aadhikariii Profile Banner
Ashutosh Adhikari Profile
Ashutosh Adhikari

@aadhikariii

Followers
223
Following
1K
Media
8
Statuses
116

PhD Student at @EdinburghNLP Previously at Microsoft Turing; CS @UWaterloo; @Mila_Quebec Views my own.

Edinburgh, Scotland
Joined June 2015
Don't wanna be here? Send us removal request.
@aadhikariii
Ashutosh Adhikari
1 month
Excited to share my first work as a PhD student at @EdinburghNLP that I will be presenting at EMNLP! RQ1: Can we achieve scalable oversight across modalities via debate? Yes! We show that debating VLMs lead to better model quality of answers for reasoning tasks.
1
7
13
@diyerxx
Lei Yang
15 days
Got burned by an Apple ICLR paper โ€” it was withdrawn after my Public Comment. So hereโ€™s what happened. Earlier this month, a colleague shared an Apple paper on arXiv with me โ€” it was also under review for ICLR 2026. The benchmark they proposed was perfectly aligned with a
55
218
2K
@FelineAutomaton
malkin1729
26 days
@iatitov and I are happy to announce a fully-funded 3.5-year PhD studentship at @EdinburghNLP, for September 2026 start, on language-based state representations for time series modelling, with applications in health data monitoring and beyond. {1/5}
1
15
31
@PMinervini
Pasquale Minervini ๐Ÿ‡ช๐Ÿ‡บ ๐Ÿ‡ฌ๐Ÿ‡ง ๐Ÿด๓ ง๓ ข๓ ณ๓ ฃ๓ ด๓ ฟ
27 days
Hey thatโ€™s @EdinburghNLP!
@ai_impact_rank
AI Research Impact Rankings
28 days
CSRankings counts publication in top conferences to rank professors/universities. But this encourages researchers to pursue quantity rather than quality. We propose https://t.co/ajtH10DbWQ, a new university ranking system that tries to measure quality instead of quantity of
4
2
51
@clairebarale
Claire Barale
1 month
At #EMNLP2025 in Suzhou to present the last work of my PhDโœจ ๐Ÿ“… tomorrow ๐Ÿ•“ 12.30 session We studied temporal reasoning on legal events and show that LLMs struggle with the linguistic complexities of legal language. Joint work between @EdinburghNLP and @TechAtBloomberg
0
1
4
@rohit_saxena
Rohit Saxena
9 months
Can multimodal LLMs truly understand research poster images?๐Ÿ“Š ๐Ÿš€ We introduce PosterSumโ€”a new multimodal benchmark for scientific poster summarization! ๐Ÿชง ๐Ÿ“‚ Dataset: https://t.co/B5NzvqnWUA ๐Ÿ“œ Paper: https://t.co/EHt4SwaGF3
3
27
82
@aadhikariii
Ashutosh Adhikari
1 month
I will be at EMNLP next week presenting this work on November the 7th! Reach out to me for any questions :)) Work done with my advisor, Mirella Lapata! Preprint: https://t.co/eu6tPw7YyP #EMNLP2025 #multimodallearning
0
0
0
@aadhikariii
Ashutosh Adhikari
1 month
RQ3: Where do debate or consultancy fail? Our analysis show that judges benefit when the experts are arguing for diverse opinions! Red quadrant is when the judge is persuaded more often than they should (i.e. they are deceptive).
1
0
0
@aadhikariii
Ashutosh Adhikari
1 month
RQ2: Can debate be used as a reliable mechanism for yielding quality reasoning data? Yes! We show that the reasoning data attained from debate in a completely unsupervised manner imbue reasoning in the expert vision language models.
1
0
1
@hila_gonen
Hila Gonen
2 months
Considering a PhD/MSc in NLP? Iโ€™m hiring students this cycle! If you are passionate about making language models reliable and safe, eager about understanding and controlling language models, and would like to add to your research some multilingual flavor - apply to my group! ๐Ÿ‘‡
16
102
737
@miniapeur
Mathieu
2 months
Hello everyone. A friend told me that I shouldn't post this message because it made me and other PhD students look bad. But I actually think it's important to show how PhD students (especially foreign ones) have to deal not only with research-related difficulties, but also with
Tweet card summary image
gofundme.com
Hello everyone. A friend told me that I shouldn't post this messageโ€ฆ Mathieu Alain needs your support for Help me resuming my PhD studies after sick leave
44
245
1K
@aadhikariii
Ashutosh Adhikari
3 months
Hi folks, I am embarrassed to say my account was compromised for a couple of weeks and X took forever to verify me. I want to apologize for any inappropriate content you might have come across from my account during the period.
0
0
1
@sahar_abdelnabi
Sahar Abdelnabi ๐Ÿ•Š
4 months
Seems fitting to repost ๐Ÿ™ƒ
@sahar_abdelnabi
Sahar Abdelnabi ๐Ÿ•Š
1 year
NeurIPS reviewer: solution is not new and was heavily studied. @NeurIPSConf #NeurIPS24
8
13
299
@rajammanabrolu
Prithviraj (Raj) Ammanabrolu
4 months
By popular demand we've extended the Wordplay Workshop deadline by a couple of weeks until Sept 12! The competition on realistic dialogue for game agents already has over 5000 submissions and the winners will also be at the workshop. Come hang out with us at EMNLP!
@rajammanabrolu
Prithviraj (Raj) Ammanabrolu
8 months
The Wordplay Workshop is back! 5th edition with EMNLP in Suzhou this Dec. We're also hosting a competition this time on making more realistic LLM powered NPCs in games! As always come by and chat all things text agents!
2
8
16
@aclmeeting
ACL 2026
5 months
๐Ÿ•Š๏ธ Lifetime Achievement Award at #ACL2025NLP A standing ovation for Prof. Kathy McKeown, recipient of the ACL 2025 Lifetime Achievement Award! ๐ŸŒŸ
1
17
125
@abeirami
Ahmad Beirami
5 months
Instead of complaining that peer review is dead, take a positive step to improve it today. The reviewers are not aliens, they are us! - Revise your review and make it clear. Identify the crucial points that impacted your score negatively and positively. - If the paper is
10
14
153
@abeirami
Ahmad Beirami
6 months
Looking for 2 emergency ACs for ACL ARR May cycle (EMNLP 2025) to oversee 2-3 papers in Conversational AI that touch on reasoning/multimodality. You should have published in EMNLP or similar venues and ideally have 5 years of experience reviewing. Email me if interested. thanks!
4
4
24
@AlexAag1234
Alex Gurung
8 months
Preprint: Can we learn to reason for story generation (~100k tokens), without reward models? Yes! We introduce an RLVR-inspired reward paradigm VR-CLI that correlates with human judgements of quality on the 'novel' task of Next-Chapter Prediction. Paper: https://t.co/eO0nUHzRjG
7
51
326
@aadhikariii
Ashutosh Adhikari
10 months
My fitness age after commencing my PhD : 18-> 21 in a matter of 4 months. Help!
0
0
0
@AlexAag1234
Alex Gurung
1 year
(1/5) How should you represent characters for long-story tasks? Our EMNLP 2024 paper proposes a new character-sheet format, called CHIRON, that can be used for both downstream tasks and story analysis. arxiv: https://t.co/YGPKYuMjAF code: https://t.co/oWP7Ur9mFf
2
6
22