wovepaper — the arXiv observatory

The paper introduces Open-AoE, a large-scale egocentric video dataset of human manipulation together with a processing and downstream toolchain that provides hand pose, camera traj…

#egocentric video#manipulation dataset#embodied learning#hand pose estimation

cs.LG2025

Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentation

Fermin Orozco, Pedro Porto Buarque de GusmÃ£o, Hongkai Wen +2

cs.CL2024

LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models

Mihir Parmar, Nisarg Patel, Neeraj Varshney +5

cs.CV2026

AoE: Always-on Egocentric Human Video Collection for Embodied AI

Bowen Yang, Zishuo Li, Yang Sun +15

cs.CL2022

BioTABQA: Instruction Learning for Biomedical Table Question Answering

Man Luo, Sharad Saxena, Swaroop Mishra +2

cs.IR2022

Improving Biomedical Information Retrieval with Neural Retrievers

Man Luo, Arindam Mitra, Tejas Gokhale +1

cs.CL2025

Benchmark on Peer Review Toxic Detection: A Challenging Task with a New Dataset

Man Luo, Bradley Peterson, Rafael Gan +5

cs.CV2025

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models

Haibo Jin, Peiyan Zhang, Peiran Wang +2

stat.ME2026

Principal Components Decomposition of Fraction of Variance Explained in High Dimensional Linear Models with Strong Correlation

Man Luo, Chun Chieh Fan, David Azriel +1

cs.LO2019

Strong equivalence for $L P^{MLN}$ programs

Man Luo

cs.CL2022

Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness

Tejas Gokhale, Swaroop Mishra, Man Luo +2

cs.CV2024

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models

Jiawei Liang, Siyuan Liang, Man Luo +4

cs.CV2022

Multi-Forgery Detection Challenge 2022: Push the Frontier of Unconstrained and Diverse Forgery Detection

Jianshu Li, Man Luo, Jian Liu +12

cs.CL2022

A Simple Approach to Jointly Rank Passages and Select Relevant Sentences in the OBQA Context

Man Luo, Shuguang Chen, Chitta Baral

cs.LG2022

Improving Contrastive Learning with Model Augmentation

Zhiwei Liu, Yongjun Chen, Jia Li +3

cs.CL2026

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

PSBC LLM Team, Huawei LLM Team, Ruihan Long +56

cs.CL2022

Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?

Neeraj Varshney, Man Luo, Chitta Baral

cs.CL2022

Neural Retriever and Go Beyond: A Thesis Proposal

Man Luo

cs.CV2021

CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results

Yuanhan Zhang, Zhenfei Yin, Jing Shao +22

physics.app-ph2019

Nb $_{2}$ SiTe $_{4}$ : A Stable Narrow-Gap Two-Dimensional Material with Ambipolar Transport and Mid-Infrared Response

Mingxing Zhao, Wei Xia, Yang Wang +5

cs.AI2025

DPO Learning with LLMs-Judge Signal for Computer Use Agents

Man Luo, David Cobbley, Xin Su +4

cs.IT2020

Approximate Message Passing with Unitary Transformation for Robust Bilinear Recovery

Zhengdao Yuan, Qinghua Guo, Man Luo

cs.AI2026

Language models guide symbolic equation discovery by controlling search

Zikai Xie, Wenmei Li, Man Luo +2

cs.CL2026

Controlling Output Rankings in Generative Engines for LLM-based Search

Haibo Jin, Ruoxi Chen, Peiyan Zhang +4

cs.AI2025

GeoThought: A Dataset for Enhancing Mathematical Geometry Reasoning in Vision-Language Models

Nannan Shi, Chuanyu Qin, Shipeng Song +1

cs.LG2022

Fleet Rebalancing for Expanding Shared e-Mobility Systems: A Multi-agent Deep Reinforcement Learning Approach

Man Luo, Bowen Du, Wenzhe Zhang +5

cs.CL2024

Assessing Empathy in Large Language Models with Real-World Physician-Patient Interactions

Man Luo, Christopher J. Warren, Lu Cheng +2

Publications (70)

Probing Semantic Routing in Large Mixture-of-Expert Models

In-BoXBART: Get Instructions into Biomedical Multi-Task Learning

REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization

In-context Learning with Retrieved Demonstrations for Language Models: A Survey

Strong Equivalence for LPMLN Programs

FastRM: An efficient and automatic explainability framework for multimodal generative models

DemoShapley: Valuation of Demonstrations for In-Context Learning

TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility

Real-Time 3D Simulation of Heat-Induced Air Turbulence

Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation

HALO: Hierarchical Reinforcement Learning for Large-Scale Adaptive Traffic Signal Control

InfoFlood: Jailbreaking Large Language Models with Information Overload

Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations

Dr.ICL: Demonstration-Retrieved In-context Learning

Can Transformers Reason About Effects of Actions?

MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluation

Inclusion 2024 Global Multimedia Deepfake Detection Challenge: Towards Multi-dimensional Face Forgery Detection

Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models

FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability

Sparse Bayesian Learning Using Approximate Message Passing with Unitary Transformation

Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review

Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning

End-to-end Knowledge Retrieval with Multi-modal Queries

CityVerse: A Unified Data Platform for Multi-Task Urban Computing with Large Language Models

A Study on the Efficiency and Generalization of Light Hybrid Retrievers

Deep Signature FBSDE Algorithm

Deployment Optimization for Shared e-Mobility Systems with Multi-agent Deep Neural Search

Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering

Scaling Knowledge Graph Construction through Synthetic Data Generation and Distillation

TrajWeaver: Trajectory Recovery with State Propagation Diffusion Model

Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?

Demand Prediction for Electric Vehicle Sharing

Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization

DDL: A Large-Scale Datasets for Deepfake Detection and Localization in Diversified Real-World Scenarios

Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models

SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs

Reasoning Can Hurt the Inductive Abilities of Large Language Models

Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering

Unitary Approximate Message Passing for Sparse Bayesian Learning

Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review

MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios

'Just because you are right, doesn't mean I am wrong': Overcoming a Bottleneck in the Development and Evaluation of Open-Ended Visual Question Answering (VQA) Tasks

From Generation to Collaboration: Using LLMs to Edit for Empathy in Healthcare

Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning

Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentation

LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models

AoE: Always-on Egocentric Human Video Collection for Embodied AI

BioTABQA: Instruction Learning for Biomedical Table Question Answering

Improving Biomedical Information Retrieval with Neural Retrievers

Benchmark on Peer Review Toxic Detection: A Challenging Task with a New Dataset

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models

Principal Components Decomposition of Fraction of Variance Explained in High Dimensional Linear Models with Strong Correlation

Strong equivalence for LPMLN programs

Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models

Multi-Forgery Detection Challenge 2022: Push the Frontier of Unconstrained and Diverse Forgery Detection

A Simple Approach to Jointly Rank Passages and Select Relevant Sentences in the OBQA Context

Improving Contrastive Learning with Model Augmentation

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?

Neural Retriever and Go Beyond: A Thesis Proposal

CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results

Nb2​SiTe4​: A Stable Narrow-Gap Two-Dimensional Material with Ambipolar Transport and Mid-Infrared Response

DPO Learning with LLMs-Judge Signal for Computer Use Agents

Approximate Message Passing with Unitary Transformation for Robust Bilinear Recovery

Language models guide symbolic equation discovery by controlling search

Controlling Output Rankings in Generative Engines for LLM-based Search

GeoThought: A Dataset for Enhancing Mathematical Geometry Reasoning in Vision-Language Models

Fleet Rebalancing for Expanding Shared e-Mobility Systems: A Multi-agent Deep Reinforcement Learning Approach

Assessing Empathy in Large Language Models with Real-World Physician-Patient Interactions

Strong equivalence for $L P^{MLN}$ programs

Nb $_{2}$ SiTe $_{4}$ : A Stable Narrow-Gap Two-Dimensional Material with Ambipolar Transport and Mid-Infrared Response