Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Saurabh Kumar

Saurabh Kumar

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

NLP×2Audio and Speech Processing×2AI×1Vision×1Multimedia×1

Frequent co-authors

Prasanta Kumar Ghosh2×
Amartyaveer1×
Sujith Pulikodan1×
Agneedh Basu1×
Pranav Bhat1×
Pavan Kumar J1×

Research Timeline

2026
FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection

The paper introduces FBHM, a new benchmark for hateful memes, and proposes LSV, a steering vector method that significantly improves VLM performance by addressing the generalization gap.

Vaani Benchmark V1.0: An Inclusive Multimodal Benchmark Dataset for Hindi

The paper introduces a new inclusive, multimodal Hindi ASR benchmark with real-world recordings and diverse demographic groups, enabling more robust and realistic evaluation.

Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion

This paper proposes a multimodal framework for jointly improving Automatic Speech Recognition (ASR) and Dialect Identification (DID) in Indian languages using a Bottleneck Encoder, RoBERTa encoder, gating mechanism, and attention encoder.

Highlighted terms show continued research focus across papers

Papers

cs.CLeess.ASEmpiricalRecentJul 3, 2026

Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion

Saurabh Kumar, Amartyaveer, Prasanta Kumar Ghosh

This paper proposes a multimodal framework for jointly improving Automatic Speech Recognition (ASR) and Dialect Identification (DID) in Indian languages using a Bottleneck Encoder, RoBERTa encoder, ga…

View →
eess.ASEmpirical
Recent
Jun 19, 2026

Vaani Benchmark V1.0: An Inclusive Multimodal Benchmark Dataset for Hindi

Sujith Pulikodan, Agneedh Basu, Saurabh Kumar, Pranav Bhat +4 more

The paper introduces a new inclusive, multimodal Hindi ASR benchmark with real-world recordings and diverse demographic groups, enabling more robust and realistic evaluation.

View →
cs.CLcs.AIcs.CVRecentMay 29, 2026

FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection

Paramananda Bhaskar, Naquee Rizwan, Daksh Jogchand, Saurabh Kumar Pandey +1 more

The paper introduces FBHM, a new benchmark for hateful memes, and proposes LSV, a steering vector method that significantly improves VLM performance by addressing the generalization gap.

View →