MINT Workshop @ NeurIPS2024

NeurIPS 2024 - Workshop on Foundation Model Interventions

Join us December 15th

[Pau Rodríguez @prlz77]

Thread on the best paper award at our workshop on model interventions @MINT_workshop

[MINT Workshop @ NeurIPS2024 @MINT_workshop]

Thank you to our junior panelists @fangcong_y10593, @EkdeepL, Itamar Pres, and @siyan_zhao for giving brilliant advice on navigating an early research career.

And to @RinMetcalfSusa for being a great moderator.

[Pau Rodríguez @prlz77]

@MINT_workshop junior panel starts!

[MINT Workshop @ NeurIPS2024 @MINT_workshop]

You can also follow our workshop on Foundation Model Interventions online https://t.co/WaF7I6Pl9Y

[Pau Rodríguez @prlz77]

Towards Reliable Evaluation of Behavior Steering Interventions in LLMs - Itamar Pres · Laura Ruis · David Krueger

[Pau Rodríguez @prlz77]

Probing the Decision Boundaries of In-context Learning in Large Language Models - Siyan Zhao

[MINT Workshop @ NeurIPS2024 @MINT_workshop]

@dyhadila presenting her work on free self-alignment in West Meeting Room 121.

Join us to learn more on Foundation Model Interventions.

[Pau Rodríguez @prlz77]

Analyzing (In)Abilities of SAEs via Formal Languages - Abhinav Menon · Manish Shrivastava · David Krueger

[Pau Rodríguez @prlz77]

Spotlight talks start @MINT_workshop
LoFiT: Localized Fine-tuning on LLM Representations - Fangcong Yin · Xi Ye · Greg Durrett

[Pau Rodríguez @prlz77]

The @MINT_workshop starts! @AtticusGeiger on the current state of interpretability 🍃🍃

[MINT Workshop @ NeurIPS2024 @MINT_workshop]

Join us for our @NeurIPSConf workshop on Model Interventions and Foundation Models starting at 8:45 am in West Meeting Room 121, 122 #NeurIPS2024

[MINT Workshop @ NeurIPS2024 @MINT_workshop]

Really excited to welcome foundation model researchers to our workshop tomorrow!!

In the last talk of our day, @JacobSteinhardt will present on Scalably Understanding AI with AI. 🤖

https://t.co/eD0z0pcVxS

[MINT Workshop @ NeurIPS2024 @MINT_workshop]

2 days until our @NeurIPS workshop on Model Interventions on Foundation Models!!

Our third talk features @hardmaru , co-founder of @SakanaAILabs and previously @GoogleDeepMind. He presents on "The Future of Collective Intelligence and Meta Evolution for Foundation Models" 🤖

[MINT Workshop @ NeurIPS2024 @MINT_workshop]

Two days until our @NeurIPS workshop on Model Interventions on Foundation Models on Sunday!!

Our second talk features @viegasf, Professor @Harvard and co-lead of @Google's PAIR initiative presenting on user-centric interpretability.

https://t.co/eD0z0pcVxS

[MINT Workshop @ NeurIPS2024 @MINT_workshop]

Three days until our @NeurIPS workshop on Sunday!!

Join us to understand the inner workings of foundation models, and how to mechanistically intervene or finetune them.

Our first talk features Atticus Geiger presenting on (scalable) interpretability

https://t.co/eD0z0pcVxS

[MINT Workshop @ NeurIPS2024 @MINT_workshop]

Really excited for our @NeurIPSConf Workshop this Sunday. Check out our program here

https://t.co/O0N087sHsk