Han Wang

@HanWang98

PhD student @unc @unccs @unc_ai_group; Research Intern @Snowflake❄️; Formerly @AMD @AmazonScience @MSFTResearch @NlpWestlake. Views are my own. He/him

Chapel Hill, NC, USA

hannight.github.io

Joined July 2019

632 Following

342 Followers

Replies Reposts Media

Pinned
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,
1
Han Wang
@HanWang98
Sep 22
🎉 Excited to share our #EMNLP2026 work on diagnosing/tracing citation errors in deep research systems (which agent is actually to blame?) We find that information gets corrupted as it passes between agents like a game of telephone, and our method traces each error back to the
Eran Hirsch
@hirscheran
Sep 22
In deep research reports, many sentences aren't supported by their citations: recall is 58.7% in NVIDIA AI-Q and 7.1% in TrajectoryKit. Our #EMNLP2026 paper (main conf) proposes an algorithm that traces each error to the agent that introduced it, and identifies the error type.
Han Wang
@HanWang98
Apr 29
🚨 Excited to announce SAS: Stabilizing Efficient Reasoning with Step-Level Advantage Selection is accepted to #ACL2026 Findings. LLMs can compress reasoning during post-training with short context alone, but silently destabilize training. We propose SAS to fix it by zeroing
2
Han Wang
@HanWang98
Apr 17
Thanks @_akhaliq for sharing our work! If you are interested in multimodal agents on open-web search, please see our thread for more details: x.com/HanWang98/stat…
AK
@_akhaliq
Apr 16
MERRIN A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments paper: huggingface.co/papers/2604.13…
Han Wang
@HanWang98
Feb 13
🎉 Excited to share our new work MuRGAt! We show that high multimodal reasoning accuracy does not guarantee faithful grounding — MLLMs often answer correctly while hallucinating where their facts come from. Multimodal fact-level attribution remains a big open challenge! More
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

Han Wang

Han Wang’s posts