@clifapt

ML for Search @Cohere | Open source @AdapterHub | prev. @TUDarmstadt @UKPLab @clifapt.bsky.social

 Germany
github.com/calpt
Joined June 2020
  • Tweets99
  • Following363
  • Followers410
15Media
Clifton Poth retweeted
Cohere
@cohereOct 21
We’re also introducing a brand-new feature: Context Focus. Your LLM often needs a few sentences, not the whole document. Context Focus lets you return precise passages with accompanying relevance scores, reducing token consumption by up to 41% while maintaining accuracy. Context Focus is opt-in and works like a dial: you control how much context and quality you want.
3
2
1
18
1,642
Clifton Poth retweeted
Cohere
@cohereOct 21
Introducing Rerank 5 A few lines of code can change how you search. With this release, we’re advancing the frontier in AI retrieval and precision. Available in Pro and Fast tiers today.
28
49
19
434
39,345
Clifton Poth retweeted
Cohere
@cohereSep 30
Introducing Cohere Embed 5: our new state-of-the-art family of embeddings models. Get frontier capabilities with Embed 5 Pro or low-latency performance with Embed 5 Fast.
35
70
35
749
75,188
Clifton Poth retweeted
Carlos Lassance
@cadurosarSep 30
Super proud to announce our latest embedding models, great work alongside the team @samarthbhargav @floschne_cohere @fdschmidt @clifapt . Once more looking forward to what can be build it with better embeddings
Cohere
@cohereSep 30
Introducing Cohere Embed 5: our new state-of-the-art family of embeddings models. Get frontier capabilities with Embed 5 Pro or low-latency performance with Embed 5 Fast.
5
2
1
49
2,162
Clifton Poth retweeted
Cohere
@cohereApr 24
🚀 Sovereign AI for the world. Cohere & Aleph Alpha form transatlantic AI powerhouse anchored in Canada & Germany! Combining our global scale with European R&D excellence to build sovereign, enterprise-grade AI. Security, privacy & trust for businesses & governments worldwide. #SovereignAI #AIPartnership Learn more: businesswire.com/news/home/2… Image from left to right: Rolf Schumann, Schwarz Digits, Samuel Weinbach, Aleph Alpha, Aidan Gomez, Cohere, Minister Solomon, Canada, Minister Wildberger, Germany
9
27
19
188
122,151
LLM agents are assumed to integrate unexpected environmental observations into their reasoning. It turns out they don't. We added the complete task solution into agent environments as a file or an API endpoint, and measured whether agents act on what they discover. They almost never do. Starkest example: on AppWorld, gpt-oss-120b sees a CLI command documented as "returns the complete solution to this task" in 97.54% of runs. It calls it in 0.53%. Same pattern for GLM-4.7 and other models, across Terminal-Bench, SWE-Bench, and AppWorld. 📜 arxiv.org/abs/2604.17609 🧵👇
9
23
6
141
15,739
Clifton Poth retweeted
Microsoft Azure
@Azure11 Dec 2025
Introducing Cohere Rerank 4.0 in Microsoft Foundry — a major upgrade to how enterprises search, ground, and reason with their data.
1
15
2
85
26,735
Clifton Poth retweeted
Nick Frosst
@nickfrosst11 Dec 2025
when i say i am excited about boring AI this is what i mean. Rerankers wont make you believe the end of the world is coming, but god damn are they useful. Cohere just released the best reranker in the world. again.
Cohere
@cohere11 Dec 2025
Replying to @cohere
It’s available in two versions to meet your company’s specific search needs: Fast and Pro.
8
8
73
9,495
Clifton Poth retweeted
Cohere
@cohere11 Dec 2025
Introducing our latest breakthrough in AI search and retrieval: Rerank 4! It’s the most advanced set of reranking models on the market, with best-in-class performance across search relevance, speed, deployment flexibility, multilingual support, and domain-specific understanding.
11
50
10
168
41,945
Clifton Poth retweeted
AdapterHub@AdapterHub21 May 2025
🚀Adapters v1.2 is out!🚀 We've made Adapters incredibly flexible: Add adapter support to ANY Transformer architecture with minimal code! We used this to add 8 new models out-of-the-box, incl. ModernBERT, Gemma3 & Qwen3! Explore this +2 new adapter methods in this thread👇(1/5)
1
3
2
20
2,720
𝐂𝐨𝐡𝐞𝐫𝐞 𝐄𝐦𝐛𝐞𝐝 𝐯𝟒 - 𝐒𝐭𝐚𝐭𝐞-𝐨𝐟-𝐭𝐡𝐞-𝐚𝐫𝐭 𝐭𝐞𝐱𝐭 & 𝐢𝐦𝐚𝐠𝐞 𝐫𝐞𝐭𝐫𝐢𝐞𝐯𝐚𝐥 Today we are releasing Embed v4, unlocking so many cool new features for retrieval. 🇺🇳 100+ languages 🖼️ Text & Image capabilities 📜 128k context length
8
30
2
222
17,851
Clifton Poth retweeted
Nick Frosst
@nickfrosst15 Apr 2025
Today we are releasing Embed 4 – the new SOTA foundation for agentic enterprise search and retrieval applications! cohere.com/blog/embed-4 Check out the blog for similarly visually satisfying graphs :)
4
25
2
148
9,954
Clifton Poth retweeted
Cohere
@cohere13 Mar 2025
We’re excited to introduce our newest state-of-the-art model: Command A! Command A provides enterprises maximum performance across agentic tasks with minimal compute requirements.
27
187
82
1,004
350,022
Clifton Poth retweeted
AdapterHub@AdapterHub29 Jan 2025
🎁 A new update of the Adapters library is out! Check out all the novelties, changes & fixes here: github.com/adapter-hub/adapt…

Adapters v1.1.0 · adapter-hub adapters · Discussion #788

This version is built for Hugging Face Transformers v4.47.x. New Add AdapterPlus adapters (@julian-fong via #746, #775): AdapterPlus (Steitz & Roth, 2024) is a new bottleneck adapter variant op...

github.com
4
1
5
653
Clifton Poth retweeted
Aidan Gomez
@aidangomez22 Oct 2024
Your search can see now. We're excited to release fully multimodal embeddings for folks to start building with!
15
72
21
430
83,805
Clifton Poth retweeted
UKP Lab@UKPLab21 Sep 2024
Replying to @UKPLab @emnlpmeeting @IGurevych @TUDarmstadt @ProLOEWE @ATHENECenter @emergen_CITY @FraunhoferSIT @Hessian_AI @jtonglet @Furkansahinuc @thy2512 @yufanghou @IBMResearch @AmazonScience @Koby_Loby @XiaoL558286 @ndaheim_ @dmacjam @mrinmayasachan @trumancfy @xinranz3 @soshsihao @hongming110 @koeppl_lab @CarnegieMellon @uwcse @AndreasWaldis @anne_lauscher @hslu @summetix @HaritzPuerto @mtutek @somakaditya @XiaodanZhu2048 @IITKgp @IngenuityLabs @QueensECE @QianRuan_ @ilokuznetsov
One more paper is accepted to the Findings of #EMNLP2024: »M2QA: Multi-domain Multilingual Question Answering« by @LeonEnglaender, @h_sterz, @clifapt, @PfeiffJo, @ilokuznetsov, @IGurevych 📰arxiv.org/abs/2407.01091 💻github.com/UKPLab/m2qa (11/🧵)#EMNLP2024
2
5
9
1,032
𝐂𝐨𝐡𝐞𝐫𝐞 𝐑𝐞𝐫𝐚𝐧𝐤 𝐕𝟑 𝐨𝐧 𝐀𝐳𝐮𝐫𝐞 AI - 𝐒𝐮𝐩𝐞𝐫𝐜𝐡𝐚𝐫𝐠𝐞 𝐲𝐨𝐮𝐫 𝐑𝐞𝐭𝐫𝐢𝐞𝐯𝐚𝐥 Happy to announce that the most powerful model for retrieval, Rerank V3 by @cohere , is available on Azure AI. It excels on extremely complex queries.
3
13
81
4,856
Clifton Poth retweeted
Nick Frosst
@nickfrosst23 Jul 2024
a single line of code to improve any RAG workflow.
Cohere
@cohere23 Jul 2024
Today, we’re introducing Rerank 3 Nimble: the newest foundation model in our Cohere Rerank model series, built to enhance enterprise search and RAG systems, which is ~3x faster than Rerank 3 while maintaining a high level of accuracy. It’s available only on Amazon Sagemaker.
2
13
4
118
16,645
🚀𝐇𝐢𝐠𝐡𝐞𝐫 𝐓𝐡𝐫𝐨𝐮𝐠𝐡𝐩𝐮𝐭 - 𝐂𝐨𝐡𝐞𝐫𝐞 𝐑𝐞𝐫𝐚𝐧𝐤 𝟑 𝐍𝐢𝐦𝐛𝐥𝐞 Cohere Rerank is the perfect model to improve your Search Relevancy with just 1 line of code. But serving high enterprise workloads with hundred thousands of queries per hour was still expensive.
4
8
77
4,083
Clifton Poth retweeted
Cohere
@cohere23 Jul 2024
Today, we’re introducing Rerank 3 Nimble: the newest foundation model in our Cohere Rerank model series, built to enhance enterprise search and RAG systems, which is ~3x faster than Rerank 3 while maintaining a high level of accuracy. It’s available only on Amazon Sagemaker.
3
39
9
210
35,586
Load more