HKUST NLP
@hkustNLP
Followers
250
Following
54
Media
1
Statuses
26
HKUST Natural Language Processing Research #NLProc
Joined October 2024
Great work! @ZhaoweiWang4.
MMLongBench. Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
0
0
2
RT @ZhouHE777: Excited to present our work, MMBoundary, at #ACL2025!. Come chat with us at our poster session!.π Hall 4/5, Session 12: Postβ¦.
0
8
0
RT @yqsong: If you are at ACL, please talk to our members of @HKUSTKnowComp and @hkustNLP big family
0
3
0
RT @ZhouHE777: π€― Multimodal LLMs can be confidently wrong. A single early mistake in perception can lead to a completely incorrect answer.β¦.
0
3
0
RT @May_F1_: @hkustNLP @uiuc_nlp @aclmeeting [1/n] "ππ’π΅π€π©πͺπ―π¨ π€πΆπ¦π΄ π§π°π³ πͺπ₯π¦π―π΅πͺπ€π’π π°π£π«π¦π€π΅π΄, π₯πͺπ΄π΅πͺπ―π€π΅ π’π΅π΅π³πͺπ£πΆπ΅π¦π΄ π§π°π³ πΆπ―πͺπ²πΆπ¦ π°π―π¦π΄." Such ππ§π€π¨π¨-πβ¦.
0
3
0
RT @aclmentorship: π’ Join us for the ACL Mentorship Session @aclmeeting #ACL2025NLP #NLProc. β’ Session Link: β’ Askβ¦.
0
12
0
RT @ZeyuQin_alan: #COLM2025 Our work has been accepted to COLM 2025π. Looking forward to discussing Scalable Oversight and Synthetic Data wβ¦.
0
6
0
RT @SuZhaochen0110: Excited to share our new survey on the reasoning paradigm shift from "Think with Text" to "Think with Image"! π§ πΌοΈ.Our wβ¦.
0
61
0
RT @junxian_he: We studied both rule-based and model-based verifiers and found that each has unique limitations. Rule-based verifiers are oβ¦.
0
14
0
RT @May_F1_: Great to see the wonderful series of work that @WangCarrey has been leading at UIUC. We also had a fun collaboration recentlyβ¦.
0
7
0
RT @Tianshi_0218: π Our new survey "From Automation to Autonomy: LLMs in Scientific Discovery" is live! . π Paper: .
0
5
0
RT @AlexWan40524978: Struggling with inconsistent LLM answers across languages? Meet CALM: a label-free framework to align LLM's cross-lingβ¦.
arxiv.org
Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. Ideally, while LLMs should provide...
0
8
0
RT @SterZhang: π Introducing VLMΒ²-Bench!. A simple yet essential ability that we use in daily life. But when tackling vision-centric tasksβ¦.
0
47
0
π€― Still waiting for a PhD offer? Seeking research opportunities?. π Our HKUST NLP Group have a number of PhD openings for qualified students; we also offer many year-round remote intern opportunities!. π Fill out: Happy Year of the Snake! ππ§§π
0
3
21
RT @junxian_he: We replicated the DeepSeek-R1-Zero and DeepSeek-R1 training on 7B model with only 8K examples, the results are surprisinglyβ¦.
0
650
0