Center for Research on Foundation Models
@StanfordCRFM
Followers
2K
Following
75
Media
0
Statuses
72
Making foundation models more reliable and accessible.
Joined May 2022
RT @dan_biderman: How can we use small LLMs to shift more AI workloads onto our laptops and phones?. In our paper and open-source code, we….
0
172
0
RT @Avanika15: we shipp’d 👭 on-device lms and frontier cloud lms. and…they were a match☺️. 98% accuracy, just 17.5% the cloud API costs. be….
0
43
0
RT @JonSaadFalcon: Interested in Building O1-style LM systems that beat individual LMs?. Checkout our latest tutorial on Archon, a modular….
0
20
0
RT @bfspector: (1/7) In celebration of National Cat Day, we’re excited to release our first major batch of updates to ThunderKittens! Thund….
0
41
0
RT @simran_s_arora: Wish writing AI kernels was like writing PyTorch??? Enter ThunderKittens 0.002: for simpler, faster, more adorable AI k….
0
39
0
RT @ChengleiSi: Automating AI research is exciting! But can LLMs actually produce novel, expert-level research ideas?. After a year-long st….
0
771
0
RT @soldni: Selecting pretraining data points based on correlation with downstream tasks is an effective data mixing technique. I love pape….
0
40
0
RT @ZitongYang0: Grab your favorite preprint of the week: how can you put its knowledge in your LM’s parameters? Continued pretraining (CPT….
0
39
0
RT @mzhangio: Ever wanted to scale subquadratic models up to 7B+ LLMs? But didn't want to pretrain billions of parameters on trillions of t….
0
51
0
RT @JoeyHejna: As imitation learning policies continue to scale, deciding how to weigh different robot datasets will become even more diffi….
0
35
0
RT @JonSaadFalcon: What is the best way to spend your inference compute budget to create LLM systems greater than the sum of their parts?….
0
55
0
RT @simran_s_arora: Want Llama 405B, but wish it scaled linearly in sequence length??? Enter LoLCATS: an efficient method for "turning Tran….
0
90
0
RT @tonyh_lee: 📢 Announcing Holistic Evaluation of Vision-Language Models (VHELM), the HELM extension for VLMs, where we holistically evalu….
arxiv.org
Current benchmarks for assessing vision-language models (VLMs) often focus on their perception or problem-solving capabilities and neglect other critical aspects such as fairness, multilinguality,...
0
25
0
RT @james_y_zou: 🔥#TextGrad is now multi-modal!. TextGrad boosts GPT-4o's visual reasoning ability:.📊MathVista score 63.8➡️66.1 w/ TextGrad….
0
31
0
RT @simran_s_arora: Excited to share Just read twice: going beyond causal language modeling to close quality gaps between efficient recurre….
0
59
0
RT @leto__jean: We dramatically sped up Diffusion policies through consistency distillation. With the resulting single step policy, we can….
0
15
0
RT @megha_byte: #2 RL agents can reflect too! .In @cedcolas, @dorsasadigh @jacobandreas, and I find when 🤖s per….
0
28
0
RT @bfspector: (1/7) Happy mother’s day! We think what the mothers of America really want is a Flash Attention implementation that’s just 1….
0
156
0
RT @MichaelWornow: Can AI agents automate enterprise-level workflows?. Excited to share ECLAIR, a 1st step towards end-to-end digital workf….
0
17
0
RT @Avanika15: Can AI agents automate enterprise-level workflows?. Excited to share ECLAIR, a first step towards end-to-end digital workflo….
0
18
0