Principal scientist and manager at the MIT-IBM Watson AI Lab
Joined February 2020
- Tweets50
- Following354
- Followers1.1K
- Likes413
Rogerio Feris retweeted
CDS Silver Professor Julia Kempe (@KempeLab) is co-organizing this year's ICLR 2026 Workshop on New Frontiers in Associative Memory.
The workshop is accepting submissions related to associative memory until Feb 14.
nfam2026.amemory.net
Rogerio Feris retweeted
🚀 Our Memory and Vision (MemVis) Workshop is happening this Sunday 8:30am-1pm, Oct 19 at #ICCV2025 in Honolulu, Hawaii!
📍 Room #304B
🕘 Full schedule is live
Join us and our amazing speakers to explore how memory connects with vision models through inspiring talks, panels, and posters!
💫 Finally, huge thanks to our generous sponsor @abaka_ai, and join us in Happy Hour here: luma.com/m7xwirk0
Rogerio Feris retweeted
MemVis @ #ICCV2025 -- 1st Workshop on Memory & Vision! 🧠👁️ Call for papers now open: Hopfield & energy nets, state-space + diffusion models, retrieval & lifelong learning, long-context FMs, multimodal memory, & more. 🗓️ Submit by 1 Aug 2025 → sites.google.com/view/memvis… 🌺 #MemVis
Rogerio Feris retweeted
🎉 Our paper “M+: Extending MemoryLLM with Scalable Long-Term Memory” is accepted to ICML 2025!
🔹 Co-trained retriever + latent memory
🔹 Retains info across 160k+ tokens
🔹 Much Lower GPU cost compared to backbone LLM
arxiv.org/abs/2502.00592
Rogerio Feris retweeted
🎯 Introducing Sparse Attention Vectors (SAVs): A breakthrough method for extracting powerful multimodal features from Large Multimodal Models (LMMs). SAVs enable SOTA performance on discriminative vision-language tasks (classification, safety alignment, etc.)!
Links in replies!
🔎Using just ~20 attention heads & only few-shot examples, SAVs:
- Outperform both LoRA and few-shot baselines
- Work with image, text, & interleaved inputs
- Extract features without finetuning - ready to go at test time!
This project was a cross-collaborative effort between researchers from UC Berkeley, Carnegie Mellon University, and MIT-IBM Research (@berkeley_ai, @CMU_Robotics, @MITIBMLab). Many thanks to all of the collaborators and co-authors on this work:
Brandon Huang, Tianning (Ray) Chai, @ZhiqiuLin, @ArbelleAssaf, @RogerioFeris, @leokarlin, @trevordarrell, @RamananDeva, @roeiherzig
Rogerio Feris retweeted
Granite 3.0 is our latest update for the IBM foundation models. The 8B and 2B models outperform strong competitors with similar sizes. The 1B and 3B MoE use only 400M and 800M active parameters to target the on-device use cases. Our technical report provides all the details you need to train a state-of-the-art 8B model from scratch!
github.com/ibm-granite/grani…
Rogerio Feris retweeted
Welcome to join our workshop to figure out what is next in Multimodal foundation models! Tuesday 08:30 Pacific Time, Summit 437-439 at Seattle Convention Center Summit🤖
Tomorrow!
Attending @CVPR?
Come to MultiModal foundation models workshop tomorrow! We have a great panel and speakers 😎
Tuesday, June 18
8:30-13:00
Summit 437-439
Rogerio Feris retweeted
Thanks for the highlight @_akhaliq!
We offer a simple and nearly-data-free way to move (large quantities) of custom PEFT models within or across LLM families or even across PEFT configurations. Useful for LLM cloud hosting when old base models need to be deprecated & upgraded
We have a cool challenge on understanding document images in our 2nd #CVPR2024 workshop on “What is Next in Multimodal Foundation Models?”, (sites.google.com/view/2nd-mm…). This is a great opportunity to showcase your work in front of a large audience (pic below from our 1st workshop)
Rogerio Feris retweeted
IBM & Meta are launching the AI Alliance to advance *open* & reliable AI.
The list of over 50 founding members from industry, government, and academia include AMD, Anyscale, CERN, Hugging Face, the Linux Foundation, NASA....
ai.meta.com/blog/ai-alliance…
Our team is hiring 2024 summer interns. We are doing research towards augmenting large language models with memory, multiple modalities (vision, speech, sound, …), and specializing LLMs for enterprise domains. @MITIBMLab
Apply here: careers.ibm.com/job/19215487…[…]jcz*_ga_FYECCCS21D*MTY5NzQ5MjI3My4xLjAuMTY5NzQ5MjI4MS4wLjAuMA/
Rogerio Feris retweeted
🚨Can we self-align LLMs with an expert domain like biomedicine with limited supervision?
Introducing Self-Specialization, uncovering expertise latent within LLMs to boost their utility in specialized domains.
arxiv.org/abs/2310.00160
@ICatGT @mlatgt @MIT_CSAIL @MITIBMLab
1/8
Rogerio Feris retweeted
What could be the computational function of astrocytes in the brain? We hypothesize that they may be the biological cells that could implement the Transformer's attention operation commonly used in AI. Much improved compared to an earlier preprint: pnas.org/doi/10.1073/pnas.22…
Rogerio Feris retweeted
(1/3)🤔Wondering what's transferred between the pre-training and fine-tuning? Our ACL finding looks into this question with synthetic pre-training tasks for MT. Surprisingly, most pre-training benefits are realized even with 75% nonsense parallel corpus or purely synthetic data!
Rogerio Feris retweeted
Recent advances in Hopfield networks of associative memory may be the guiding theoretical principle for designing novel large scale neural architectures. I explain my enthusiasm about these ideas in the article ⬇️⬇️⬇️. Please let me know what you think. nature.com/articles/s42254-0…
Rogerio Feris retweeted
We can all agree we’re at a unique and evolutionary moment in AI, with enterprises increasingly turning to this technology’s transformative power to unlock new levels of innovation and productivity. At #Think2023, @IBM unveiled watsonx. Learn more: newsroom.ibm.com/2023-05-09-…
Rogerio Feris retweeted
New technique from the @MITIBMLab and its collaborators learns to "grow" a larger machine-learning model from a smaller, pre-trained model, reducing the monetary and environmental cost of developing AI applications and with similar or improved performance.
news.mit.edu/2023/new-techni…
ALT 2 pairs of neural networks on decorative background. The left pair is shown expanding vertically with more rows; the right pair expands horizontally with more columns.
We are looking for a summer intern (MSc/PhD) to work on large language models for sports & entertainment, with the goal of improving the experience of millions of fans as part of major tournaments (US Open/Wimbledon) @IBMSports @MITIBMLab Apply at: krb-sjobs.brassring.com/TGne…
Rogerio Feris retweeted
Multi-Task Prompt Tuning Enables Transfer Learning
-Learn single prompt from multiple task-specific prompts
-Learn multiplicative low rank updates to adapt it to tasks
Parameter-efficient & state-of-the-art performance across diverse NLP tasks
Paper: arxiv.org/abs/2303.02861
