Sonal Kumar
27 papers · 2021–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
π Cross-Pollinator (14) π Conference Polyglot (9) π Interdisciplinary Bridge π§ Keyword Pioneer π Academic Marathon (5)
π
Academic Marathon
(5)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(40)
π§¬
Topic Evolution
π€
Dynamic Duo
(26)
π₯
Mega-Team
(34)
π¬
Deep Specialist
(11)
π₯
Unstoppable
(5)
ποΈ
Keyword Collector
(105)
π
Century Club
(26)
β
The Questioner
(5)
β‘
Prolific Year
(9)
Conferences
EMNLP (6)
NAACL (5)
ACL (4)
ICLR (4)
ICML (2)
INTERSPEECH (2)
AAAI (1)
CVPR (1)
IJCNLP (1)
SEMEVAL (1)
Top co-authors
Keywords
data augmentation
(5)
multimodal learning
(5)
transformer model
(4)
sequence tagging
(3)
benchmark evaluation
(3)
large language model
(3)
toxic span detection
(3)
dependency parsing
(3)
audio-language model
(3)
biaffine attention
(3)
biaffine model
(2)
contrastive learning
(2)
visual cue
(2)
span extraction
(2)
text classification
(2)
low-resource setting
(2)
automatic speech recognition
(2)
text generation
(1)
named entity recognition
(1)
transfer learning
(1)
Papers
MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence
AAAI 2026
MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark
ICLR 2025
EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding
EMNLP 2025
MULTIVOX: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions
EMNLP 2025
Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
ICLR 2025
Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data
ICLR 2025
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
ICML 2025
PAT: Parameter-Free Audio-Text Aligner to Boost Zero-Shot Audio Classification
NAACL 2025
ProSE: Diffusion Priors for Speech Enhancement
NAACL 2025
Do Audio-Language Models Understand Linguistic Variations?
NAACL 2025
Do Vision-Language Models Understand Compound Nouns?
NAACL 2024
CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models
ICLR 2024
CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP
NAACL 2024
A Closer Look at the Limitations of Instruction Tuning
ICML 2024
ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions
ACL 2024
ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations
ACL 2024
AV-RIR: Audio-Visual Room Impulse Response Estimation
CVPR 2024
GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities
EMNLP 2024
EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning
EMNLP 2024
LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition
INTERSPEECH 2024
CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network
EMNLP 2023
DALE: Generative Data Augmentation for Low-Resource Legal NLP
EMNLP 2023
ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER
ACL 2023
Span Classification with Structured Information for Disfluency Detection in Spoken Utterances
INTERSPEECH 2022
Cisco at SemEval-2021 Task 5: Whatβs Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments
SEMEVAL 2021
Cisco at SemEval-2021 Task 5: Whatβs Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments
ACL 2021
Cisco at SemEval-2021 Task 5: Whatβs Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments
IJCNLP 2021