🌴Muhao Chen🌴

🚨 Check out our latest paper! Diagnosing and Mitigating Modality Interference in MLLMs: 📉 MLLMs struggle on unimodal tasks 🧠 We call this Modality Interference, a symptom of Cross-Modality Competency Problem 🛠️ Causal Analysis and Solution provided 📄 arxiv.org/abs/2505.19616

🔍 Introducing QA-LIGN: A reflective alignment approach using a draft→reflection→revision pipeline. We create symbolic reward models that serve as both natural language critics & general reward models, bridging rule-based rewards and RLAIF. 📄 Paper: arxiv.org/pdf/2506.08123

Are we heading down the right path towards omni-modality? 🤔 This new paper explores the effects of extending modality in language models.

🚨 New paper accepted to #ACL2025! We propose SudoLM, a framework that lets LLMs learn access control over parametric knowledge. Rather than blocking everyone from sensitive knowledge, SudoLM grants access to authorized users only. Paper: arxiv.org/abs/2410.14676… 🧵[1/6]👇

😴 Extending modality based on an LLM has been a common practice when we are talking about multimodal LLMs. ❓ Can it generalize to omni-modality? We study the effects of extending modality and ask three questions: arxiv.org/abs/2506.01872 #LLM #MLLM #OmniModality

Can LLM guardrails think twice before deciding? ✨ Check out our #ACL2025 paper: THINKGUARD — a critique-augmented safety guardrail! ✅ Structured critiques ✅ Interpretable decisions ✅ Robust against adversarial prompts 📑 arxiv.org/abs/2502.13458 🧵[1/n]

🚀Check our latest work accepted by ACL 2025 Main. AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection In this work: 🔍 We introduce Safe-OS, an online benchmark for OS agents that includes prompt injection attacks, environment-based attacks, and…

Worried about backdoors in LLMs? 🌟 Check out our #NAACL2025 work on test-time backdoor mitigation! ✅ Black-box 📦 ✅ Plug-and-play 🛡️ We explore: → Defensive Demonstrations 🧪 → Self-generated Prefixes 🧩 → Self-refinement ✍️ 📄 arxiv.org/abs/2311.09763 🧵[1/n]

Excited to share our papers at #ICLR2025 in Singapore! Check out the summaries on our blog (ccgblog.seas.upenn.edu/2025/04/ccg-pa…), and then check out the papers at oral session 1B (BIRD) and poster session 2 (for all three)! @AnnieFeng6, @XingyuFu2, @BenZhou96, @muhao_chen, @DanRothNLP

🎉 Excited to share that our paper, "MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding", will be presented at #ICLR2025!​ 📅 Date: April 24 🕒 Time: 3:00 PM 📍 Location: Hall 3 + Hall 2B #11 MuirBench challenges multimodal LLMs with diverse multi-image…

🚨 Call for Papers! @aclmeeting 🚨 LLM Security Workshop @ ACL 2025 (the first workshop of ACL SIGSEC) 🔐 Topics: Adversarial attacks, defenses, vulnerabilities, ethical & legal aspects, safe deployment of LLMs and more 📅 Submission Deadline: April 15, 2025 📍 August 1, 2025 in…

🚀 Excited to share MetaScale, our latest work advancing LLM reasoning capabilities! MetaScale empowers GPT-4o to match or even surpass frontier reasoning models like o1, Claude-3.5-Sonnet, and o1-mini on the challenging Arena-Hard benchmark (@lmarena_ai). Additionally, MetaScale…

NSF Budget Cuts Would Put the Future of U.S. Innovation and Security at Risk cra.org/nsf-budget-cut…

New interview with @muhao_chen, former CCG postdoc, who talks with us about cats and hamsters, LLM safety, and far-flung national parks! ccgblog.seas.upenn.edu/2025/01/interv…

𝗠𝘂𝗶𝗿𝗕𝗲𝗻𝗰𝗵 is officially accepted at #ICLR2025! 🎉 Recent VLMs/MLLMs such as LLaVA-OneVision, MM1.5, and MAmmoTH-VL have demonstrated significant progress on MuirBench.🚀 Excited to see how MuirBench continues to drive the innovation of VLMs! #AI #MachineLearning #VLM…

Please consider submitting to the AAAI spring Symposium on AI for Engineering and Scientific Discoveries; we will accept regular AAAI sized papers (maximum 8 pages including references) or short 2-page abstracts: sites.google.com/view/aaai-ss25…. • Paper/abstract Submission Deadline:…