Sonal Kumar

73 papers A* 15A 2Misc 4Journal 38Unranked 14
YearRankTypeTitle / Venue / Authors
2026 J jnl
Audio Hallucination Attacks: Probing the Reliability of Large Audio Language Models.
CoRR
Ashish Seth, Sonal Kumar, Ramaneswaran Selvakumar, Nishit Anand, Utkarsh Tyagi, Prem Seetharaman, Ramani Duraiswami, Dinesh Manocha
2026 A* conf
MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence.
AAAI
Sonal Kumar, Simon Sedlácek, Vaibhavi Lokegaonkar, Fernando López, Wenyi Yu, Nishit Anand, Hyeonggon Ryu, Lichang Chen, Maxim Plicka, Miroslav Hlavácek, William Fineas Ellingwood, Sathvik Udupa, Siyuan Hou, Allison Ferner, Sara Barahona, Cecilia Bolaños, Satish Rahi, Laura Herrera-Alarcón, Satvik Dixit, Rupali S. Patil, Soham Deshmukh, Lasha Koroshinadze, Yao Liu, Leibny Paola García-Perera, Eleni Zanou, Themos Stafylakis, Joon Son Chung, David Harwath, Chao Zhang, Dinesh Manocha, Alicia Lozano-Diez, Santosh Kesiraju, Sreyan Ghosh, Ramani Duraiswami
2026 J jnl
TAC: Timestamped Audio Captioning.
CoRR
Sonal Kumar, Prem Seetharaman, Ke Chen, Oriol Nieto, Jiaqi Su, Zhepei Wang, Rithesh Kumar, Dinesh Manocha, Nicholas J. Bryan, Zeyu Jin, Justin Salamon
2025 A* conf
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities.
ICML
Sreyan Ghosh, Zhifeng Kong, Sonal Kumar, S. Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle, Dinesh Manocha, Bryan Catanzaro
2025 J jnl
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities.
CoRR
Sreyan Ghosh, Zhifeng Kong, Sonal Kumar, S. Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle, Dinesh Manocha, Bryan Catanzaro
2025 J jnl
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models.
CoRR
Arushi Goel, Sreyan Ghosh, Jaehyeon Kim, Sonal Kumar, Zhifeng Kong, Sang-gil Lee, Chao-Han Huck Yang, Ramani Duraiswami, Dinesh Manocha, Rafael Valle, Bryan Catanzaro
2025 J jnl
C-LEAD: Contrastive Learning for Enhanced Adversarial Defense.
CoRR
Suklav Ghosh, Sonal Kumar, Arijit Sur
2025 — conf
Do Audio-Language Models Understand Linguistic Variations?
NAACL (Short Papers)
Ramaneswaran Selvakumar, Sonal Kumar, Hemant Kumar Giri, Nishit Anand, Ashish Seth, Sreyan Ghosh, Dinesh Manocha
2025 A* conf
EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding.
EMNLP
Ashish Seth, Utkarsh Tyagi, Ramaneswaran Selvakumar, Nishit Anand, Sonal Kumar, Sreyan Ghosh, Ramani Duraiswami, Chirag Agarwal, Dinesh Manocha
2025 J jnl
EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding.
CoRR
Ashish Seth, Utkarsh Tyagi, Ramaneswaran Selvakumar, Nishit Anand, Sonal Kumar, Sreyan Ghosh, Ramani Duraiswami, Chirag Agarwal, Dinesh Manocha
2025 J jnl
MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence.
CoRR
Sonal Kumar, Simon Sedlácek, Vaibhavi Lokegaonkar, Fernando López, Wenyi Yu, Nishit Anand, Hyeonggon Ryu, Lichang Chen, Maxim Plicka, Miroslav Hlavácek, William Fineas Ellingwood, Sathvik Udupa, Siyuan Hou, Allison Ferner, Sara Barahona, Cecilia Bolaños, Satish Rahi, Laura Herrera-Alarcón, Satvik Dixit, Rupali S. Patil, Soham Deshmukh, Lasha Koroshinadze, Yao Liu, Leibny Paola García-Perera, Eleni Zanou, Themos Stafylakis, Joon Son Chung, David Harwath, Chao Zhang, Dinesh Manocha, Alicia Lozano-Diez, Santosh Kesiraju, Sreyan Ghosh, Ramani Duraiswami
2025 A* conf
MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark.
ICLR
S. Sakshi, Utkarsh Tyagi, Sonal Kumar, Ashish Seth, Ramaneswaran Selvakumar, Oriol Nieto, Ramani Duraiswami, Sreyan Ghosh, Dinesh Manocha
2025 A* conf
MULTIVOX: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions.
EMNLP
Ramaneswaran Selvakumar, Ashish Seth, Nishit Anand, Utkarsh Tyagi, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha
2025 J jnl
Multi-Domain Audio Question Answering Toward Acoustic Content Reasoning in The DCASE 2025 Challenge.
CoRR
Chao-Han Huck Yang, Sreyan Ghosh, Qing Wang, Jaeyeon Kim, Hengyi Hong, Sonal Kumar, Guirui Zhong, Zhifeng Kong, Sakshi Singh, Vaibhavi Lokegaonkar, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha, Gunhee Kim, Jun Du, Rafael Valle, Bryan Catanzaro
2025 J jnl
MultiVox: Benchmarking Voice Assistants for Multimodal Interactions.
CoRR
Ramaneswaran Selvakumar, Ashish Seth, Nishit Anand, Utkarsh Tyagi, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha
2025 — conf
PAT: Parameter-Free Audio-Text Aligner to Boost Zero-Shot Audio Classification.
NAACL (Long Papers)
Ashish Seth, Ramaneswaran Selvakumar, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha
2025 — conf
ProSE: Diffusion Priors for Speech Enhancement.
NAACL (Long Papers)
Sonal Kumar, Sreyan Ghosh, Utkarsh Tyagi, Anton Jeran Ratnarajah, Chandra Kiran Reddy Evuru, Ramani Duraiswami, Dinesh Manocha
2025 Misc conf
ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds.
ICASSP
Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
2025 Misc conf
River-GEM: Generating and Enhancing Muddy Water Images.
ICASSP
Alik Pramanick, Chivukula Sairam Satwik, Sonal Kumar, Akshay Daydar, Arijit Sur
2025 — conf
SILA: Signal-to-Language Augmentation for Enhanced Control in Text-to-Audio Generation.
WASPAA
Sonal Kumar, Prem Seetharaman, Justin Salamon, Dinesh Manocha, Oriol Nieto
2025 A* conf
Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data.
ICLR
Sreyan Ghosh, Sonal Kumar, Zhifeng Kong, Rafael Valle, Bryan Catanzaro, Dinesh Manocha
2025 A* conf
Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs.
ICLR
Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Oriol Nieto, Zeyu Jin, Dinesh Manocha
2024 A* conf
A Closer Look at the Limitations of Instruction Tuning.
ICML
Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Ramaneswaran S., Deepali Aneja, Zeyu Jin, Ramani Duraiswami, Dinesh Manocha
2024 J jnl
A Closer Look at the Limitations of Instruction Tuning.
CoRR
Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Ramaneswaran S., Deepali Aneja, Zeyu Jin, Ramani Duraiswami, Dinesh Manocha
2024 — conf
ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions.
ACL (1)
Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Chandra Kiran Reddy Evuru, Ramaneswaran S., S. Sakshi, Dinesh Manocha
2024 J jnl
ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions.
CoRR
Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Chandra Kiran Reddy Evuru, S. Ramaneswaran, Sakshi Singh, Dinesh Manocha
2024 — conf
ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations.
ACL (Findings)
Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, S. Sakshi, Sanjoy Chowdhury, Dinesh Manocha
2024 A* conf
AV-RIR: Audio-Visual Room Impulse Response Estimation.
CVPR
Anton Ratnarajah, Sreyan Ghosh, Sonal Kumar, Purva Chiniya, Dinesh Manocha
2024 — conf
CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP.
NAACL-HLT (Findings)
Chandra Kiran Reddy Evuru, Sreyan Ghosh, Sonal Kumar, Ramaneswaran S., Utkarsh Tyagi, Dinesh Manocha
2024 J jnl
CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP.
CoRR
Chandra Kiran Reddy Evuru, Sreyan Ghosh, Sonal Kumar, Ramaneswaran S., Utkarsh Tyagi, Dinesh Manocha
2024 A* conf
CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models.
ICLR
Sreyan Ghosh, Ashish Seth, Sonal Kumar, Utkarsh Tyagi, Chandra Kiran Reddy Evuru, Ramaneswaran S., Sakshi Singh, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
2024 J jnl
DatUS: Data-Driven Unsupervised Semantic Segmentation With Pretrained Self-Supervised Vision Transformer.
IEEE Trans. Cogn. Dev. Syst.
Sonal Kumar, Arijit Sur, Rashmi Dutta Baruah
2024 J jnl
DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer.
CoRR
Sonal Kumar, Arijit Sur, Rashmi Dutta Baruah
2024 J jnl
Do Audio-Language Models Understand Linguistic Variations?
CoRR
Ramaneswaran Selvakumar, Sonal Kumar, Hemant Kumar Giri, Nishit Anand, Ashish Seth, Sreyan Ghosh, Dinesh Manocha
2024 — conf
Do Vision-Language Models Understand Compound Nouns?
NAACL (Short Papers)
Sonal Kumar, Sreyan Ghosh, S. Sakshi, Utkarsh Tyagi, Dinesh Manocha
2024 J jnl
Do Vision-Language Models Understand Compound Nouns?
CoRR
Sonal Kumar, Sreyan Ghosh, Sakshi Singh, Utkarsh Tyagi, Dinesh Manocha
2024 A* conf
EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning.
EMNLP
Ashish Seth, Ramaneswaran Selvakumar, S. Sakshi, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha
2024 J jnl
EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning.
CoRR
Ashish Seth, Ramaneswaran Selvakumar, S. Sakshi, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha
2024 A* conf
GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities.
EMNLP
Sreyan Ghosh, Sonal Kumar, Ashish Seth, Chandra Kiran Reddy Evuru, Utkarsh Tyagi, S. Sakshi, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
2024 J jnl
GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities.
CoRR
Sreyan Ghosh, Sonal Kumar, Ashish Seth, Chandra Kiran Reddy Evuru, Utkarsh Tyagi, Sakshi Singh, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
2024 — conf
GraPix: Exploring Graph Modularity Optimization for Unsupervised Pixel Clustering.
ICPR (10)
Sonal Kumar, Arijit Sur, Rashmi Dutta Baruah
2024 Misc conf
IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation.
ICASSP
Sonal Kumar, Anirudh Phukan, Arijit Sur
2024 A conf
LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition.
INTERSPEECH
Sreyan Ghosh, Sonal Kumar, Ashish Seth, Purva Chiniya, Utkarsh Tyagi, Ramani Duraiswami, Dinesh Manocha
2024 J jnl
LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition.
CoRR
Sreyan Ghosh, Sonal Kumar, Ashish Seth, Purva Chiniya, Utkarsh Tyagi, Ramani Duraiswami, Dinesh Manocha
2024 J jnl
MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark.
CoRR
S. Sakshi, Utkarsh Tyagi, Sonal Kumar, Ashish Seth, Ramaneswaran Selvakumar, Oriol Nieto, Ramani Duraiswami, Sreyan Ghosh, Dinesh Manocha
2024 — conf
Med-SeAM: Medical Context Aware Self-Supervised Learning Framework for Anomaly Classification in Knee MRI.
ICVGIP
Akshay Daydar, Ajay Kumar Reddy, Sonal Kumar, Arijit Sur, Hanif Laskar
2024 J jnl
PAT: Parameter-Free Audio-Text Aligner to Boost Zero-Shot Audio Classification.
CoRR
Ashish Seth, Ramaneswaran Selvakumar, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha
2024 J jnl
ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds.
CoRR
Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
2024 Misc conf
Recap: Retrieval-Augmented Audio Captioning.
ICASSP
Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru, Ramani Duraiswami, Dinesh Manocha
2024 J jnl
SILA: Signal-to-Language Augmentation for Enhanced Control in Text-to-Audio Generation.
CoRR
Sonal Kumar, Prem Seetharaman, Justin Salamon, Dinesh Manocha, Oriol Nieto
2024 J jnl
Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data.
CoRR
Sreyan Ghosh, Sonal Kumar, Zhifeng Kong, Rafael Valle, Bryan Catanzaro, Dinesh Manocha
2024 J jnl
VDGD: Mitigating LVLM Hallucinations in Cognitive Prompts by Bridging the Visual Perception Gap.
CoRR
Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Oriol Nieto, Zeyu Jin, Dinesh Manocha
2023 — conf
ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER.
ACL (1)
Sreyan Ghosh, Utkarsh Tyagi, Manan Suri, Sonal Kumar, Ramaneswaran S., Dinesh Manocha
2023 J jnl
ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER.
CoRR
Sreyan Ghosh, Utkarsh Tyagi, Manan Suri, Sonal Kumar, Ramaneswaran S., Dinesh Manocha
2023 J jnl
ASPIRE: Language-Guided Augmentation for Robust Image Classification.
CoRR
Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Sakshi Singh, Sanjoy Chowdhury, Dinesh Manocha
2023 J jnl
AV-RIR: Audio-Visual Room Impulse Response Estimation.
CoRR
Anton Ratnarajah, Sreyan Ghosh, Sonal Kumar, Purva Chiniya, Dinesh Manocha
2023 A* conf
BioAug: Conditional Generation based Data Augmentation for Low-Resource Biomedical NER.
SIGIR
Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha
2023 J jnl
BioAug: Conditional Generation based Data Augmentation for Low-Resource Biomedical NER.
CoRR
Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha
2023 A* conf
CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network.
EMNLP
Sreyan Ghosh, Manan Suri, Purva Chiniya, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha
2023 J jnl
CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network.
CoRR
Sreyan Ghosh, Manan Suri, Purva Chiniya, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha
2023 J jnl
CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models.
CoRR
Sreyan Ghosh, Ashish Seth, Sonal Kumar, Utkarsh Tyagi, Chandra Kiran Reddy Evuru, Ramaneswaran S., Sakshi Singh, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
2023 A* conf
DALE: Generative Data Augmentation for Low-Resource Legal NLP.
EMNLP
Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Ramaneswaran S., Sakshi Singh, Utkarsh Tyagi, Dinesh Manocha
2023 J jnl
DALE: Generative Data Augmentation for Low-Resource Legal NLP.
CoRR
Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Ramaneswaran S., Sakshi Singh, Utkarsh Tyagi, Dinesh Manocha
2023 J jnl
RECAP: Retrieval-Augmented Audio Captioning.
CoRR
Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru, Ramani Duraiswami, Dinesh Manocha
2022 J jnl
A novel multimodal dynamic fusion network for disfluency detection in spoken utterances.
CoRR
Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Manan Suri, Rajiv Ratn Shah
2022 J jnl
BSSFFS: blockchain-based sybil-secured smart forest fire surveillance.
J. Ambient Intell. Humaniz. Comput.
Sreemana Datta, Sonal Kumar, Ditipriya Sinha, Ayan Kumar Das
2022 A conf
Span Classification with Structured Information for Disfluency Detection in Spoken Utterances.
INTERSPEECH
Sreyan Ghosh, Sonal Kumar, Yaman Kumar, Rajiv Ratn Shah, Srinivasan Umesh
2022 J jnl
Span Classification with Structured Information for Disfluency Detection in Spoken Utterances.
CoRR
Sreyan Ghosh, Sonal Kumar, Yaman Kumar Singla, Rajiv Ratn Shah, Srinivasan Umesh
2021 J jnl
Cisco at AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides using Contextualised Embeddings.
CoRR
Sreyan Ghosh, Sonal Kumar, Harsh Jalan, Hemant Yadav, Rajiv Ratn Shah
2021 — conf
Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments.
SemEval@ACL/IJCNLP
Sreyan Ghosh, Sonal Kumar
2021 J jnl
Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments.
CoRR
Sreyan Ghosh, Sonal Kumar
2020 — conf
Blockchain-Based Sybil-Secure Data Transmission (SSDT) IoT Framework for Smart City Applications.
FICTA (1)
Sonal Kumar, Ayan Kumar Das, Ditipriya Sinha
2009 — conf
Enabling web services for Classification of Satellite Image.
SWWS
Sonal Kumar, Daya Gupta, V. K. Panchal, Shashi Kumar