5 papers
FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS
Harshit Singh, Ayush Pratap Singh, Nityanand Mathur
Flow-matching text-to-speech systems achieve remarkable zero-shot quality but remain static after deployment: pronunciation errors on out-of-vocabulary proper nouns persist unless…
DISK: Dynamic Inference SKipping for World Models
Anugunj Naman, Gaibo Zhang, Ayushman Singh +1
We present DISK, a training-free adaptive inference method for autoregressive world models. DISK coordinates two coupled diffusion transformers for video and ego-trajectory via dua…
SonoEdit: Null-Space Constrained Knowledge Editing for Pronunciation Correction in LLM-Based TTS
Ayush Pratap Singh, Harshit Singh, Nityanand Mathur +2
Neural text-to-speech (TTS) systems systematically mispronounce low-resource proper nouns, particularly non-English names, brands, and geographic locations, due to their underrepre…
Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization
Kushal Chawla, Chenyang Zhu, Pengshan Cai +9
Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically…
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
Samuel Cahyawijaya, Holy Lovenia, Joel Ruben Antony Moniz +89
Southeast Asia (SEA) is a region of extraordinary linguistic and cultural diversity, yet it remains significantly underrepresented in vision-language (VL) research. This often resu…