wovepaper — the arXiv observatory

The paper presents Frontis-MA1, a 35‑billion‑parameter model trained as a meta‑evolution agent for machine learning engineering, using a new OpenMLE stack that combines operator le…

#recursive self-improvement#ai4ai#machine learning engineering#meta‑learning

cs.CV2020

Pyramid Attention Networks for Image Restoration

Yiqun Mei, Yuchen Fan, Yulun Zhang +6

cs.CL2025

A Survey of Reinforcement Learning for Large Reasoning Models

Kaiyan Zhang, Yuxin Zuo, Bingxiang He +36

cs.CV2024

MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds

Zhenggang Tang, Yuchen Fan, Dilin Wang +4

cs.CE2026

Bridging Computational Fluid Dynamics Algorithm and Physics-Informed Learning: SIMPLE-PINN for Incompressible Navier-Stokes Equations

Chang Wei, Yuchen Fan, Chin Chun Ooi +3

cs.CV2026

Reading $\neq =$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models

Heng Zhou, Ao Yu, Li Kang +5

cs.CV2022

Recurrent Video Restoration Transformer with Guided Deformable Attention

Jingyun Liang, Yuchen Fan, Xiaoyu Xiang +7

cs.CV2019

SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection

Xiaofan Zhang, Cong Hao, Haoming Lu +9

cs.CV2018

YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark

Ning Xu, Linjie Yang, Yuchen Fan +4

cs.CV2025

3D Mesh Editing using Masked LRMs

Will Gao, Dilin Wang, Yuchen Fan +6

cs.CV2025

Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds

Xiaoyu Xiang, Liat Sless Gorelik, Yuchen Fan +5

cs.DC2026

Application-Driven Architecture Exploration for Cross-Layer Heterogeneous Systems

Yuchen Fan, Minghong Sun, Jikui Ma +19

cond-mat.str-el2026

Phase diagram and Ashkin-Teller universality in the classical square-lattice Heisenberg-compass model

Yuchen Fan

cs.RO2026

SinD 2.0: A Multi-City UAV Dataset with Semantic Risk Annotations for SOTIF-Oriented Safety Validation at Signalized Intersections

Yunwei Li, Shengjie Fu, Chunrong Chen +13

cs.CV2025

WorldGen: From Text to Traversable and Interactive 3D Worlds

Dilin Wang, Hyunyoung Jung, Tom Monnier +22

cs.GR2026

AssetGen: Deployable 3D Asset Generation at Interactive Speed

Dilin Wang, Xiaoyu Xiang, Kihyuk Sohn +14

math.DS2019

A Better Upper Bound of Hausdorff Measure of the Cartesian Product of the Middle Third Cantor Set with Itself Compare to Others'

Yuchen Fan

cs.CL2025

LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge

Heng Zhou, Ao Yu, Yuchen Fan +10

cs.CL2024

Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models

Yantao Liu, Zijun Yao, Xin Lv +5

cs.CV2024

WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians

Dmytro Kotovenko, Olga Grebenkova, Nikolaos Sarafianos +8

cs.CV2019

Scale-wise Convolution for Image Restoration

Yuchen Fan, Jiahui Yu, Ding Liu +1

cond-mat.str-el2023

Emergent criticality in fully frustrated quantum magnets

Yuchen Fan, Ning Xi, Changle Liu +2

cs.LG2026

How Far Can Unsupervised RLVR Scale LLM Training?

Bingxiang He, Yuxin Zuo, Zeyuan Liu +18

cs.CV2024

LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation

Henghui Ding, Lingyi Hong, Chang Liu +30

cs.CV2018

YouTube-VOS: Sequence-to-Sequence Video Object Segmentation

Ning Xu, Linjie Yang, Yuchen Fan +6

cs.CE2026

FFV-PINN: A Fast Physics-Informed Neural Network with Simplified Finite Volume Discretization and Residual Correction

Chang Wei, Yuchen Fan, Jian Cheng Wong +3

cs.CV2026

Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion

Zhenggang Tang, Yuehao Wang, Yuchen Fan +9

cs.CV2018

Wide Activation for Efficient and Accurate Image Super-Resolution

Jiahui Yu, Yuchen Fan, Jianchao Yang +4

eess.IV2025

Training Neural Networks on RAW and HDR Images for Restoration Tasks

Andrew Yanzhe Ke, Lei Luo, Xiaoyu Xiang +4

cs.LG2025

Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models

Xingtai Lv, Youbang Sun, Kaiyan Zhang +8

cs.CL2024

BoRA: Bi-dimensional Weight-Decomposed Low-Rank Adaptation

Qiushi Wang, Yuchen Fan, Junwei Bao +2

cs.AI2025

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization

Ermo Hua, Che Jiang, Xingtai Lv +7

cs.CV2018

Non-Local Recurrent Network for Image Restoration

Ding Liu, Bihan Wen, Yuchen Fan +2

cs.CV2019

Video Instance Segmentation

Linjie Yang, Yuchen Fan, Ning Xu

cond-mat.str-el2022

Fluctuation-induced first order phase transitions in Kitaev-like $d^{4}$ honeycomb magnet

Yuchen Fan, Yuan Wan

cs.CL2024

Evaluating Generative Language Models in Information Extraction as Subjective Question Correction

Yuchen Fan, Yantao Liu, Zijun Yao +3

cs.CL2026

LFQA-E: Carefully Benchmarking Long-form QA Evaluation

Yuchen Fan, Chen Lin, Xin Zhong +11

cs.CL2024

Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models

Yuchen Fan, Yuzhong Hong, Qiushi Wang +3

Publications (71)

EVA-Score: Evaluating Abstractive Long-form Summarization on Informativeness through Extraction and Validation

Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning

TCBERT: A Technical Report for Chinese Topic Classification BERT

Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models

Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining

Neural Sparse Representation for Image Restoration

Liquid-gas analog multicriticality in a frustrated Ising bilayer

SSRL: Self-Search Reinforcement Learning

Process Reinforcement through Implicit Rewards

PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory

PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar

Efficient and Explicit Modelling of Image Hierarchies for Image Restoration

Post-Trained MoE Can Skip Half Experts via Self-Distillation

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results

Phase diagram and quantum criticality of Heisenberg spin chains with Ising-like interchain couplings -- Implication to YbAlO3​

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient Scalings

Toward Efficient Agents: Memory, Tool learning, and Planning

MoVideo: Motion-Aware Video Generation with Diffusion Models

Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation

Scale-PINN: Learning Efficient Physics-Informed Neural Networks Through Sequential Correction

NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results

Generalized field mixing for endpoint criticality with marginal flow: resolving the four-state Potts endpoint in the square-lattice J1​--J2​ Ising model

Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents

Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Decomposing Two-Bounce Light

VRT: A Video Restoration Transformer

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Hitting probability for Reflected Brownian Motion at Small Target

Quantum-critical scaling at the Bose-glass transition of the 3d diluted Heisenberg antiferromagnet in a field

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning

LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Pyramid Attention Networks for Image Restoration

A Survey of Reinforcement Learning for Large Reasoning Models

MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds

Bridging Computational Fluid Dynamics Algorithm and Physics-Informed Learning: SIMPLE-PINN for Incompressible Navier-Stokes Equations

Reading = Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models

Recurrent Video Restoration Transformer with Guided Deformable Attention

SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection

YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark

3D Mesh Editing using Masked LRMs

Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds

Application-Driven Architecture Exploration for Cross-Layer Heterogeneous Systems

Phase diagram and Ashkin-Teller universality in the classical square-lattice Heisenberg-compass model

SinD 2.0: A Multi-City UAV Dataset with Semantic Risk Annotations for SOTIF-Oriented Safety Validation at Signalized Intersections

WorldGen: From Text to Traversable and Interactive 3D Worlds

AssetGen: Deployable 3D Asset Generation at Interactive Speed

A Better Upper Bound of Hausdorff Measure of the Cartesian Product of the Middle Third Cantor Set with Itself Compare to Others'

LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge

Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models

WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians

Scale-wise Convolution for Image Restoration

Emergent criticality in fully frustrated quantum magnets

How Far Can Unsupervised RLVR Scale LLM Training?

LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation

YouTube-VOS: Sequence-to-Sequence Video Object Segmentation

FFV-PINN: A Fast Physics-Informed Neural Network with Simplified Finite Volume Discretization and Residual Correction

Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion

Wide Activation for Efficient and Accurate Image Super-Resolution

Training Neural Networks on RAW and HDR Images for Restoration Tasks

Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models

BoRA: Bi-dimensional Weight-Decomposed Low-Rank Adaptation

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization

Non-Local Recurrent Network for Image Restoration

Video Instance Segmentation

Fluctuation-induced first order phase transitions in Kitaev-like d4 honeycomb magnet

Evaluating Generative Language Models in Information Extraction as Subjective Question Correction

LFQA-E: Carefully Benchmarking Long-form QA Evaluation

Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models

Phase diagram and quantum criticality of Heisenberg spin chains with Ising-like interchain couplings -- Implication to YbAlO $_{3}$

Generalized field mixing for endpoint criticality with marginal flow: resolving the four-state Potts endpoint in the square-lattice $J_{1}$ -- $J_{2}$ Ising model

Reading $\neq =$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models

Fluctuation-induced first order phase transitions in Kitaev-like $d^{4}$ honeycomb magnet