Skip to content

Commit c759b45

Browse files
csinvacsinva
committed
add new paper links
1 parent 8fe6cfd commit c759b45

File tree

3 files changed

+64
-12
lines changed

3 files changed

+64
-12
lines changed

‎_includes/01_research.html

Lines changed: 53 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -168,24 +168,54 @@ <h2 style="text-align: center; margin-top: -150px;"> Research</h2>
168168
<tbody>
169169
<tr>
170170
<td class="center">'25</td>
171-
<td>Vector-ICL: In-context Learning with Continuous Vector Representations
171+
<td>Systematic Bias in Clinical Decision Instrument Development
172172
</td>
173-
<td>zhuang et al.</td>
174-
<td class="med">🔎🌀</td>
175-
<td class="center"><a href="https://arxiv.org/abs/2410.05629">iclr</a></td>
176-
<td class="big"><a href="https://github.com/EvanZhuang/vector-icl"><i class="fa fa-github fa-fw"></i></a>
173+
<td>obra, singh, et al.</td>
174+
<td class="med">🔎💊</td>
175+
<td class="center"><a href="https://www.medrxiv.org/content/10.1101/2025.02.12.25320965v1">medrxiv</a></td>
176+
<td class="big"><a href="https://github.com/csinva/clinical-rule-analysis"><i
177+
class="fa fa-github fa-fw"></i></a>
177178
</td>
179+
178180
<td class="med">
179181
</td>
180182
</tr>
181183
<tr>
182-
<td class="center">'24</td>
183-
<td>Interpretable Language Modeling via Induction-head Ngram Models
184+
<td class="center">'25</td>
185+
<td>Analyzing patient perspectives with llms
184186
</td>
185-
<td>kim*, mantena*, et al.</td>
186-
<td class="med">🧠🔎🌀</td>
187-
<td class="center"><a href="https://arxiv.org/abs/2411.00066">arxiv</a></td>
188-
<td class="big"><a href="https://github.com/ejkim47/induction-gram"><i class="fa fa-github fa-fw"></i></a>
187+
<td>kornblith*, singh* et al.</td>
188+
<td class="med">💊🌀</td>
189+
<td class="center"><a href="https://www.nature.com/articles/s41598-025-89996-w">nature scientific
190+
reports</a></td>
191+
<td class="big"><a href="https://github.com/csinva/pedidose-efic-analysis"><i
192+
class="fa fa-github fa-fw"></i></a>
193+
</td>
194+
195+
<td class="med">
196+
</td>
197+
</tr>
198+
<tr>
199+
<td class="center">'25</td>
200+
<td>Simplifying DINO via Coding Rate Regularization
201+
</td>
202+
<td>wu et al.</td>
203+
<td class="med">🌀</td>
204+
<td class="center"><a href="https://arxiv.org/abs/2502.10385">arxiv</a></td>
205+
<td class="big"><a href="https://github.com/RobinWu218/SimDINO"><i class="fa fa-github fa-fw"></i></a><a
206+
href="https://robinwu218.github.io/SimDINO/"><i class="fa fa-home fa-fw"></i></a>
207+
</td>
208+
<td class="med">
209+
</td>
210+
</tr>
211+
<tr>
212+
<td class="center">'25</td>
213+
<td>Vector-ICL: In-context Learning with Continuous Vector Representations
214+
</td>
215+
<td>zhuang et al.</td>
216+
<td class="med">🔎🌀</td>
217+
<td class="center"><a href="https://arxiv.org/abs/2410.05629">iclr</a></td>
218+
<td class="big"><a href="https://github.com/EvanZhuang/vector-icl"><i class="fa fa-github fa-fw"></i></a>
189219
</td>
190220
<td class="med">
191221
</td>
@@ -218,6 +248,18 @@ <h2 style="text-align: center; margin-top: -150px;"> Research</h2>
218248
class="fa fa-desktop fa-fw"></i></a>
219249
</td>
220250
</tr>
251+
<tr>
252+
<td class="center">'24</td>
253+
<td>Interpretable Language Modeling via Induction-head Ngram Models
254+
</td>
255+
<td>kim*, mantena*, et al.</td>
256+
<td class="med">🧠🔎🌀</td>
257+
<td class="center"><a href="https://arxiv.org/abs/2411.00066">arxiv</a></td>
258+
<td class="big"><a href="https://github.com/ejkim47/induction-gram"><i class="fa fa-github fa-fw"></i></a>
259+
</td>
260+
<td class="med">
261+
</td>
262+
</tr>
221263
<tr>
222264
<td class="center">'24</td>
223265
<td>Rethinking Interpretability in the Era of Large Language Models

‎_notes/neuro/comp_neuro.md

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1096,6 +1096,11 @@ subtitle: Diverse notes on various topics in computational neuro, data-driven ne
10961096
- A variational autoencoder provides novel, data-driven features that explain functional brain representations in a naturalistic navigation task ([cho, zhang, & gallant, 2023](https://jov.arvojournals.org/article.aspx?articleid=2792546))
10971097
- What's the Opposite of a Face? Finding Shared Decodable Concepts and their Negations in the Brain ([efird...fyshe, 2024](https://arxiv.org/abs/2405.17663)) - build clustering shared across subjects in CLIP space
10981098

1099+
## speech
1100+
1101+
- Improving semantic understanding in speech language models via brain-tuning ([moussa, klakow, & toneva, 2024](https://arxiv.org/abs/2410.09230))
1102+
- BrainWavLM: Fine-tuning Speech Representations with Brain Responses to Language ([vattikonda, vaidya, antonello, & huth, 2025](https://arxiv.org/abs/2502.08866))
1103+
10991104

11001105
# advanced topics
11011106

‎_notes/research_ovws/ovw_llms.md

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1367,11 +1367,14 @@ mixture of experts models have become popular because of the need for (1) fast s
13671367
- BioTranslator: Multilingual translation for zero-shot biomedical classification ([xu, woicik, poon, altman, & wang, 2023](https://www.nature.com/articles/s41467-023-36476-2)) - takes a user- written textual description of a new concept and then translates this description to a non-text biological data instance
13681368
- results for biological data, e.g. genes, proteins
13691369
- enables the identification of novel cell types using only a textual description
1370-
- Learning to Generate Novel Scientific Directions with Contextualized Literature-based Discovery ([wang...hope, 2023](https://arxiv.org/abs/2305.14259))
1370+
- Towards an AI co-scientist ([gottweis...natarajan, 2025](https://storage.googleapis.com/coscientist_paper/ai_coscientist.pdf))
1371+
1372+
- Learning to Generate Novel Scientific Directions with Contextualized Literature-based Discovery ([wang...hope, 2023](https://arxiv.org/abs/2305.14259))
13711373
- literature-based discovery ([swanson, 1986](https://www.journals.uchicago.edu/doi/abs/10.1086/601720)) - focus on predicting pairwise links between concepts from papers (e.g. drug-disease links)
13721374
- task 1: idea-sentence generation -- given sentences describing background context + a seed term, generate a sentence describing an idea
13731375
- task 2: idea-node prediction -- given the background context, predict new links between existing concepts (and generate new concepts)
13741376
- forecasting paper titles ([blog post](https://csinva.io/gpt-paper-title-generator/))
1377+
13751378
- Communication with animals
13761379

13771380
- [Coller-Dolittle Prize](https://coller-dolittle-24.sites.tau.ac.il) for Inter-species Communication
@@ -1479,6 +1482,8 @@ mixture of experts models have become popular because of the need for (1) fast s
14791482
- Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding - A Survey ([fang...qi,...faloutsos, 2024](https://stewarthu.com/papers/LLM-on-tabular-data.pdf))
14801483

14811484
- **tabPFN main works**
1485+
- TabICL: A Tabular Foundation Model for In-Context Learning on Large Data ([qu...varoquax, le morvan, 2025](https://www.arxiv.org/abs/2502.05564))
1486+
14821487
- TabPFN v2: Accurate predictions on small data with a tabular foundation model ([hollman....hutter, 2025](https://www.nature.com/articles/s41586-024-08328-6))
14831488
-
14841489
Model is open-source on huggingface and easy to use, but training dataset is not released (it was trained only on synthetic data)

0 commit comments

Comments
 (0)