-[10/2025] Our paper “BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization” was accepted to Nature Communications Biology. -[09/2025] Three papers on attention manipulation for LLM safety, expert question generation, and hallucination for embodied agent were accepted at EMNLP 2025.

• [05/2025] Our paper “Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models” was accepted to ICML as a spotlight poster.
• [2/2025] Our paper “TRAWL: Tensor Reduced and Approximated Weights for Large Language Models” was accepted to PAKDD 2025 DSFA.
• [1/2025] Our paper “VIKI: Systematic Cross-Platform Profile Inference of Tech Users” was accepted to WebSci 2025.
• [1/2025] Our paper “LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner” has been accepted at ICRA 2025.
• [1/2025] Our paper Not all heads matter: A head-level KV cache compression method with integrated retrieval and reasoning, led by my PhD student Yu Fu, has been accepted into ICLR 2025!
• [11/2024] I am honored to serve as a senior area chair for ACL 2025.
• [10/2024] 5 papers from my group have been accepted to SoCal NLP Symposium 2024.
• [9/2024] Three papers on hallucination interpretability, cross-modal unlearning, and adversarial attacks have been accepted to EMNLP Findings.
• [9/2024] I am honored to serve as a senior area chair for NAACL 2025 and area chair for ICLR 2025.
• [7/2024] Our paper on Personalized Conversational Information Retrieval has been accepted at CIKM 2024.
• [7/2024] IllusionVQA has been accepted at COLM.
• [5/2024] Excited that 5 papers (on Summarization Safety Alignment, Bias in Text-to-Image Generation, Misogyny Benchmark, Text Re-ranking, Temporal QA) are accepted to ACL 2024 or ACL Findings.
• [5/2024] Our work “Cross-Task Defense: Instruction-Tuning LLMs for Content Safety” has been accepted to NAACL TrustNLP 2024 workshop.
• [3/2024] I am honored to serve as a senior area chair for EMNLP 2024.
• [3/2024] Our paper Source-Free Domain Adaptation for Question Answering with Masked Self-training has been accepted at TACL 2024.
• [2/2024] My PhD students Yu Fu (1st year) and Erfan Shayegani (2nd year) will be interning at Microsoft Research this summer. Congrats!
• [1/2024] Our paper Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models has been accepted into ICLR 24 as a spotlight (5% of papers, acc. 31% ), Congrats! This paper also featured on UCR news.
• [12/2023] Our paper Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy, led by my PhD student Yu Fu, has been accepted into AAAI 24 (an overall acceptance rate of 23.75%).
• [11/2023] Thrilled our submission on VLM attack with Erfan Shayegani and Nael Abu-Ghazaleh won the Best Paper Award (3/155 papers) at the 2023 Southern California NLP Symposium!
• [10/2023] Our paper “Subtle Misogyny Detection and Mitigation: An Expert-Annotated Dataset” has been accepted as a spotlight (2/all submissions) at NeurIPS 2023 SoLaR Workshop.
• [10/2023] Check out the UCR news on Faculty members discuss AI’s possible impacts at UCR.
• [10/2023] I am honored to serve as a senior area chair for NAACL 2024.
• [10/2023] Our paper Inverse Reinforcement Learning for Text Summarization led by my PhD student Yu Fu has been accepted to the findings of EMNLP 2023.
• [10/2023] Our tutorial on Vulnerabilities of Large Language Models to Adversarial Attacks has been accepted for ACL 2024.
• [07/2023] I was awarded a Regents Faculty Fellowship grant 2023-2024.
• [06/2023] I was selected for UCR OASIS Internal Funding Awards 2023-2024.
• [05/2023] Our proposal of KDD 2023 tutorial on Fast Text Generation with Text-Editing Models has been accepted
• [04/2023] Thrilled to join the Biasly team at Mila as a visiting NLP advisor, working on AI for humanity and to mitigate gender biases in language models.
• [03/2023] Our application to form a special interest group on summarization has been accepted by ACL. Checkout the newest ACL’s SIG - SIGSUMM
• [01/2023] Expressed my opinions about chatGPT for education @UCR News
• [01/2023] Joined UCR as an assistant professor in the CSE department
• [12/2022] The 4th workshop on “New Frontiers in Summarization Workshop” has been accepted to EMNLP 2023
• [11/2022] Career and Personal Pathway Panelist at Google exploreCSR-DS and ML workshop @ University of California Riverside
• [11/2022] Talk at UCR Data Science Seminar on “hallucinations in text generation”
• [11/2022] Successfully defended my PhD! Checkout my thesis here
• [10/2022] Our paper “Faithful to the Document or to the World? Mitigating Hallucinations via Entity-Linked Knowledge in Abstractive Summarization” has been accepted to the findings of EMNLP 2022
• [10/2022] Our paper “Learning with Rejection for Abstractive Text Summarization” has been accepted to EMNLP 2022
• [07/2022] Our workshop on “Efficient Natural Language and Speech Processing (ENLSP-II): The Future of Pre-trained Models” has been accepted to NeurIPS 2022
• [04/2022] Happy to announce that I will be joining the University of Califonia, Riverside as a tenure-track assistant professor
• [12/2021] Our “Text Generation with Text-Editing Models” tutorial has been accepted to NAACL 2022