Home Knowledge Base CTC

CTC

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Reconsidering Positional Supervision in Masked Diffusion Language Model Training

Announce Type: replace Abstract: Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive language models. They can be viewed as parallel decoders trained with a position-wise cross-entropy (CE) loss, the same setup as non-autoregressive translation (NAT). In NAT, CE-trained parallel decoders have been argued to be sensitive to small positional shifts, since CE penalizes them harshly.

arXiv CS 8d ago

TurboTax Full Service Coupons This June

TurboTax has been my go-to for self-filing taxes for years. It’s good enough for me—and literally millions of other users. TurboTax has quickly become a favorite among users for its easy-to-use self-filing services, along with easy access to assistance from tax professionals.

Wired 6d ago

WAXAL-NET: Finetuned Edge ASR Across 19 African Languages

arXiv:2606.02375v1 Announce Type: new Abstract: We evaluate whether compact domain-specialized ASR models can outperform massively multilingual foundation models for conversational African speech across 19 languages in the WAXAL corpus. Fine-tuned edge models achieve a macro-averaged WER of $38.0\%$ compared to $64.9\%$ for the best zero-shot baseline, a $26.9$ percentage-point reduction using models $3-40\times$ smaller. Results confirm that domain specialization dominates scale for...

arXiv CS 8d ago

Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers

arXiv:2606.04678v1 Announce Type: new Abstract: End-to-end ASR systems typically use fixed-depth acoustic encoders at inference, making it difficult to trade additional test-time computation for improved recognition without training a larger model. A natural approach is to reuse a shared Transformer block recurrently, but we find that naive looping does not fully exploit additional recurrent compute. We introduce LARM, a depth-conditioned looped Transformer that turns recurrent encoder depth...

arXiv CS 6d ago