Shangshang Wang
@shangshang-wang.bsky.social
https://shangshang-wang.github.io/
Phd student in CS + AI @usc.edu. CS undergrad, master at ShanghaiTech. LLM reasoning, RL, AI4Science.
Phd student in CS + AI @usc.edu. CS undergrad, master at ShanghaiTech. LLM reasoning, RL, AI4Science.
Pinned
Sparse autoencoders (SAEs) can be used to elicit strong reasoning abilities with remarkable efficiency.
Using only 1 hour of training at $2 cost without any reasoning traces, we find a way to train 1.5B models via SAEs to score 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23.
Using only 1 hour of training at $2 cost without any reasoning traces, we find a way to train 1.5B models via SAEs to score 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23.
Sparse autoencoders (SAEs) can be used to elicit strong reasoning abilities with remarkable efficiency.
Using only 1 hour of training at $2 cost without any reasoning traces, we find a way to train 1.5B models via SAEs to score 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23.
Using only 1 hour of training at $2 cost without any reasoning traces, we find a way to train 1.5B models via SAEs to score 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23.
June 12, 2025 at 5:02 PM
Sparse autoencoders (SAEs) can be used to elicit strong reasoning abilities with remarkable efficiency.
Using only 1 hour of training at $2 cost without any reasoning traces, we find a way to train 1.5B models via SAEs to score 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23.
Using only 1 hour of training at $2 cost without any reasoning traces, we find a way to train 1.5B models via SAEs to score 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23.
😃 Want strong LLM reasoning without breaking the bank? We explored just how cost-effectively RL can enhance reasoning using LoRA!
[1/9] Introducing Tina: A family of tiny reasoning models with strong performance at low cost, providing an accessible testbed for RL reasoning. 🧵
[1/9] Introducing Tina: A family of tiny reasoning models with strong performance at low cost, providing an accessible testbed for RL reasoning. 🧵
April 23, 2025 at 5:10 PM
😃 Want strong LLM reasoning without breaking the bank? We explored just how cost-effectively RL can enhance reasoning using LoRA!
[1/9] Introducing Tina: A family of tiny reasoning models with strong performance at low cost, providing an accessible testbed for RL reasoning. 🧵
[1/9] Introducing Tina: A family of tiny reasoning models with strong performance at low cost, providing an accessible testbed for RL reasoning. 🧵
🔍 Diving deep into LLM reasoning?
From OpenAI's o-series to DeepSeek R1, from post-training to test-time compute — we break it down into structured spreadsheets. 🧵
From OpenAI's o-series to DeepSeek R1, from post-training to test-time compute — we break it down into structured spreadsheets. 🧵
February 19, 2025 at 6:01 PM
🔍 Diving deep into LLM reasoning?
From OpenAI's o-series to DeepSeek R1, from post-training to test-time compute — we break it down into structured spreadsheets. 🧵
From OpenAI's o-series to DeepSeek R1, from post-training to test-time compute — we break it down into structured spreadsheets. 🧵
Reposted by Shangshang Wang
Introducing METAGENE-1🧬, an open-source 7B-parameter metagenomics foundation model pretrained on 1.5 trillion base pairs. Built for pandemic monitoring, pathogen detection, and biosurveillance, with SOTA results across many genomics tasks.
🧵1/
🧵1/
January 6, 2025 at 5:04 PM
Introducing METAGENE-1🧬, an open-source 7B-parameter metagenomics foundation model pretrained on 1.5 trillion base pairs. Built for pandemic monitoring, pathogen detection, and biosurveillance, with SOTA results across many genomics tasks.
🧵1/
🧵1/