Ram Kadiyala

Congrats to everyone involved in Kaleidoscope, a cross-institutional collaboration accepted to ICLR 2026 🔥 A special shoutout to @mziizm who championed this collaboration from day 1. It is the first accepted paper for many of the collaborators who are first time authors.

Many researchers join our community seeking mentorship, support, and a roadmap as they embark on their journeys. @_1024_m and @jebish7 did just this. Now, just 2 years later, they are creating these pathways for others, opening doors, and leading the way.

In 2025, our Open Science Community Leads showed what’s possible when AI research is built in the open. 38 leads, 17 programs, 125 guest speakers advancing open, collaborative AI across the world (find all talks here! cohere.link/uw1lvQQ). 🤯

(3/3) Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance. arxiv.org/pdf/2504.09753 A Hindi-English bi-lingual LLM with over 140 checkpoints trained with variations in data distributions. Findings : - LLM-translated data can work as good as real data to address lack of data - Each task type has a different optimal data distribution amount, which could be determined by test runs on a subset of data. - LLM-generated thinking texts were made descriptive yet concise, this led to less emission (less token consumptions) during evals for text-generation tasks while providing better performance. Release : - Open Data, Models and 140 Checkpoints huggingface.co/collections/la… huggingface.co/1-800-LLMs

(2/3) Uncovering Cultural Representation Disparities in Vision-Language Models arxiv.org/pdf/2505.14729 huggingface.co/datasets/Biase… Key Highlights : - We test several VLMs at country/culture recognition task in 3 settings : Open-ended, MCQs with similar or neighbouring countries, MCQs with random countries - We also test them by image ablations (noise, rotations, greyscaling, etc..) Findings : - Country level biases do correlate with country wise availability of online data i.e more data or mentions >> less bias or misclassification. This contradicts the common assumption of western-favouritism. - Image perturbations affect biases in a very random way even among models belonging to the same family. - Language of prompt had negligible effect other than improving accuracy over countries that speak the language.

Three of our papers have been accepted at AACL 2025 @aaclmeeting (2 Main, 1 Findings). 1. DSBC : Data Science task Benchmarking with Context engineering arxiv.org/pdf/2507.23336 2. Uncovering Cultural Representation Disparities in Vision-Language Models arxiv.org/pdf/2505.14729 3. Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance arxiv.org/pdf/2504.09753 Grateful to the co-authors @SidYaeger @Siddartha_10 @jebish7 @delliott @alexrs95 @_sumand @_srishtiyadav @KanwalMehreen2 This was made possible through research grants from @TraversaalAI @AnthropicAI @Cohere_Labs

Our open science community welcomes a new group focusing on agents, led by @_1024_m & @jebish7. They'll explore: 📊evaluation frameworks 🖥️agentic applications 🏇efficient systems ...via panel discussions and community-led projects. Join our community on this exploration.