PPaperPicks

Usman Naseem

Macquarie University, Sydney, Australia

84 papers at tracked venues · 55 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-0191-7171 ↗Homepage ↗

Venues

WWW ×30ACL ×16EMNLP ×10EACL ×6AAAI ×4IJCAI ×4ACM MM ×3ICDM ×3CIKM ×1ECAI ×1ICCV ×1ICWSM ×1MICCAI ×1NAACL ×1SIGIR ×1WSDM ×1

Frequent coauthors

Surendrabikram Thapa
DBLP profile ↗ORCID search ↗
×5
Pranav Bhandari
DBLP profile ↗ORCID search ↗
×4
Gautam Siddharth Kashyap
DBLP profile ↗ORCID search ↗
×4
Jiahao Yuan
DBLP profile ↗ORCID search ↗
×3
Abid Ali
DBLP profile ↗ORCID search ↗
×3
Yiran Zhang
DBLP profile ↗ORCID search ↗
×2
Afrozah Nadeem
DBLP profile ↗ORCID search ↗
×2
Zhihao Zhang
DBLP profile ↗ORCID search ↗
×2
Utsav Maskey
DBLP profile ↗ORCID search ↗
×2
Shuvam Shiwakoti
DBLP profile ↗ORCID search ↗
×2
Zhihao Sui
DBLP profile ↗ORCID search ↗
×2
Shouyu Chen
DBLP profile ↗ORCID search ↗
×2

Papers

  1. Activation Decomposition and Steering for LLM Backdoor Remediation
    ACL 2026 ·
    Lingfeng Zhong
    DBLP profile ↗ORCID search ↗
  2. Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
    EACL 2026 ·
    Pranav Bhandari
    DBLP profile ↗ORCID search ↗
  3. AlignCultura: Towards Culturally Aligned Large Language Models?
    ACL 2026 ·
    Gautam Siddharth Kashyap
    DBLP profile ↗ORCID search ↗
  4. Are Large Language Models Economically Viable for Industry Deployment?
    ACL 2026 ·
    Abdullah Mohammad
    DBLP profile ↗ORCID search ↗
  5. Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA
    AAAI 2026 ·
    Yiran Zhang
    DBLP profile ↗ORCID search ↗
  6. Concept-Grounded Detection of Vaccine Misinformation in Multimodal Content Using Interpretable Vision-Language Models
    WWW 2026 ·
    Laxmi Thapa
    DBLP profile ↗ORCID search ↗
  7. Counterfactual Augmented Causal Reasoning for Aspect-Based Sentiment Analysis
    WWW 2026 ·
    Yiming Wu
    DBLP profile ↗ORCID search ↗
  8. Do Clinical Question Answering Systems Really Need Specialised Medical Fine Tuning?
    EACL 2026 ·
    Sushant Kumar Ray
    DBLP profile ↗ORCID search ↗
  9. Do Large Language Models Reflect Demographic Pluralism in Safety?
    EACL 2026 · Usman Naseem
  10. Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
    ACL 2026 ·
    Pranav Bhandari
    DBLP profile ↗ORCID search ↗
  11. Fairness Evaluation and Inference Level Mitigation in LLMs
    ACL 2026 ·
    Afrozah Nadeem
    DBLP profile ↗ORCID search ↗
  12. Framing Political Bias in Multilingual LLMs Across Pakistani Languages
    ACL 2026 ·
    Afrozah Nadeem
    DBLP profile ↗ORCID search ↗
  13. From Native Memes to Global Moderation: Cross-Cultural Evaluation of Vision-Language Models for Hateful Meme Detection
    WWW 2026 ·
    Mo Wang
    DBLP profile ↗ORCID search ↗
  14. HCSL: Rumor Detection by Integrating Intra-Sample Curriculum Learning and Hierarchical Semantic Learning
    WWW 2026 ·
    Ping Liu
    DBLP profile ↗ORCID search ↗
  15. Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context
    ACL 2026 ·
    Zhihao Zhang
    DBLP profile ↗ORCID search ↗
  16. Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning
    WWW 2026 ·
    Jiahao Yuan
    DBLP profile ↗ORCID search ↗
  17. LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target
    ACL 2026 ·
    Md. Arid Hasan
    DBLP profile ↗ORCID search ↗
  18. LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation
    AAAI 2026 ·
    Weiquan Huang
    DBLP profile ↗ORCID search ↗
  19. MULSUM: A Multimodal Summarization System with Vis-Aligner and Diversity-Aware Image Selection
    EACL 2026 ·
    Abid Ali
    DBLP profile ↗ORCID search ↗
  20. Measuring What Matters Beyond Text: Evaluating Multimodal Summaries by Quality, Alignment, and Diversity
    ACL 2026 ·
    Abid Ali
    DBLP profile ↗ORCID search ↗
  21. Multimodal Content Analysis for Social Good
    WWW 2026 ·
    Surendrabikram Thapa
    DBLP profile ↗ORCID search ↗
  22. No Evidence, No Problem: When Less is More for Out of Context Multimodal Misinformation Detection
    WWW 2026 ·
    Siyuan Chen
    DBLP profile ↗ORCID search ↗
  23. POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization
    ACL 2026 · Usman Naseem
  24. ReRule: Temporal Rule-Augmented Language Modeling for Causal Event Chain Completion
    WWW 2026 ·
    Wei Zhang
    DBLP profile ↗ORCID search ↗
  25. Revealing the Truth with ConLLM for Detecting Multi-Modal Deepfakes
    EACL 2026 ·
    Gautam Siddharth Kashyap
    DBLP profile ↗ORCID search ↗
  26. Robust Harmful Meme Detection under Missing Modalities via Shared Representation Learning
    WWW 2026 ·
    Felix Breiteneder
    DBLP profile ↗ORCID search ↗
  27. SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering
    ACL 2026 ·
    Utsav Maskey
    DBLP profile ↗ORCID search ↗
  28. They Said Memes Were Harmless - We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural References
    WWW 2026 ·
    Sahil Tripathi
    DBLP profile ↗ORCID search ↗
  29. Towards Visually Grounded Multimodal Summarization via Cross-Modal Transformer and Gated Attention
    ACL 2026 ·
    Abid Ali
    DBLP profile ↗ORCID search ↗
  30. When the Model Said 'No Comment', We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified
    EACL 2026 ·
    Gautam Siddharth Kashyap
    DBLP profile ↗ORCID search ↗
  31. XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content
    ACL 2026 ·
    Vadivel Abishethvarman
    DBLP profile ↗ORCID search ↗
  32. A Multimodal Prompt-based Framework for Analyzing Code-Mixed and Low-Resource Memes
    ICWSM 2025 ·
    Surendrabikram Thapa
    DBLP profile ↗ORCID search ↗
  33. Addressing the Challenges of Mental Health Conversations with Large Language Models
    WWW 2025 ·
    Shuvam Shiwakoti
    DBLP profile ↗ORCID search ↗
  34. Alleviating Textual Reliance in Medical Language-Guided Segmentation via Prototype-Driven Semantic Approximation
    ICCV 2025 ·
    Shuchang Ye
    DBLP profile ↗ORCID search ↗
  35. Ask, Acquire, Understand: A Multimodal Agent-based Framework for Social Abuse Detection in Memes
    WWW 2025 ·
    Xuanrui Lin
    DBLP profile ↗ORCID search ↗
  36. BEAST: Leveraging Contrastive Learning and Unsupervised Sentence Embeddings for Improved Drug Abuse Detection
    WWW 2025 ·
    Shuvam Shiwakoti
    DBLP profile ↗ORCID search ↗
  37. Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities
    EMNLP 2025 ·
    Utsav Maskey
    DBLP profile ↗ORCID search ↗
  38. COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement
    IJCAI 2025 ·
    Zhihao Sui
    DBLP profile ↗ORCID search ↗
  39. COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism
    AAAI 2025 ·
    Jianing He
    DBLP profile ↗ORCID search ↗
  40. Can LLM Agents Maintain a Persona in Discourse?
    EMNLP 2025 ·
    Pranav Bhandari
    DBLP profile ↗ORCID search ↗
  41. Cross Platform MultiModal Retrieval Augmented Distillation for Code-Switched Content Understanding
    WWW 2025 ·
    Surendrabikram Thapa
    DBLP profile ↗ORCID search ↗
  42. DiGrI: Distorted Greedy Approach for Human-Assisted Online Suicide Ideation Detection
    WWW 2025 · Usman Naseem
  43. Enhancing Zero-Shot Learning of Pathology Vision-Language Foundation Models in Tumour Malignancy Recognition
    ECAI 2025 ·
    Xiao Wang
    DBLP profile ↗ORCID search ↗
  44. Entity-Aware Optimal Transport and Residual Attention for Multimodal Content Moderation
    WWW 2025 ·
    Siddhant Bikram Shah
    DBLP profile ↗ORCID search ↗
  45. Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires
    WWW 2025 ·
    Pranav Bhandari
    DBLP profile ↗ORCID search ↗
  46. Explainable Medical Image Captioning
    WWW 2025 ·
    Md Sarwar Kamal
    DBLP profile ↗ORCID search ↗
  47. ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content
    EMNLP 2025 ·
    Bhavik Chandna
    DBLP profile ↗ORCID search ↗
  48. Few Labels with Active Learning: From Weak to Strong Labels for Misinformation Detection
    WWW 2025 ·
    Abdulrahman Abdullah Alalawi
    DBLP profile ↗ORCID search ↗
  49. From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation
    EMNLP 2025 ·
    Zhihao Zhang
    DBLP profile ↗ORCID search ↗
  50. GameTox: A Comprehensive Dataset and Analysis for Enhanced Toxicity Detection in Online Gaming Communities
    NAACL 2025 · Usman Naseem
  51. KG-UQ: Knowledge Graph-Based Uncertainty Quantification for Long Text in Large Language Models
    WWW 2025 ·
    Yingqing Yuan
    DBLP profile ↗ORCID search ↗
  52. LLMs as Historical Actors: How AI Systems Influence the Web's Evolution
    WWW 2025 · Usman Naseem
  53. LLMs on a Budget? Say HOLA
    EMNLP 2025 ·
    Zohaib Hasan Siddiqui
    DBLP profile ↗ORCID search ↗
  54. MoCFL: Mobile Cluster Federated Learning Framework for Highly Dynamic Network
    WWW 2025 ·
    Kai Fang
    DBLP profile ↗ORCID search ↗
  55. PersoPilot: An Adaptive AI-Copilot for Transparent Contextualized Persona Classification and Personalized Response Generation
    ICDM 2025 ·
    Saleh Afzoon
    DBLP profile ↗ORCID search ↗
  56. Pluralistic Alignment for Healthcare: A Role-Driven Framework
    EMNLP 2025 ·
    Jiayou Zhong
    DBLP profile ↗ORCID search ↗
  57. PoliMeme: Exploring Offensive Meme Propagation in the Israel-Palestine Conflict
    WWW 2025 ·
    Pratham Grover
    DBLP profile ↗ORCID search ↗
  58. RF-DTR: A Multi-Stage DCT Token Regression Network for Progressive Rib Fracture Mask Refinement
    IJCAI 2025 ·
    Shouyu Chen
    DBLP profile ↗ORCID search ↗
  59. Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy
    IJCAI 2025 ·
    Zhihao Sui
    DBLP profile ↗ORCID search ↗
  60. ReflectDiffu: Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework
    ACL 2025 ·
    Jiahao Yuan
    DBLP profile ↗ORCID search ↗
  61. Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up
    ACL 2025 ·
    Jiahao Yuan
    DBLP profile ↗ORCID search ↗
  62. Third International Workshop on Multimodal Content Analysis for Social Good
    WWW 2025 · Usman Naseem
  63. Too Helpful, Too Harmless, Too Honest or Just Right?
    EMNLP 2025 ·
    Gautam Siddharth Kashyap
    DBLP profile ↗ORCID search ↗
  64. Towards a Bipartisan Understanding of Peace and Vicarious Interactions
    IJCAI 2025 ·
    Arka Dutta
    DBLP profile ↗ORCID search ↗
  65. Truth, Trust, and Trouble: Medical AI on the Edge
    EMNLP 2025 ·
    Mohammad Anas Azeez
    DBLP profile ↗ORCID search ↗
  66. TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models
    EMNLP 2025 ·
    Yiran Zhang
    DBLP profile ↗ORCID search ↗
  67. Unleashing the Potential of Diffusion Models Towards Diversified Sequential Recommendations
    SIGIR 2025 ·
    Zhuo Cai
    DBLP profile ↗ORCID search ↗
  68. VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare
    ACL 2025 ·
    Anudeex Shetty
    DBLP profile ↗ORCID search ↗
  69. Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding
    AAAI 2025 ·
    Guangyin Bao
    DBLP profile ↗ORCID search ↗
  70. A Linguistic Grounding-Infused Contrastive Learning Approach for Health Mention Classification on Social Media
    WSDM 2024 · Usman Naseem
  71. Can Large Language Models Enhance Predictions of Disease Progression? Investigating Through Disease Network Link Prediction
    EMNLP 2024 ·
    Haohui Lu
    DBLP profile ↗ORCID search ↗
  72. CapAlign: Improving Cross Modal Alignment via Informative Captioning for Harmful Meme Detection
    WWW 2024 ·
    Junhui Ji
    DBLP profile ↗ORCID search ↗
  73. Context-Aware Offensive Meme Detection: A Multi-Modal Zero-Shot Approach with Caption-Enhanced Classification
    ICDM 2024 ·
    Faseela Abdullakutty
    DBLP profile ↗ORCID search ↗
  74. Decoding Memes: A Comprehensive Analysis of Late and Early Fusion Models for Explainable Meme Analysis
    WWW 2024 ·
    Faseela Abdullakutty
    DBLP profile ↗ORCID search ↗
  75. Foreword for the First International Workshop on Multimodal Content Analysis for Social Good (MM4SG 2024)
    WWW 2024 ·
    Surendrabikram Thapa
    DBLP profile ↗ORCID search ↗
  76. MSynFD: Multi-hop Syntax Aware Fake News Detection
    WWW 2024 ·
    Liang Xiao
    DBLP profile ↗ORCID search ↗
  77. MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili
    ACM MM 2024 ·
    Han Wang
    DBLP profile ↗ORCID search ↗
  78. Performance Evaluation of Deep Learning and Transformer Models Using Multimodal Data for Breast Cancer Classification
    MICCAI 2024 ·
    Sadam Hussain
    DBLP profile ↗ORCID search ↗
  79. RUHate-MM: Identification of Hate Speech and Targets using Multimodal Data from Russia-Ukraine Crisis
    WWW 2024 ·
    Surendrabikram Thapa
    DBLP profile ↗ORCID search ↗
  80. Structural Representation Learning and Disentanglement for Evidential Chinese Patent Approval Prediction
    CIKM 2024 ·
    Jinzhi Shan
    DBLP profile ↗ORCID search ↗
  81. UMML: Layout-aware Text-Image Fusion for Unified Multilingual Multimodal Learning
    ICDM 2024 ·
    Hariram Veeramani
    DBLP profile ↗ORCID search ↗
  82. Unveiling Misogyny Memes: A Multimodal Analysis of Modality Effects on Identification
    WWW 2024 ·
    Shijing Chen
    DBLP profile ↗ORCID search ↗
  83. VR-DiagNet: Medical Volumetric and Radiomic Diagnosis Networks with Interpretable Clinician-like Optimizing Visual Inspection
    ACM MM 2024 ·
    Shouyu Chen
    DBLP profile ↗ORCID search ↗
  84. Vaccine Misinformation Detection in X using Cooperative Multimodal Framework
    ACM MM 2024 · Usman Naseem