Stefano Soatto, Zhuowen Tu, Qi Dong, Kunyu Shi, Luis Goncalves
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Sequence-to-sequence vision-language models are showing promise, but their applicability is limited by their inference latency due to their autoregressive way of generating predictions. We propose a parallel decoding sequence-to-sequence vision-language model, trained with a Query-CTC loss, that marginalizes over multiple inference paths in the decoder. This allows us to model the joint distribution of tokens, rather than restricting to conditional distribution as in an autoregressive model. The resulting model, NARVL, achieves performance on-par with its state-of-the-art autoregressive counterpart, but is faster at inference time, reducing from the linear complexity associated with the sequential generation of tokens to a paradigm of constant time joint inference.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.02249")
get_code_for_paper("2403.02249")
have("2403.02249")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2403.02249.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2403.02249)
Connect an agent — have() is free.