| |
|
AI/ML Lecture & Mixer
|
| With Zayne Sprague (Courant Inst of Mathematical Sciences). |
|
Oct 14 (Wed) @ 05:00 PM
FREE
| | Amazon JFK27 Hank, 12 W 39th St
|
|
|
|
|
| |
| Register |
|
|
| |
A monthly ML research colloquium by the New York Machine Learning Research Guild - this session in collaboration with our partner, CUNY Tech Prep.
Speaker: Zayne Sprague PhD Researcher, Courant Institute of Mathematical Sciences, NYU & Google
Topic: From Chain of Thought to Agent Swarms: A Brief Story on Reasoning in LLMs
Giving language models more time to think has produced substantial gains, but in targeted domains, & the benefits appear to remain uneven across tasks. This talk explores how models can use additional computation at inference time effectively, reviewing the progression from prompt based methods to multi-agent systems. We will begin with chain-of-thought prompting, asking a model to think before giving a final answer, presenting our work showing that chain-of-thought prompting has its strongest benefits concentrated in mathematics & symbolic reasoning. These domains also share a practical advantage: answers can often be checked automatically, providing feedback that can be used to train models through reinforcement learning. This leads us to SkillFactory, where we use a model's own successful & unsuccessful attempts to construct training examples that demonstrate checking answers & retrying. Combining supervised finetuning on these examples with reinforcement learning helps models develop these behaviors & generalize to harder problems. Finally, we will discuss recent work on agent swarms, exploring how reasoning can scale in parallel & what role verification can play in making that additional computation useful.
This session is a close-quarters look at that work, with plenty of room to push back & dig in.
# Who this is for
NY-MLR colloquia are small by design. The room is capped, & we keep it that way so the discussion stays substantive & everyone in it can contribute.
We'd love to see you if you're:
- A practitioner working seriously on ML, in industry or in a lab
- A researcher or graduate student in ML, NLP, or an adjacent field
- A highly motivated student or self-directed learner of any age or background, with real depth of interest
# Schedule
5:00 - 5:30 PM - Doors open, arrivals, mingling
5:30 - 6:30 PM - Speaker Lecture
6:30 - 7:00 PM - Moderated Q&A
7:00 - 8:00 PM - After hours, mingling, wind-down
8:00 PM - Lights out
Venue: Amazon JFK27 ("Hank") 12 W 39th St, New York, NY 10018
|
|
|
|
|
|
|
|
