Weekly Mountain, Paper, and Work

April week5       
*research(ai/bio/nlp-papers/lectrues/projects)        


** upload zenodo    

** Ideation(with conference?)-please keep the ideas...      
*** qiita + norm? -> meta + emb (->llm)  
*** unlearning?  

** fair vllm?   


** LLM app for gene (wait?)    
** advAttack_verification and geneLMs (wait?) 


*class->candiexam    




* future...research    

** iterative alignment algo  
** paper focus: E-NLP(??description?)    
** Aug focus(B)  
** deep hierarchy    
(future pro+nu)  
** generative benchmark  
(gf+rm+dc--->nucl)  
(check nucl with blast--->check real nicl whether sim or not)  
** using drug bank web or db(good for using)  


## eng v/q/w first and..  ( reading/listening/speaking/writing(paper)   )  
## math? code? (lecture/assignment/project)

Monday, April 28, 2025

class
research
o

Tuesday, April 29, 2025

class
research
o

Wednesday, April 30, 2025

class
research
o
align with meta, OTU, and seqs
OTU based prediction->not practical–>maybe add tree number for xgb and rf
meta + LLM prediction–> gemma,llama,qwen? –> not practical i think..
predict soil?
pedict diabetes?
dif gen lm?

OTU + meta + LLM
학회에서의 인사이트들?

이미 clip, llm 다 씀 for med ai..wow
contrastive learning, generation for aug 등 생각할만한 거 다 하는 느낌..
bio도 금방일듯
federated learning 좀 흥미로웠네(학습한 피처만 보내는거..중앙으로..병원등 개인정보땜에)

unlearning-> 잊게 만드는거.. 요즘 많이 다루는 분야인듯(이것도 개인정보 관련)

diffusion기반(랜덤기반) 디엔에이?
co-scientist? multi agent..llms with other apis(collaborator)..별건아닌거같아..

새로운 신기한거 많네 causal model들이나 hypergraph? heterophilly?
평소같으면 전혀 안 찾아볼 것들 보게되는 것도 아주 굿

그래프네트워크랑 언어모델이랑(트랜스포머)를 함께 사용하는 접근법도 아주 많네..!

트랜스포머에 모종의 확률의 추가하여 약간의 변화를 주는 방법도 많은듯

시퀀스랑 텍스트랑도 많이들 생각하는…

fidelity? 충실도? fidelity는 모델이 원래 데이터, 원본 모델, 혹은 목표 함수와 얼마나 잘 일치하는지를 나타내는 개념이며, 다양한 머신러닝 응용에서 중요한 품질 평가 기준이 됩니다.
->여러 메트릭을 포함하는 개념인듯.. comsine sim, KL divergence, robust accuracy, 등등

-여기서부터 이어서… 이미지로부터 dna seq추출 신기(사실은 seq분류였음)

이미 rna모델은 엄청 많이 다루네.. 미생물로 확장해서 소타보다 강함을 보이거나

특이한 테스크로 프리트레인하거나 뭐 k mer에 스트라이드를 줘서 최적화하거나…

vector quantization으로 토큰화하는거 진짜 신기하네.. 이걸로 protein 생성모델 만드는거 오오 신기

E(3)-동변량 그래프 신경망(EGNN) 라는 단백질 3d구조 기반의(기울기 등 space정보 포함) 벡터롤 또 얻어서 PLM 벡터랑 합쳐서 뭐 예측 모델에 사용하기도 하네.. 이것도 특이….

rna LM + protein LM도 있는데 각각의 임베딩을 다시 입력으로 받아서 트랜스포머 써서 특정 테스크를 위한 파인튜닝하여 새로 임베딩 얻어서 사용하는… 그것도 인상적이었음

테스크 인사이트??
** Drug Target Discovery (유전자 발현 수준에서 특정 바이오마커를 찾는??)
** Disease Trajectory Reconstruction Using EHRs(유전체 데이터(GWAS, RNA-seq)를 포함할 수도..유전자 변이나 발현 패턴이 질병 진행과 연관될 경우)
** identifying pathogen(병원체)

** 좀 다르지만 생물학 문제(뭐 수능문제같은거)로 LLM평가해도 될 듯 … novelty랑 creativity랑 좀 더 depth한 개념들 갖고…
** 바로 위와 연관지어서 라우팅으로 생물과 화학을 나눈다던지, 또 연산부분은 나눈다던지 등..

** 또 좀 다르지만 t-SNE 대체재 또는 보완재로 UMAP, NCVis, It-SNE, 그리고 PaCMAP(with Differential Expression of Genes Between Clusters), LocalMAP
** interpretable neural networks..ProtoPNet? 이건 잘 모르겠군 도입하기가 ㅎㅎ
** 연관해서 causual 연구들도 관련이 있을듯… 분야가 확실히 많더라

April week4       
*research(ai/bio/nlp-papers/lectrues/projects)        


** upload zenodo    

** Ideation(with conference?)-please keep the ideas...      
*** qiita + norm? -> meta + emb (->llm)  
*** unlearning?  

** fair vllm?   


** LLM app for gene (wait?)    
** advAttack_verification and geneLMs (wait?) 


*class->candiexam    




* future...research    

** iterative alignment algo  
** paper focus: E-NLP(??description?)    
** Aug focus(B)  
** deep hierarchy    
(future pro+nu)  
** generative benchmark  
(gf+rm+dc--->nucl)  
(check nucl with blast--->check real nicl whether sim or not)  
** using drug bank web or db(good for using)  


## eng v/q/w first and..  ( reading/listening/speaking/writing(paper)   )  
## math? code? (lecture/assignment/project)

Monday, April 21, 2025

class
research
o

Tuesday, April 22, 2025

class
research
o

Wednesday, April 23, 2025

class
research
o

Thursday, April 24, 2025

class
research
o

Friday, April 25, 2025

class
research
o

Saturday, April 26, 2025

class
research
o

Sunday, April 27, 2025

class
research
o
align with meta, OTU, and seqs
OTU based prediction->not practical
meta + LLM prediction
OTU + meta + LLM

April week3       
*research(ai/bio/nlp-papers/lectrues/projects)        


** upload zenodo    

** Ideation(with conference?)-please keep the ideas...      
*** qiita + norm? -> meta + emb (->llm)  
*** unlearning?  

** fair vllm?   


** LLM app for gene (wait?)    
** advAttack_verification and geneLMs (wait?) 


*class->candiexam    




* future...research    

** iterative alignment algo  
** paper focus: E-NLP(??description?)    
** Aug focus(B)  
** deep hierarchy    
(future pro+nu)  
** generative benchmark  
(gf+rm+dc--->nucl)  
(check nucl with blast--->check real nicl whether sim or not)  
** using drug bank web or db(good for using)  


## eng v/q/w first and..  ( reading/listening/speaking/writing(paper)   )  
## math? code? (lecture/assignment/project)

Monday, April 14, 2025

class
research
o

Tuesday, April 15, 2025

class
research
o

Wednesday, April 16, 2025

class
research
o

Thursday, April 17, 2025

class
research
o

Friday, April 18, 2025

class
research
o

Saturday, April 19, 2025

class
research
o

Sunday, April 20, 2025

class
research
o
find mapping seqs with sample meta -> huge.. a lot of sequences… hard to handle
seq norm way -> kraken -> tax abundance bag
zenodo-ing
if possible, make model using seqs + meta (ing->but getting emb takes toooo much time…. is it possible? )…
refine and share rf and xgb
–>use llm for meta

April week2       
*research(ai/bio/nlp-papers/lectrues/projects)        


** upload zenodo    

** Ideation(with conference?)-please keep the ideas...      

** fair vllm?   


** LLM app for gene (wait?)    
** advAttack_verification and geneLMs (wait?) 


*class->candiexam    




* future...research    

** iterative alignment algo  
** paper focus: E-NLP(??description?)    
** Aug focus(B)  
** deep hierarchy    
(future pro+nu)  
** generative benchmark  
(gf+rm+dc--->nucl)  
(check nucl with blast--->check real nicl whether sim or not)  
** using drug bank web or db(good for using)  


## eng v/q/w first and..  ( reading/listening/speaking/writing(paper)   )  
## math? code? (lecture/assignment/project)

Monday, April 07, 2025

class
research
o

Tuesday, April 08, 2025

class
research
o

Wednesday, April 09, 2025

class
research
o

Thursday, April 10, 2025

class
research
o

Friday, April 11, 2025

class
research
o

Saturday, April 12, 2025

class
research
o

Sunday, April 13, 2025

class
research
o

April week1       
*research(ai/bio/nlp-papers/lectrues/projects)  

** advAttack_verification and geneLMs ->rebuttal      


** LLM app for gene  

** upload zenodo    

** Ideation(with conference?)-please keep the ideas...      

** fair vllm?   

*class  
**FCV   
**DAI    



* future...research    

** iterative alignment algo  
** paper focus: E-NLP(??description?)    
** Aug focus(B)  
** deep hierarchy    
(future pro+nu)  
** generative benchmark  
(gf+rm+dc--->nucl)  
(check nucl with blast--->check real nicl whether sim or not)  
** using drug bank web or db(good for using)  


## eng v/q/w first and..  ( reading/listening/speaking/writing(paper)   )  
## math? code? (lecture/assignment/project)

Tuesday, April 01, 2025

class
research
o

Wednesday, April 02, 2025

class
research
o

Thursday, April 03, 2025

class
research
o

Friday, April 04, 2025

class
research
o

Saturday, April 05, 2025

class
research
o

Sunday, April 06, 2025

class
research
o

meta + LLM prediction