yuhang Xu +6

Reliably transferring specialized human knowledge from text into large language models remains a fundamental challenge in artificial intelligence. Fine-tuning on domain corpora has…

cs.AI2026

GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models

Jingxuan Wei, Caijun Jia, Xi Bai +7

The advent of Unified Multimodal Models (UMMs) signals a paradigm shift in artificial intelligence, moving from passive perception to active, cross-modal generation. Despite their…

q-bio.BM2025

PFMBench: Protein Foundation Model Benchmark

Zhangyang Gao, Hao Wang, Cheng Tan +6

This study investigates the current landscape and future directions of protein foundation model research. While recent advancements have transformed protein science and engineering…

cs.LG2023

Harnessing Hard Mixed Samples with Decoupled Regularizer

Zicheng Liu, Siyuan Li, Ge Wang +3

Mixup is an efficient data augmentation approach that improves the generalization of neural networks by smoothing the decision boundary with mixed data. Recently, dynamic mixup met…

cond-mat.str-el2018

Anomalous quantum-critical spin dynamics in YFe2Al10

Kevin Huang, Cheng Tan, Jian Zhang +8

We report results of a muon spin relaxation (SR) study of YFeAl, a quasi-2D nearly-ferromagnetic metal in which unconventional quantum critical behavior is observed.…

cs.MM2026

Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring

Dongxu Zhang, Yiding Sun, Cheng Tan +4

While Chain-of-Thought (CoT) reasoning significantly enhances the performance of Multimodal Large Language Models (MLLMs), its autoregressive nature incurs prohibitive latency cons…

cond-mat.supr-con2023

Superconducting Properties of La(CuNi_x)AsO: A SR Study

Qiong Wu, Kaiwen Chen, Zihao Zhu +8

We report the results of muon spin rotation and relaxation (SR) measurements on the recently discovered layered Cu-based superconducting material LaCuNi$_{x}…

cs.AI2026

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control

Jingxuan Wei, Xi Bai, Shan Liu +8

Large vision-language models have significantly advanced GUI agents, enabling executable interaction across web, mobile, and desktop interfaces. Yet these gains largely rely on a f…

cs.LG2026

RiboSphere: Learning Unified and Efficient Representations of RNA Structures

Zhou Zhang, Hanqun Cao, Cheng Tan +3

Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimentally determined 3D structures a…

cs.CR2019

Taming Distrust in the Decentralized Internet with PIXIU

Yubin Xia, Qingyuan Liu, Cheng Tan +4

Decentralized Internet is booming. People are fascinated by its promise that users can truly own their data. However, in a decentralized Internet, completing a task usually involve…

q-bio.BM2025

ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search

Mengdi Liu, Xiaoxue Cheng, Zhangyang Gao +4

Designing protein sequences that fold into a target 3D structure, known as protein inverse folding, is a fundamental challenge in protein engineering. While recent deep learning me…

q-bio.QM2022

AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB

Zhangyang Gao, Cheng Tan, Stan Z. Li

While DeepMind has tentatively solved protein folding, its inverse problem -- protein design which predicts protein sequences from their 3D structures -- still faces significant ch…

cs.AR2024

Enhancing CGRA Efficiency Through Aligned Compute and Communication Provisioning

Zhaoying Li, Pranav Dangi, Chenyang Yin +5

Coarse-grained Reconfigurable Arrays (CGRAs) are domain-agnostic accelerators that enhance the energy efficiency of resource-constrained edge devices. The CGRA landscape is diverse…

cs.AI2023

A Survey on Generative Diffusion Model

Hanqun Cao, Cheng Tan, Zhangyang Gao +4

Deep generative models have unlocked another profound realm of human creativity. By capturing and generalizing patterns within data, we have entered the epoch of all-encompassing A…

cs.CL2022

Leveraging Graph-based Cross-modal Information Fusion for Neural Sign Language Translation

Jiangbin Zheng, Siyuan Li, Cheng Tan +3

Sign Language (SL), as the mother tongue of the deaf community, is a special visual language that most hearing people cannot understand. In recent years, neural Sign Language Trans…

q-bio.BM2024

PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction

Lirong Wu, Yufei Huang, Cheng Tan +5

Compound-Protein Interaction (CPI) prediction aims to predict the pattern and strength of compound-protein interactions for rational drug discovery. Existing deep learning-based me…

cond-mat.supr-con2018

Nodal superconductivity coexists with low-moment static magnetism in single-crystalline tetragonal FeS: A muon spin relaxation and rotation study

Cheng Tan, Tianping Ying, Zhaofeng Ding +8

We report muon spin relaxation and rotation (SR) measurements on hydrothermally-grown single crystals of the tetragonal superconductor~FeS, which help to clarify the controvers…

cond-mat.mes-hall2016

Tunable Ultrafast Thermal Relaxation in Graphene Measured by Continuous-Wave Photomixing

M. Mehdi Jadidi, Ryan J. Suess, Cheng Tan +9

Hot electron effects in graphene are significant because of graphene's small electronic heat capacity and weak electron-phonon coupling, yet the dynamics and cooling mechanisms of…

cs.DB2024

From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing

Jingxuan Wei, Cheng Tan, Qi Chen +6

We introduce the task of text-to-diagram generation, which focuses on creating structured visual representations directly from textual descriptions. Existing approaches in text-to-…

cs.CV2025

MogaNet: Multi-order Gated Aggregation Network

Siyuan Li, Zedong Wang, Zicheng Liu +6

By contextualizing the kernel as global as possible, Modern ConvNets have shown great potential in computer vision tasks. However, recent progress on multi-order game-theoretic int…

cs.CR2024

A Sharded Blockchain-Based Secure Federated Learning Framework for LEO Satellite Networks

Wenbo Wu, Cheng Tan, Kangcheng Yang +3

Low Earth Orbit (LEO) satellite networks are increasingly essential for space-based artificial intelligence (AI) applications. However, as commercial use expands, LEO satellite net…

cs.AI2023

Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework

Jingxuan Wei, Cheng Tan, Zhangyang Gao +5

Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks. While t…

cs.IR2026

PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams

Fuqiang Wang, Song Tan, Zheng Guo +8

Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which i…

q-bio.BM2023

MotifRetro: Exploring the Combinability-Consistency Trade-offs in retrosynthesis via Dynamic Motif Editing

Zhangyang Gao, Xingran Chen, Cheng Tan +1

Is there a unified framework for graph-based retrosynthesis prediction? Through analysis of full-, semi-, and non-template retrosynthesis methods, we discovered that they strive to…

q-bio.BM2024

Advances of Deep Learning in Protein Science: A Comprehensive Survey

Bozhen Hu, Cheng Tan, Lirong Wu +7

Protein representation learning plays a crucial role in understanding the structure and function of proteins, which are essential biomolecules involved in various biological proces…

cs.CE2025

Learning the PTM Code through a Coarse-to-Fine, Mechanism-Aware Framework

Jingjie Zhang, Hanqun Cao, Zijun Gao +8

Post-translational modifications (PTMs) form a combinatorial "code" that regulates protein function, yet deciphering this code - linking modified sites to their catalytic enzymes -…

cs.AI2024

UniIF: Unified Molecule Inverse Folding

Zhangyang Gao, Jue Wang, Cheng Tan +5

Molecule inverse folding has been a long-standing challenge in chemistry and biology, with the potential to revolutionize drug discovery and material science. Despite specified mod…

cs.LG2023

Dropout Attacks

Andrew Yuan, Alina Oprea, Cheng Tan

Dropout is a common operator in deep learning, aiming to prevent overfitting by randomly dropping neurons during training. This paper introduces a new family of poisoning attacks a…

cond-mat.str-el2020

Evidence for the topological order in a kagome antiferromagnet

Yuan Wei, Zili Feng, Wiebke Lohstroh +19

A Z2 quantum spin liquid hosts one of the simplest topological orders and exhibits many exotic properties due to long-range quantum entanglements. Its elementary excitations are an…

cs.AI2026

AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories

Xue Xia, Chengkai Yao, Mingyu Tsoi +10

Systematic ablations are essential to attribute performance gains in AI Virtual Cells, yet they are rarely performed because biological repositories are under-standardized and tigh…

cond-mat.mes-hall2021

Dual-gated graphene devices for near-field nano-imaging

Sai S. Sunku, Dorri Halbertal, Rebecca Engelke +11

Graphene-based heterostructures display a variety of phenomena that are strongly tunable by electrostatic local gates. Monolayer graphene (MLG) exhibits tunable surface plasmon pol…

cs.IT2018

On Stability Condition of Wireless Networked Control Systems under Joint Design of Control Policy and Network Scheduling Policy

Lei Deng, Cheng Tan, Wing Shing Wong

In this paper, we study a wireless networked control system (WNCS) with sub-systems sharing a common wireless channel. Each sub-system consists of a plant and a controlle…

cs.AI2026

SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models

Dongxu Zhang, Yiding Sun, Zihao Guo +5

Reasoning failures in large language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may…

cs.AI2026

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

Xinlei Yu, Zhangquan Chen, Yongbo He +36

Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an inc…

cs.AI2026

The Trinity of Consistency as a Defining Principle for General World Models

Jingxuan Wei, Siyuan Li, Yuhang Xu +21

The construction of World Models capable of learning, simulating, and reasoning about objective physical laws constitutes a foundational challenge in the pursuit of Artificial Gene…

q-bio.BM2024

RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design

Cheng Tan, Yijie Zhang, Zhangyang Gao +4

While artificial intelligence has made remarkable strides in revealing the relationship between biological macromolecules' primary sequence and tertiary structure, designing RNA se…

cond-mat.supr-con2019

Broken time-reversal symmetry in superconducting PrLaPtGe

Jian Zhang, Zhaofeng Ding, Kevin Huang +5

The superconducting state of the filled skutterudite alloy series PrLaPtGe has been systematically studied by specific heat, zero-field muon spin relaxat…

cs.LG2023

CONVERT:Contrastive Graph Clustering with Reliable Augmentation

Xihong Yang, Cheng Tan, Yue Liu +7

Contrastive graph node clustering via learnable data augmentation is a hot research spot in the field of unsupervised graph learning. The existing methods learn the sampling distri…

cs.LG2024

Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting

Lirong Wu, Haitao Lin, Guojiang Zhao +2

Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). However, most existing GNNs are based on message passing to perform fea…

cond-mat.mes-hall2025

Interface-Controlled Antiferromagnetic Tunnel Junctions based on a metallic van der Waals A-type Antiferromagnet

Wei-Min Zhao, Yi-Lun Liu, Liu Yang +11

Magnetic tunnel junctions (MTJs) are crucial components in high-performance spintronic devices. Traditional MTJs rely on ferromagnetic (FM) materials but significant improvements i…

cs.LG2026

Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding

Yingxuan Zhuang, Jingxiao Yang, Miao Pan +7

MLLMs frequently hallucinate objects inconsistent with visual inputs. This issue is typically attributed to the over-reliance on language priors, which can override the visual cont…

physics.chem-ph2025

Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules

Xiangru Wang, Zekun Jiang, Heng Yang +4

Molecular property prediction is fundamental to chemical engineering applications such as solvent screening. We present Socrates-Mol, a framework that transforms language models in…

cs.CV2026

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging

Luyuan Zhang, Siyuan Li, Zedong Wang +7

Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconstruction but suffer from dens…

cs.DC2021

Serving DNN Models with Multi-Instance GPUs: A Case of the Reconfigurable Machine Scheduling Problem

Cheng Tan, Zhichao Li, Jian Zhang +5

Multi-Instance GPU (MIG) is a new feature introduced by NVIDIA A100 GPUs that partitions one physical GPU into multiple GPU instances. With MIG, A100 can be the most cost-efficient…

cond-mat.mes-hall2024

Electrically tunable, rapid spin-orbit torque induced modulation of colossal magnetoresistance in MnSiTe nanoflakes

Cheng Tan, Mingxun Deng, Yuanjun Yang +13

As a quasi-layered ferrimagnetic material, MnSiTe nanoflakes exhibit magnetoresistance behaviour that is fundamentally different from their bulk crystal counterparts. T…

cond-mat.mtrl-sci2020

Gate-Tuned Interlayer Coupling in van der Waals Ferromagnet FeGeTe Nanoflakes

Guolin Zheng, Wen-Qiang Xie, Sultan Albarakati +11

The weak interlayer coupling in van der Waals (vdW) magnets has confined their application to two dimensional (2D) spintronic devices. Here, we demonstrate that the interlayer coup…

math.OC2018

Integrated Stabilization Policy over a Software Defined Network

Cheng Tan, Wing Shing Wong, Huanshui Zhang

In this paper, we mainly investigate an integrated system operating under a software defined network (SDN) protocol. SDN is a new networking paradigm in which network intelligence…

physics.optics2026

Broadband Continuous Frequency Tuning in Non-Hermitian Laser Arrays Enabled by Mode-Switching Boundary Topology

Chuanfeng Yan, Cheng Tan, Kai Wang +6

Broadband and continuous frequency tuning is central to the versatility of semiconductor lasers, yet existing approaches typically rely on external moving components, limiting scal…

cs.CV2025

USTEP: Spatio-Temporal Predictive Learning under A Unified View

Cheng Tan, Jue Wang, Zhangyang Gao +2

Spatio-temporal predictive learning plays a crucial role in self-supervised learning, with wide-ranging applications across a diverse range of fields. Previous approaches for tempo…

cond-mat.str-el2020

Persistent spin dynamics and absence of spin freezing in the - phase diagram of the 2D triangular antiferromagnet YbMgGaO

Zhaofeng Ding, Zihao Zhu, Jian Zhang +4

We report results of muon spin relaxation and rotation (SR) experiments on the spin-liquid candidate~YbMgGaO. No static magnetism per Yb ion, ordered…

cond-mat.str-el2022

Intrinsic new properties of a quantum spin liquid

Yanxing Yang, Xin Li, Cheng Tan +10

Quantum fluctuations are expected to lead to highly entangled spin-liquid states in certain two-dimensional spin-1/2 compounds. We have synthesized and measured thermodynamic prope…

cs.LG2024

A Graph is Worth Words: Euclideanizing Graph using Pure Transformer

Zhangyang Gao, Daize Dong, Cheng Tan +3

Can we model Non-Euclidean graphs as pure language or even Euclidean vectors while retaining their inherent information? The Non-Euclidean property have posed a long term challenge…

cond-mat.mtrl-sci2024

Massive Dirac Fermions and Strong Shubnikov-de Haas Oscillations in Topological Insulator Sm,Fe:Bi2Se3 Single Crystals

Weiyao Zhao, Chi Xuan Trang, Qile Li +9

Topological insulators (TIs) are emergent materials with unique band structure, which allow the study of quantum effect in solids, as well as contribute to high performance quantum…

math.OC2026

Integrated Learning and Robust Optimization

Cheng Tan, Yuchen Mao, Shuming Wang +1

Many operational decisions require solving a linear program whose cost vector is unknown at decision time and must be predicted from contextual information. Because prediction and…

cs.LG2023

Personalized Reward Learning with Interaction-Grounded Learning (IGL)

Jessica Maghakian, Paul Mineiro, Kishan Panaganti +3

In an era of countless content offerings, recommender systems alleviate information overload by providing users with personalized content suggestions. Due to the scarcity of explic…

q-bio.BM2023

Generative De Novo Protein Design with Global Context

Cheng Tan, Zhangyang Gao, Jun Xia +2

The linear sequence of amino acids determines protein structure and function. Protein design, known as the inverse of protein structure prediction, aims to obtain a novel protein s…

cond-mat.mtrl-sci2016

Laser-assisted Oxidation of Multi-layer Tungsten Diselenide Nanosheets

Cheng Tan, Yingnan Liu, Harry Chou +4

We report the structural and electrical characterization of tungsten oxides formed by illuminating multi-layer tungsten diselenide (WSe2) nanosheets with an intense laser beam in t…

cs.AI2026

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

Jinhang Xu, Qiyuan Zhu, Yujun Wu +11

LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automation for whom? Researchers ope…

cs.LG2024

SemiReward: A General Reward Model for Semi-supervised Learning

Siyuan Li, Weiyang Jin, Zedong Wang +4

Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish…

cond-mat.mes-hall2016

Nanosecond spin relaxation times in single layer graphene spin valves with hexagonal boron nitride tunnel barriers

Simranjeet Singh, Jyoti Katoch, Jinsong Xu +5

We present an experimental study of spin transport in single layer graphene using atomic sheets of hexagonal boron nitride (h-BN) as a tunnel barrier for spin injection. While h-BN…

cs.LG2026

Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation Estimation

Changxi Chi, Jun Xia, Yufei Huang +9

Estimating single-cell responses across various perturbations facilitates the identification of key genes and enhances drug screening, significantly boosting experimental efficienc…

cs.CE2023

VQPL: Vector Quantized Protein Language

Zhangyang Gao, Cheng Tan, Stan Z. Li

Is there a foreign language describing protein sequences and structures simultaneously? Protein structures, represented by continuous 3D points, have long posed a challenge due to…

cs.AI2026

Dual Latent Memory for Visual Multi-agent System

Xinlei Yu, Chengming Xu, Zhangquan Chen +8

While Visual Multi-Agent Systems (VMAS) promise to enhance comprehensive abilities through inter-agent collaboration, empirical evidence reveals a counter-intuitive "scaling wall":…

cs.SI2025

Rejection or Inclusion in the Emotion-Identity Dynamics of TikTok Refugees on RedNote

Mingchen Li, Wenbo Xu, Wenqing Gu +5

This study examines cross-cultural interactions between Chinese users and self-identified "TikTok Refugees"(foreign users who migrated to RedNote after TikTok's U.S. ban). Based on…

cs.CV2025

Depth3DLane: Monocular 3D Lane Detection via Depth Prior Distillation

Dongxin Lyu, Han Huang, Cheng Tan +1

Monocular 3D lane detection is challenging due to the difficulty in capturing depth information from single-camera images. A common strategy involves transforming front-view (FV) i…

cond-mat.mes-hall2020

Determination of the spin orientation of helical electrons in monolayer WTe2

Cheng Tan, Ming-Xun Deng, Feixiang Xiang +7

Monolayer WTe2 is predicted to be a quantum spin Hall insulator (QSHI) and electron transport along its edges has been experimentally observed. However, the 'smoking gun' of QSHI,…

cond-mat.supr-con2019

Muon spin rotation and relaxation in PrNdOsSb: superconductivity and magnetism in Pr-rich alloys

P. C. Ho, D. E. MacLaughlin, M. B. Maple +9

The Pr-rich end of the alloy series PrNdOsSb has been studied using muon spin rotation and relaxation. The end compound PrOsSb is an unconventiona…

cs.AI2025

LLM/Agent-as-Data-Analyst: A Survey

Zirui Tang, Weizheng Wang, Zihang Zhou +16

Large language models (LLMs) and agent techniques have brought a fundamental shift in the functionality and development paradigm of data analysis tasks (a.k.a LLM/Agent-as-Data-Ana…

cs.AI2026

Defining AI-Native Systems: Autonomy as Revision Authority

Cheng Tan

AI has begun to write systems code: agents now synthesize, verify, and deploy system components. Despite this shift, "AI-native" remains a marketing term with no precise technical…

cs.LG2024

FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning

Sizhe Liu, Jun Xia, Lecheng Zhang +8

Molecular relational learning (MRL) is crucial for understanding the interaction behaviors between molecular pairs, a critical aspect of drug discovery and development. However, th…

cs.LG2024

Switch EMA: A Free Lunch for Better Flatness and Sharpness

Siyuan Li, Zicheng Liu, Juanxi Tian +9

Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DN…

cs.CV2025

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Siyuan Li, Luyuan Zhang, Zedong Wang +8

Masked Image Modeling (MIM) with Vector Quantization (VQ) has achieved great success in both self-supervised pre-training and image generation. However, most existing methods strug…

cs.CV2026

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement

Tingyu Li, Le Zhou, Siyuan Li +5

Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tasks. However, in comp…

cs.PL2026

NEURA: A Unified and Retargetable Compilation Framework for Coarse-Grained Reconfigurable Architectures

Shangkun Li, Jinming Ge, Diyuan Tao +6

Coarse-Grained Reconfigurable Architectures (CGRAs) are a promising and versatile accelerator platform, offering a balance between the performance and efficiency of specialized acc…

cs.LG2024

Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding

Bozhen Hu, Zelin Zang, Jun Xia +3

Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding. Most existing neural network approaches learn latent represent…

cs.CV2026

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution

Siyong Jian, Siyuan Li, Luyuan Zhang +5

Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the policy while keeping the VQ dec…

cs.LG2024

CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph

Haitao Lin, Guojiang Zhao, Odin Zhang +7

Structure-based drug design (SBDD) aims to generate potential drugs that can bind to a target protein and is greatly expedited by the aid of AI techniques in generative models. How…

cs.AI2026

Xiaomi-GUI-0 Technical Report

Wanxia Cao, Chengzhen Duan, Pei Fu +29

Graphical user interface (GUI) agents build on vision-language models to complete user tasks end-to-end in real applications through interface actions such as tapping, swiping, tex…

cs.CL2024

Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions

Cheng Tan, Dongxin Lyu, Siyuan Li +5

Large Language Models (LLMs) have demonstrated wide-ranging applications across various fields and have shown significant potential in the academic peer-review process. However, ex…

cs.AI2025

SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches

Cheng Tan, Qi Chen, Jingxuan Wei +6

Hand-drawn sketches are a natural and efficient medium for capturing and conveying ideas. Despite significant advancements in controllable natural image generation, translating fre…

cond-mat.mes-hall2024

Multi-species optically addressable spin defects in a van der Waals material

Sam C. Scholten, Priya Singh, Alexander J. Healey +11

Optically addressable spin defects hosted in two-dimensional van der Waals materials represent a new frontier for quantum technologies, promising to lead to a new class of ultrathi…

cond-mat.mtrl-sci2019

Charge-stripe order, antiferromagnetism, and spin dynamics in the cuprate-analog nickelate LaNiO

Oscar O. Bernal, Douglas E. MacLaughlin, Gerald D. Morris +7

We report a muon spin rotation (SR) study of the cuprate-analog nickelate LaNiO, which undergoes a transition at 105 K to a low-temperature phase with charge-stripe…

cs.AI2025

Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary Constructions

Jingxuan Wei, Caijun Jia, Qi Chen +6

Mathematical geometric reasoning is essential for scientific discovery and educational development, requiring precise logic and rigorous formal verification. While recent advances…

cs.LG2022

CoSP: Co-supervised pretraining of pocket and ligand

Zhangyang Gao, Cheng Tan, Lirong Wu +1

Can we inject the pocket-ligand interaction knowledge into the pre-trained model and jointly learn their chemical space? Pretraining molecules and proteins has attracted considerab…

cs.CL2025

ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference

Qi Chen, Jingxuan Wei, Zhuoya Yao +5

Understanding how scientific ideas evolve requires more than summarizing individual papers-it demands structured, cross-document reasoning over thematically related research. In th…

cs.AR2022

I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization

Tong Geng, Chunshu Wu, Yongan Zhang +6

Graph Convolutional Networks (GCNs) have drawn tremendous attention in the past three years. Compared with other deep learning modalities, high-performance hardware acceleration of…

q-bio.GN2024

VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling

Siyuan Li, Zedong Wang, Zicheng Liu +5

Similar to natural language models, pre-trained genome language models are proposed to capture the underlying intricacies within genomes with unsupervised sequence modeling. They h…

cs.LG2021

Co-learning: Learning from Noisy Labels with Self-supervision

Cheng Tan, Jun Xia, Lirong Wu +1

Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degra…

cs.DC2026

TileLoom: Automatic Dataflow Planning for Tile-Based Languages on Spatial Dataflow Accelerators

Wei Li, Zhenyu Bai, Heru Wang +6

Spatial dataflow accelerators are a promising direction for next-generation computer systems because they can reduce the memory bottlenecks of traditional von Neumann machines such…

cs.CV2023

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

Cheng Tan, Siyuan Li, Zhangyang Gao +5

Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsup…

cs.AI2024

Specification Generation for Neural Networks in Systems

Isha Chaudhary, Shuyi Lin, Cheng Tan +1

Specifications - precise mathematical representations of correct domain-specific behaviors - are crucial to guarantee the trustworthiness of computer systems. With the increasing d…

math.OC2018

Learning Based Control Policy and Regret Analysis for Online Quadratic Optimization with Asymmetric Information Structure

Cheng Tan, Wing Shing Wong

In this paper, we propose a learning approach to analyze dynamic systems with asymmetric information structure. Instead of adopting a game theoretic setting, we investigate an onli…

cond-mat.mes-hall2022

Dissipation-enabled hydrodynamic conductivity in a tunable bandgap semiconductor

Cheng Tan, Derek Y. H. Ho, Lei Wang +10

Electronic transport in the regime where carrier-carrier collisions are the dominant scattering mechanism has taken on new relevance with the advent of ultraclean two-dimensional m…

cs.CV2026

PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning

Dongxu Zhang, Yiding Sun, Pengcheng Li +12

While Multimodal Large Language Models (MLLMs) demonstrate proficiency in 2D scenes, extending their perceptual intelligence to 3D point cloud understanding remains a significant c…