Log inSign up
user avatar
David Wan
@meetdavidwan
PhD student at @unccs advised by @mohitban47 | @Google PhD Fellow| prev: @AmazonScience, @MetaAI, @SFResearch
meetdavidwan.github.io
Joined February 2019
490
Following
709
Followers
RepliesMedia
  • Pinned
    user avatar
    David Wan
    @meetdavidwan
    Feb 13
    🚀Announcing MuRGAt! MLLMs are improving at reasoning over complex multimodal inputs, but does that translate to faithful grounding to multimodal sources (video, audio, charts, etc.)? We find that even strong MLLMs often hallucinate citations despite getting the answer
    Image
  • user avatar
    David Wan
    @meetdavidwan
    May 8
    🥳 Excited to share that MuRGAt is accepted to #ICML2026! Even strong MLLMs hallucinate citations to multimodal sources (video, audio, charts). Our new Fact-Level Multimodal Attribution benchmark tackles this by: 🕐 Requiring fine-grained temporal & per-modality citations (vs.
    user avatar
    David Wan
    @meetdavidwan
    Feb 13
    🚀Announcing MuRGAt! MLLMs are improving at reasoning over complex multimodal inputs, but does that translate to faithful grounding to multimodal sources (video, audio, charts, etc.)? We find that even strong MLLMs often hallucinate citations despite getting the answer
    Image
  • user avatar
    David Wan
    @meetdavidwan
    Apr 16
    Can AI search agents actually handle the messy, multimodal web? 🌐 We built MERRIN to find out. MERRIN tests whether search agents can reason across text, images, video, and audio when sources conflict and queries don’t tell you which modality to look at. The gap is stark: The
    user avatar
    Han Wang
    @HanWang98
    Apr 16
    🚨 Excited to announce MERRIN: a human-annotated, expert-vetted benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments! 🌐🔍 The web is noisy, conflicting, and multimodal. Even strong search agents fail when questions require reasoning across text,
    Image
  • user avatar
    David Wan
    @meetdavidwan
    Feb 5
    🚀 I'm on the 2026 Research Scientist Job Market! I am a Google PhD Fellow at UNC (advised by @mohitban47). I work on Faithful and Multimodal AI, focusing on reducing hallucinations and improving reasoning in generation tasks by: 🔹 Faithfulness & Hallucination Mitigation:
  • user avatar
    David Wan
    @meetdavidwan
    Dec 15, 2025
    Massive congratulations to my fantastic advisor, @mohitban47, on becoming an ACL Fellow! 🚀 Truly deserved recognition for his incredible work and his invaluable guidance and mentorship. Thank you for everything!
    user avatar
    Mohit Bansal
    @mohitban47
    Dec 14, 2025
    Deeply happy and honored to be elected as an ACL Fellow -- and to be a part of the respected cohort of this+past years' fellows (congrats everyone)! 🙏 All the credit (and sincere gratitude) to all my amazing students, postdocs, collaborators, mentors, and family! 🤗💙
    Image