Tootfinder

Training-free LLM Merging for Multi-task Learning
Zichuan Fu, Xian Wu, Yejing Wang, Wanyu Wang, Shanshan Ye, Hongzhi Yin, Yi Chang, Yefeng Zheng, Xiangyu Zhao
https://arxiv.org/abs/2506.12379

Training-free LLM Merging for Multi-task Learning
Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing (NLP) tasks. The release of open-source LLMs like LLaMA and Qwen has triggered the development of numerous fine-tuned models tailored for various tasks and languages. In this paper, we explore an important question: is it possible to combine these specialized models to create a unified model with multi-task capabilities. We introduces Hierarchical Iterative Merging (Hi-Merging), a …

Don't throw the baby out with the bathwater: How and why deep learning for ARC
Jack Cole, Mohamed Osman
https://arxiv.org/abs/2506.14276 https://

Don't throw the baby out with the bathwater: How and why deep learning for ARC
The Abstraction and Reasoning Corpus (ARC-AGI) presents a formidable challenge for AI systems. Despite the typically low performance on ARC, the deep learning paradigm remains the most effective known strategy for generating skillful (state-of-the-art) neural networks (NN) across varied modalities and tasks in vision, language etc. The deep learning paradigm has proven to be able to train these skillful neural networks and learn the abstractions needed in these diverse domains. Our work doubles…

For me if someone schedules a meeting before 08:00 and after 15:00 it is an automatic NO.
Early morning mail checks (before 07:00) is done only when I am on call and to see if there was any emergencies in the prior evening production run that I missed. When I do that my day starts at that time! I adjust the end of day time to allow for the early start. Normal hours for me is 07:00 to 15:30.

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
Chenchen Yuan, Zheyu Zhang, Shuo Yang, Bardh Prenkaj, Gjergji Kasneci
https://arxiv.org/abs/2506.14625

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
Large Language Models (LLMs) have shown impressive moral reasoning abilities. Yet they often diverge when confronted with complex, multi-factor moral dilemmas. To address these discrepancies, we propose a framework that synthesizes multiple LLMs' moral judgments into a collectively formulated moral judgment, realigning models that deviate significantly from this consensus. Our aggregation mechanism fuses continuous moral acceptability scores (beyond binary labels) into a collective probability,…

Want to shape the future of the GÉANT Community Programme (GCP)?
Join the GÉANT Community Committee (GCC)—applications close today!
As a member, you’ll:
✅ Help steer community-driven collaboration & innovation
✅ Be the voice of the community to GÉANT’s General Assembly
✅ Ensure diverse topics are represented across the GCP
How to submit your nomination ⤵
📃 Read the eligibility criteria:

Call for new GÉANT Community Committee (GCC) Members – Apply by 14 AprilGÉANT CONNECT Online
Submissions are now open for you to join the GÉANT Community Committee (GCC). What are the duties of a GCC member? As a GCC member , you will support the GÉANT Community Programme (GCP) to ensure we continue to maintain a thriving community for years to come, and all relevant subjects are covered within the

It's not over. Join the fight this Monday, June 16th @ 5PM PT.

✅ No Kings: What's Next in the Fight? (Attendee Debrief Call)
https://www.mobilize.us/nokings/event/798722/?utm_source=indivisible

No Kings: What's Next in the Fight? (Attendee Debrief Call) · No Kings
On June 14, we told our governments and communities: No Kings! Join us on Monday night after the big day for a debrief call for everyone across the movement who attended a No Kings event. We'll talk about what we accomplished and what's next in the fight.

Understanding the Effect of Knowledge Graph Extraction Error on Downstream Graph Analyses: A Case Study on Affiliation Graphs
Erica Cai, Brendan O'Connor
https://arxiv.org/abs/2506.12367

Understanding the Effect of Knowledge Graph Extraction Error on Downstream Graph Analyses: A Case Study on Affiliation Graphs
Knowledge graphs (KGs) are useful for analyzing social structures, community dynamics, institutional memberships, and other complex relationships across domains from sociology to public health. While recent advances in large language models (LLMs) have improved the scalability and accessibility of automated KG extraction from large text corpora, the impacts of extraction errors on downstream analyses are poorly understood, especially for applied scientists who depend on accurate KGs for real-wo…

Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees
Ahmed Heakl, Sarim Hashmi, Chaimaa Abi, Celine Lee, Abdulrahman Mahmoud
https://arxiv.org/abs/2506.14606

Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees
The hardware ecosystem is rapidly evolving, with increasing interest in translating low-level programs across different instruction set architectures (ISAs) in a quick, flexible, and correct way to enhance the portability and longevity of existing code. A particularly challenging class of this transpilation problem is translating between complex- (CISC) and reduced- (RISC) hardware architectures, due to fundamental differences in instruction complexity, memory models, and execution paradigms. I…

Language Surgery in Multilingual Large Language Models
Joanito Agili Lopo, Muhammad Ravi Shulthan Habibi, Tack Hwa Wong, Muhammad Ilham Ghozali, Fajri Koto, Genta Indra Winata, Peerat Limkonchotiwat, Alham Fikri Aji, Samuel Cahyawijaya
https://arxiv.org/abs/2506.12450

Language Surgery in Multilingual Large Language Models
Large Language Models (LLMs) have demonstrated remarkable generalization capabilities across tasks and languages, revolutionizing natural language processing. This paper investigates the naturally emerging representation alignment in LLMs, particularly in the middle layers, and its implications for disentangling language-specific and language-agnostic information. We empirically confirm the existence of this alignment, analyze its behavior in comparison to explicitly designed alignment models, …

Hatevolution: What Static Benchmarks Don't Tell Us
Chiara Di Bonaventura, Barbara McGillivray, Yulan He, Albert Mero\~no-Pe\~nuela
https://arxiv.org/abs/2506.12148

Hatevolution: What Static Benchmarks Don't Tell Us
Language changes over time, including in the hate speech domain, which evolves quickly following social dynamics and cultural shifts. While NLP research has investigated the impact of language evolution on model training and has proposed several solutions for it, its impact on model benchmarking remains under-explored. Yet, hate speech benchmarks play a crucial role to ensure model safety. In this paper, we empirically evaluate the robustness of 20 language models across two evolving hate speec…