A Aditya Bhardwaj
@aditya-bhardwaj.bsky.social
PhD student at IIIT Delhi | #NLProc #AIforHealthcare #socialcomputing
Reposted by A Aditya Bhardwaj
Scoop: The U.S. Navy has banned the use of China's DeepSeek, CNBC has learned.
In a warning issued by email, the Navy said DeepSeek's AI was not to be used "in any capacity" due to "potential security and ethical concerns associated with the model's origin and usage."
www.cnbc.com/2025/01/28/u...
In a warning issued by email, the Navy said DeepSeek's AI was not to be used "in any capacity" due to "potential security and ethical concerns associated with the model's origin and usage."
www.cnbc.com/2025/01/28/u...
U.S. Navy bans use of DeepSeek due to 'security and ethical concerns'
The U.S. Navy issued a warning to its members to avoid using DeepSeek "in any capacity," due to "potential security and ethical concerns."
www.cnbc.com
January 28, 2025 at 10:21 PM
Scoop: The U.S. Navy has banned the use of China's DeepSeek, CNBC has learned.
In a warning issued by email, the Navy said DeepSeek's AI was not to be used "in any capacity" due to "potential security and ethical concerns associated with the model's origin and usage."
www.cnbc.com/2025/01/28/u...
In a warning issued by email, the Navy said DeepSeek's AI was not to be used "in any capacity" due to "potential security and ethical concerns associated with the model's origin and usage."
www.cnbc.com/2025/01/28/u...
Reposted by A Aditya Bhardwaj
new paper is up! we look at drug-related hashtags on tiktok to see how they are used and their content. what we find? no, #tiktok users are NOT using the platform to promote harmful behavior but rather to provide support for those in #recovery, advocate for #harmreduction
arxiv.org/abs/2501.16123
arxiv.org/abs/2501.16123
From #Dr00gtiktok to #harmreduction: Exploring Substance Use Hashtags on TikTok
The rise of TikTok as a primary source of information for youth, combined with its unique short-form video format, creates urgent questions about how substance use content manifests and spreads on the...
arxiv.org
January 28, 2025 at 3:26 PM
new paper is up! we look at drug-related hashtags on tiktok to see how they are used and their content. what we find? no, #tiktok users are NOT using the platform to promote harmful behavior but rather to provide support for those in #recovery, advocate for #harmreduction
arxiv.org/abs/2501.16123
arxiv.org/abs/2501.16123
Reposted by A Aditya Bhardwaj
Our findings show a significant improvement in classifying mental health symptoms expressed in memes, highlighting the importance of integrating commonsense understanding in AI models.
Check out the full paper here: arxiv.org/abs/2501.15321
#TheWebConference #MentalHealth #NLProc #Research
3/3
Check out the full paper here: arxiv.org/abs/2501.15321
#TheWebConference #MentalHealth #NLProc #Research
3/3
Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification
The expression of mental health symptoms through non-traditional means, such as memes, has gained remarkable attention over the past few years, with users often highlighting their mental health strugg...
arxiv.org
January 29, 2025 at 4:46 AM
Our findings show a significant improvement in classifying mental health symptoms expressed in memes, highlighting the importance of integrating commonsense understanding in AI models.
Check out the full paper here: arxiv.org/abs/2501.15321
#TheWebConference #MentalHealth #NLProc #Research
3/3
Check out the full paper here: arxiv.org/abs/2501.15321
#TheWebConference #MentalHealth #NLProc #Research
3/3
Reposted by A Aditya Bhardwaj
AxiOM Dataset: A novel collection derived from the GAD questionnaire, categorizing memes into six fine-grained anxiety symptoms.
M3H Framework: A commonsense and domain-enriched approach to improve Multimodal Language Models' ability to interpret figurative language and commonsense knowledge.
2/3
M3H Framework: A commonsense and domain-enriched approach to improve Multimodal Language Models' ability to interpret figurative language and commonsense knowledge.
2/3
January 29, 2025 at 4:46 AM
AxiOM Dataset: A novel collection derived from the GAD questionnaire, categorizing memes into six fine-grained anxiety symptoms.
M3H Framework: A commonsense and domain-enriched approach to improve Multimodal Language Models' ability to interpret figurative language and commonsense knowledge.
2/3
M3H Framework: A commonsense and domain-enriched approach to improve Multimodal Language Models' ability to interpret figurative language and commonsense knowledge.
2/3
Reposted by A Aditya Bhardwaj
#WWW | Excited to share our latest research on enhancing the understanding of mental health expressions in memes!
In our paper, "Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification," we introduce...
#AI #MentalHealth #NLProc #MultimodalAnalysis
1/3
In our paper, "Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification," we introduce...
#AI #MentalHealth #NLProc #MultimodalAnalysis
1/3
January 29, 2025 at 4:46 AM
#WWW | Excited to share our latest research on enhancing the understanding of mental health expressions in memes!
In our paper, "Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification," we introduce...
#AI #MentalHealth #NLProc #MultimodalAnalysis
1/3
In our paper, "Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification," we introduce...
#AI #MentalHealth #NLProc #MultimodalAnalysis
1/3
Reposted by A Aditya Bhardwaj
#NAACL2025 | Excited to share that our work has been accepted to #Findings of NAACL 2025!
Title: Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation
Authors: Palaash Goel, Dushyant Singh Chauhan, Md Shad Akhtar
#NAACL2025 #NLProc
1/2
Title: Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation
Authors: Palaash Goel, Dushyant Singh Chauhan, Md Shad Akhtar
#NAACL2025 #NLProc
1/2
January 23, 2025 at 8:52 AM
#NAACL2025 | Excited to share that our work has been accepted to #Findings of NAACL 2025!
Title: Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation
Authors: Palaash Goel, Dushyant Singh Chauhan, Md Shad Akhtar
#NAACL2025 #NLProc
1/2
Title: Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation
Authors: Palaash Goel, Dushyant Singh Chauhan, Md Shad Akhtar
#NAACL2025 #NLProc
1/2
Reposted by A Aditya Bhardwaj
#WWW2025 | Happy to announce that our work has been accepted for #oral presentation at TheWebConf 2025 🎉
Title: Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification
Stay tuned for preprint on our lab's webpage: @flamenlp
#theWebConf #nlproc #mentalhealth
Title: Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification
Stay tuned for preprint on our lab's webpage: @flamenlp
#theWebConf #nlproc #mentalhealth
January 22, 2025 at 6:31 AM
#WWW2025 | Happy to announce that our work has been accepted for #oral presentation at TheWebConf 2025 🎉
Title: Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification
Stay tuned for preprint on our lab's webpage: @flamenlp
#theWebConf #nlproc #mentalhealth
Title: Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification
Stay tuned for preprint on our lab's webpage: @flamenlp
#theWebConf #nlproc #mentalhealth