wovepaper — the arXiv observatory

LongStraw introduces an execution framework that enables reinforcement‑learning post‑training on million‑token prompts using a fixed GPU budget by separating prompt evaluation from…

#long-context reinforcement learning#large language model training#GPU memory efficiency#policy optimization

cs.CV2026

Unified Personalized Reward Model for Vision Generation

Yibin Wang, Yuhang Zang, Feng Han +4

physics.chem-ph2025

Super-resolution femtosecond electron diffraction reveals electronic and nuclear dynamics at conical intersections

Hui Jiang, Juanjuan Zhang, Tianyu Wang +9

cs.CV2024

Generate Point Clouds with Multiscale Details from Graph-Represented Structures

Ximing Yang, Zhibo Zhang, Zhengfu He +1

physics.atom-ph2010

New determination of structure parameters in strong field tunneling ionization theory of molecules

Song-Feng Zhao, Cheng Jin, Anh-Thu Le +2

cs.CV2024

High-fidelity Person-centric Subject-to-Image Synthesis

Yibin Wang, Weizhong Zhang, Jianwei Zheng +1

cs.CV2024

PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering

Yibin Wang, Weizhong Zhang, Jianwei Zheng +1

cs.NI2010

A Practical Localization Algorithm Based on Wireless Sensor Networks

Tao Huang, Zhikui Chen, Feng Xia +2

cs.CV2026

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Dianyi Wang, Ruihang Li, Feng Han +17

cs.CL2023

ProtoEM: A Prototype-Enhanced Matching Framework for Event Relation Extraction

Zhilei Hu, Zixuan Li, Daozhu Xu +5

cs.CV2025

HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image Classification

Cheng Jin, Luyang Luo, Huangjing Lin +2

physics.chem-ph2025

Imaging the photochemical dynamics of cyclobutanone with MeV ultrafast electron diffraction

Tianyu Wang, Hui Jiang, Cheng Jin +5

cs.LG2026

AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning

Changhai Zhou, Shiyang Zhang, Yuhua Zhou +5

cs.CR2021

Safe Distillation Box

Jingwen Ye, Yining Mao, Jie Song +3

cs.LG2012

Groupwise Constrained Reconstruction for Subspace Clustering

Ruijiang Li, Bin Li, Ke Zhang +2

eess.IV2025

Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation

Jiabo Ma, Zhengrui Guo, Fengtao Zhou +20

cs.LG2024

Optimized Gradient Clipping for Noisy Label Learning

Xichen Ye, Yifan Wu, Weizhong Zhang +3

cs.CV2024

Robust Fine-tuning for Pre-trained 3D Point Cloud Models

Zhibo Zhang, Ximing Yang, Weizhong Zhang +1

cs.CV2024

Out-of-Distribution Detection using Neural Activation Prior

Weilin Wan, Weizhong Zhang, Quan Zhou +2

cs.CV2023

Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection

Kaiyi Zhang, Yang Chen, Ximing Yang +2

cs.CV2024

Efficient scene text image super-resolution with semantic guidance

LeoWu TomyEnrique, Xiangcheng Du, Kangliang Liu +3

cs.CV2025

PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology

Jiabo Ma, Yingxue Xu, Fengtao Zhou +23

cs.CL2025

PsychBench: A comprehensive and professional benchmark for evaluating the performance of LLM-assisted psychiatric clinical practice

Shuyu Liu, Ruoxi Wang, Ling Zhang +7

Publications (103)

Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions

PRINTER:Deformation-Aware Adversarial Learning for Virtual IHC Staining with In Situ Fidelity

SIT: A Bionic and Non-Linear Neuron for Spiking Neural Network

GameGen-X: Interactive Open-world Game Video Generation

Progressive Scene Text Erasing with Self-Supervision

Intelligent social bots uncover the link between user preference and diversity of news consumption

A Breast Vision Pathology Foundation Model for Real-world Clinical Utility

The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation

Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems

UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation

Fine-Grained Scene Image Classification with Modality-Agnostic Adapter

ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation

Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning

Towards Robust Influence Functions with Flat Validation Minima

A Pathology Foundation Model for Gastric Cancer with Real-World Validation

A-FloPS: Accelerating Diffusion Models via Adaptive Flow Path Sampler

Explore and Establish Synergistic Effects Between Weight Pruning and Coreset Selection in Neural Network Training

Generalizable Cervical Cancer Screening via Large-scale Pretraining and Test-Time Adaptation

Attention-based Transformation from Latent Features to Point Clouds

Democratizing and accelerating AI-driven pathology research through agentic intelligence

EPA: Neural Collapse Inspired Robust Out-of-Distribution Detector

Investigating Data Pruning for Pretraining Biological Foundation Models at Scale

Large Language Model Compression with Global Rank and Sparsity Optimization

Transient dynamics of the phase transition in VO2 revealed by mega electron-volt ultrafast electron diffraction

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Cross-Domain Document Layout Analysis Using Document Style Guide

HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Device Scenarios

Influence of gas pressure on high-order harmonic generation of Ar and Ne

DDT: Dual-branch Deformable Transformer for Image Denoising

Electron-Backscattering-Assisted High Harmonic Generation from Bilayer Nanostructures

Unified Reward Model for Multimodal Understanding and Generation

Discovering Pathology Rationale and Token Allocation for Efficient Multimodal Pathology Reasoning

A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model

Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Models

Extension of the bright high-harmonic photon energy range via nonadiabatic critical phase matching

LLM-driven Medical Report Generation via Communication-efficient Heterogeneous Federated Learning

1 Bit Electronically Reconfigurable Transmitarray Antenna with Out-of-Band Scatter Suppression

Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies

DreamText: High Fidelity Scene Text Synthesis

Minutes to Seconds: Speeded-up DDPM-based Image Inpainting with Coarse-to-Fine Sampling

UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images

ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory

OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference

A Versatile Pathology Co-pilot via Reasoning Enhanced Multimodal Large Language Model

Linear Speedup of Incremental Aggregated Gradient Methods on Streaming Data

GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation

Analysis of effects of macroscopic propagation and multiple molecular orbitals on the minimum in high-order harmonic generation of aligned CO2​

Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering

Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation

Separation of Target Structure and Medium Propagation Effects in High-Harmonic Generation

Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization

Learning-based Traversability Costmap for Autonomous Off-road Navigation

Genome-Anchored Foundation Model Embeddings Improve Molecular Prediction from Histology Images

Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model

LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment

Medium propagation effects in high harmonic generation of Ar and N2​

Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning

WYTIWYR: A User Intent-Aware Framework with Multi-modal Inputs for Visualization Retrieval

Cheng-Yau logarithmic gradient estimates for a nonlinear elliptic equation on smooth metric measure spaces

Large Language Models have Chain-of-Affect

TripletGAN: Training Generative Model with Triplet Loss

A Deployment-Friendly Foundational Framework for Efficient Computational Pathology

Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification

Document Layout Analysis with Aesthetic-Guided Image Augmentation

Intensity dependence of multiple orbital contributions and shape resonance in high-order harmonic generation of aligned N2​ molecules}

Aggregated Text Transformer for Scene Text Detection

Adaptive Charging Networks: A Framework for Smart Electric Vehicle Charging

Manifold-Constrained Noise Optimization for Diverse Diffusion Sampling

MultiColor: Image Colorization by Learning from Multiple Color Spaces

Extension of all-optical reconstruction method for isolated attosecond pulses using high-harmonic generation streaking spectra

Computational Budget Should Be Considered in Data Selection

Spatially homogeneous few-cycle compression of Yb lasers via all-solid-state free-space soliton management

DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding

Generation of isolated attosecond pulses in the far field by spatial filtering with an intense few-cycle mid-infrared laser

In-Band Co-Polarization Scattering Beam Scanning of Antenna Array Based on 1-Bit Reconfigurable Load Impedance

Advanced Black-Box Tuning of Large Language Models with Limited API Calls

SRPCN: Structure Retrieval based Point Completion Network

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Unified Personalized Reward Model for Vision Generation

Analysis of effects of macroscopic propagation and multiple molecular orbitals on the minimum in high-order harmonic generation of aligned CO $_{2}$

Medium propagation effects in high harmonic generation of Ar and N $_{2}$

Intensity dependence of multiple orbital contributions and shape resonance in high-order harmonic generation of aligned N $_{2}$ molecules}