ReALM: Reference Resolution As Language Modeling · HackerPapers discussions

ReALM: Reference Resolution As Language Modeling — mentioned by alwillis

Thu, 11 Apr 2024 23:43:04 GMT

> This makes total sense but does it? Does Apple really have an application roadmap to ultimately utilize these tensor cores? Apple always does things in a holistic way. They wouldn't put these AI cores in their devices if they didn't also have a software strategy to go along with it. Unlike with most companies, AI won't be bolted on; it'll well-integrated into the operating system. For example, they've been working on LLMs[1]: > We demonstrate large improvements over an existing system with similar functionality across different types of references, with our smallest model obtaining absolute…

Paper and discussion history. A mention is not an endorsement.

ReALM: Reference Resolution As Language Modeling — mentioned by curious_cat_163

Thu, 11 Apr 2024 22:18:21 GMT

> Apple also plans to add a much improved Neural Engine that has an increased number of cores for AI tasks. This makes total sense but does it? Does Apple really have an application roadmap to ultimately utilize these tensor cores? For all the M1, M2, M3s out there, Siri still sucks. We keep seeing latest arXiv papers [1] coming out of their research efforts hinting at potential improvements but there is not much in those papers that needs to wait for an M4 or M5... What gives? [1] https://arxiv.org/abs/2403.20329

Paper and discussion history. A mention is not an endorsement.

ReALM: Reference Resolution As Language Modeling — mentioned by Someone

Wed, 03 Apr 2024 18:46:07 GMT

> Apple has released ReALM (Reference Resolution As Language Modeling) Interesting use of the word “released”. As far as I can tell, they published a paper (https://arxiv.org/abs/2403.20329), but didn’t release their model, nor their training set, nor their code. All we have is a rough description of the approach and numbers measuring how well it works. I wouldn’t know whether it’s easy or difficult to reproduce their results, but they don’t make that easy. Edit: other articles use ‘reveal’, not ‘release’. That’s a bit better, but IMO still a bit too optimistic.

Paper and discussion history. A mention is not an endorsement.

ReALM: Reference Resolution As Language Modeling — mentioned by turnsout

Wed, 03 Apr 2024 15:10:47 GMT

This is the frontier—tiny, specialized models like this and ReALM [0], coupled to the application logic and able to run on-device. Eventually devices will be powerful enough to run more general purpose models locally, but for high-frequency user tasks with a low tolerance for error, smaller specialized models may always win. [0]: https://arxiv.org/abs/2403.20329

Paper and discussion history. A mention is not an endorsement.

ReALM: Reference Resolution As Language Modeling — HN submission

Tue, 02 Apr 2024 23:26:37 GMT

ReALM: Reference Resolution as Language Modeling

140 points; 15 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReALM: Reference Resolution As Language Modeling — HN submission

Tue, 02 Apr 2024 12:58:19 GMT

ReALM: Reference Resolution as Language Modeling

12 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

ReALM: Reference Resolution As Language Modeling — HN submission

Mon, 01 Apr 2024 22:51:06 GMT

ReALM: Reference Resolution as Language Modeling

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.