33 papers
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
Jordan Painter, Dipankar Srirag, Adarsh Kappiyath +3
Large language models increasingly \emph{understand} dialectal English, yet still \emph{produce} only standard, US-leaning English, leaving dialectal generation, the harder half of…
TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech
Girish A. Koushik, Helen Treharne, Diptesh Kanojia
Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interplay of audio, visual, and textua…
TeMuDance: Contrastive Alignment-Based Textual Control for Music-Driven Dance Generation
Xinran Liu, Diptesh Kanojia, Wenwu Wang +1
Existing music-driven dance generation approaches have achieved strong realism and effective audio-motion alignment. However, they generally lack semantic controllability, making i…
Improving Search Suggestions for Alphanumeric Queries
Samarth Agrawal, Jayanth Yetukuri, Diptesh Kanojia +2
Alphanumeric identifiers such as manufacturer part numbers (MPNs), SKUs, and model codes are ubiquitous in e-commerce catalogs and search. These identifiers are sparse, non linguis…
Parameter-Efficient Quality Estimation via Frozen Recursive Models
Umar Abubacar, Roman Bauer, Diptesh Kanojia
Tiny Recursive Models (TRM) achieve strong results on reasoning tasks through iterative refinement of a shared network. We investigate whether these recursive mechanisms transfer t…
MUNIChus: Multilingual News Image Captioning Benchmark
Yuji Chen, Alistair Plum, Hansi Hettiarachchi +4
The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and v…