Differences

This shows you the differences between two versions of the page.

--- trans_learn:reading_group_2024_spring [2024/03/13 04:11] – yang
+++ trans_learn:reading_group_2024_spring [2024/07/17 05:08] (current) – chekaki
@@ Line 2: / Line 2: @@
-  * **Location**: Info Building 807
+  * **Location**: Info Building 809
   * **Time**: Wednesday 4:30pm (biweekly)
-==== Schedule ====
+===== Schedule =====
 Please sign up here:
 [[https://docs.qq.com/sheet/DQ0xsY1p2TEFoVXNo?tab=fn20u6 | 2024 Spring Reading Group Schdule]]
-==== Format ====
-This year, we adopt a new discussion format called ``role-play seminar''. Instead of the traditional one-to-many style, ``role-play seminar'' encourages everyone to participate in discussion by taking a specific role. The roles will rotate in each meeting.  Below are the description of each role:
+===== Topic =====
+We will focus on the following topics for this year's reading group
+  * Efficient adaptation of LLM & foundation models cross domains and tasks
+  * Learning to transfer for continuous adaptation  (with a focus on domain dynamics learning)
+  * Impactful application of above topics in the medical domain
+The selected paper should have been a seminal work in its filed or a representative of the state-of-the-arts that made large impact. This rule can be relaxed if the paper is highly relevant to our current line of research. We would also prefer works that are well-written with good theoretical support.
+-----------------------------
+===03/13/2024===
+  * Presenter: Xuechao Chen
+  * Paper: LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS
+  * Slides: {{ :trans_learn:paperreading_lora.pptx |}}
+===03/27/2024===
+  * Presenter: Hanbing Liu
+  * Paper:
+  * Slides:
+===04/10/2024===
+  * Presenter: Jingyun Yang
+  * Paper: Learning to Route Among Specialized Experts for Zero-Shot Generalization
+  * Slides:{{ :trans_learn:reading_group_240410.pptx |}}
+===05/15/2024===
+  * Presenter: Xiangyu Chen
+  * Paper: Merging by Matching Models in Task Parameter Subspaces
+  * Slides:{{ :trans_learn:model_merging_240515.pptx |}}
+===06/19/2024===
+  * Presenter: Haohua Wang
+  * Paper: Direct Preference Optimization: Your Language Model is Secretly a Reward Model
+  * Slides:{{ :|}}
+-----------------------------
+===== Format =====
+This year, we adopt a new discussion format called  **role-playing seminar**. Instead of the traditional one-to-many style, Role-playing seminar encourages everyone to participate in the discussion by taking on a specific role. The roles will rotate in each meeting.  Below is a summary of what participants in each role should prepare before the seminar.  For more information, please check out [[https://colinraffel.com/blog/role-playing-seminar.html | the creator's blogpost]].
 ==== Lead ====
-  Summarize the paper and its main claims and contributions. What problem is the paper trying to solve? Why is that problem interesting and important? How does the paper solve the problem and what is the novelty?
+Summarize the paper and its main claims and contributions. What problem is the paper trying to solve? Why is that problem interesting and important? How does the paper solve the problem and what is the novelty?
 ==== Scientific Peer Reviewer ====
- The paper has not been published yet and is currently submitted to a top conference where you’ve been assigned as a peer reviewer. Evaluate the paper's strengths and weaknesses including the technical novelty, clarity of exposition, magnitude of impact, and reproducibility.
+The paper has not been published yet and is currently submitted to a top conference where you’ve been assigned as a peer reviewer. Evaluate the paper's strengths and weaknesses including the technical novelty, clarity of exposition, magnitude of impact, and reproducibility.
 ==== Archaeologist ====