Daniel Cer Profile
Daniel Cer

@daniel_m_cer

Followers
559
Following
3K
Media
8
Statuses
178

Research Scientist at @GoogleAI, @googIeresearch.

California, USA
Joined March 2012
Don't wanna be here? Send us removal request.
@daniel_m_cer
Daniel Cer
5 days
RT @tonywu_71: Similarity maps also works for the Hf-native ColQwen2 model! šŸ¤— I have created a cookbook to quickly try this out:. https://t….
Tweet card summary image
github.com
Recipes for learning, fine-tuning, and adapting ColPali to your multimodal RAG use cases. šŸ‘ØšŸ»ā€šŸ³ - tonywu71/colpali-cookbooks
0
5
0
@daniel_m_cer
Daniel Cer
1 month
RT @MaxSonate: Our Gemini model just won a gold medal at the IMO 2025. It’s a massive milestone for AI, and I’m so proud to have played a p….
0
8
0
@daniel_m_cer
Daniel Cer
1 month
RT @lateinteraction: šŸ“¢ If you’re at #SIGIR2025 this week, make sure to be at Luca Scheerer’s paper talk:. ā€œWARP: An Efficient Engine for Mu….
0
20
0
@daniel_m_cer
Daniel Cer
2 months
RT @tomaarsen: ā€¼ļøSentence Transformers v5.0 is out! The biggest update yet introduces Sparse Embedding models, encode methods improvements,….
0
66
0
@daniel_m_cer
Daniel Cer
2 months
RT @beirmug: We had a successful participation of over 45+ teams & 150+ runs last year in TREC RAG 2024! šŸ”„šŸ”„. We are back with @TREC_RAG 202….
Tweet card summary image
docs.google.com
We are having some systems issues, so in the meantime, we are taking registrations through this form. Please use a direct email address and not a mailing list or group alias as the contact email.
0
3
0
@daniel_m_cer
Daniel Cer
2 months
RT @harveyiyun: LLMs excel at finding surprising ā€œneedlesā€ in very long documents, but can they detect when information is conspicuously mi….
0
32
0
@daniel_m_cer
Daniel Cer
2 months
RT @oscrhong: Interesting tidbit from prof @chrmanning: The first mention of ā€œLarge Language Modelā€ comes from a 1998 NLP workshop Taiwan!….
0
7
0
@daniel_m_cer
Daniel Cer
2 months
RT @GoogleResearch: Neural embedding models have become a cornerstone of modern information retrieval. Today we introduce MUVERA, a state-o….
0
79
0
@daniel_m_cer
Daniel Cer
2 months
RT @_reachsumit: Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval. Introduces a bi-encoder approach that performs….
Tweet card summary image
arxiv.org
In this work, we tackle the problem of text-to-video retrieval (T2VR). Inspired by the success of late interaction techniques in text-document, text-image, and text-video retrieval, our approach,...
0
3
0
@daniel_m_cer
Daniel Cer
2 months
RT @meetdavidwan: Excited to share our new work, CLaMR! šŸš€. We tackle multimodal content retrieval by jointly considering video, speech, OCR….
0
65
0
@daniel_m_cer
Daniel Cer
2 months
RT @bclavie: Multimodal RAG: Just use ColPali/DSE then pass your screenshots to the LLM. This is the dream, but how well do LLMs read text….
0
82
0
@daniel_m_cer
Daniel Cer
3 months
RT @raphaelsrty: I'm thrilled to announce the release of FastPlaid ! šŸš€šŸš€. FastPlaid is a high-performance engine for multi-vector search, bu….
0
38
0
@daniel_m_cer
Daniel Cer
3 months
RT @tonywu_71: šŸš€ ColQwen2 just dropped in Transformers! šŸ¤—. Say goodbye to brittle OCR pipelines — now you can retrieve documents directly i….
0
94
0
@daniel_m_cer
Daniel Cer
3 months
RT @davidbau: Dear MAGA friends,. I have been worrying about STEM in the US a lot, because right now the Senate is writing new laws that cu….
0
72
0
@daniel_m_cer
Daniel Cer
3 months
RT @_reachsumit: R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning. Introduces RL to teach LLMs ada….
Tweet card summary image
github.com
Contribute to Yuan-Li-FNLP/R3-RAG development by creating an account on GitHub.
0
2
0
@daniel_m_cer
Daniel Cer
3 months
RT @ManuelFaysse: 🚨 Context matters for effective retrieval—but most embedding models cannot leverage crucial information outside of the pa….
0
30
0
@daniel_m_cer
Daniel Cer
3 months
RT @younggyoseo: Excited to present FastTD3: a simple, fast, and capable off-policy RL algorithm for humanoid control -- with an open-sourc….
0
115
0
@daniel_m_cer
Daniel Cer
3 months
RT @beirmug: Did you know that fine-tuning retrievers & re-rankers on large but unclean training datasets can harm their performance? 😔. In….
0
19
0
@daniel_m_cer
Daniel Cer
3 months
RT @lateinteraction: Google folks continues to do awesome late interaction work. Compared to vanilla ColBERT, a version of this new ā€œCRISP….
0
14
0