Hugging Face Trending Papers June 3, 2026

DLLG: Dynamic Logit-Level Gating of LLM Experts

Read the original on Hugging Face Trending Papers →

Leveraging multiple specialized LLMs can combine complementary strengths, but existing approaches trade adaptability for stability: routing commits prematurely, heuristic ensembling depends on fragile proxies, and parameter merging introduces interference. We propose DLLG (Dynamic Logit-Level Gating), a dynamic logit-level ensembling framework that learns token-level expert fusion from sparse response-level supervision.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 15

Token-Level LLM Collaboration via FusionRoute

arXiv:2601. 05106v5 Announce Type: replace Abstract: Large language models (LLMs) exhibit strengths across diverse domains.

By Nuoya Xiong, Yuhang Zhou, Hanqing Zeng, Zhaorun Chen, Furong Huang, Shuchao Bi, Lizhu Zhang, Zhuokai Zhao

llms fine-tuning benchmarks

arXiv AI

Jun 4

Adaptive Minds: Empowering Agents with LoRA-as-Tools

arXiv:2510. 15416v2 Announce Type: replace Abstract: We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke.

By Pavan C Shekar, Aswanth Krishnan

llms agents fine-tuning benchmarks

arXiv AI

Jun 26

Tuning Language Models by Mixture-of-Depths Ensemble

arXiv:2410. 13077v2 Announce Type: replace-cross Abstract: Transformer-based Large Language Models (LLMs) traditionally rely on final-layer loss for finetuning and final-layer representations for predictions, potentially overlooking the predictive power embedded in late layers.

By Haoyan Luo, Lucia Specia

llms fine-tuning safety

arXiv AI

Aug 10

TEXAS: Task-Expert-Aware Supervision for Downstream Mixture-of-Experts LLM Adaptation

arXiv:2608. 06396v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models route each token through a small subset of experts, making routing patterns useful for identifying task-relevant experts during downstream adaptation.

By Guanzhi Deng, Haibo Wang, Kuan Wu, Xiangru Jian, Shing Yin Wong, Sichun Luo, Zhuoran Wang, Linqi Song

llms fine-tuning benchmarks

arXiv AI

Jun 3

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

arXiv:2606. 03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static.

By Guhong Chen, Yingcheng Shi, Yongbin Li, Binhua Li, Xander Xu, Hu Wei, Shiwen Ni, Min Yang, Jieping Ye

llms agents reinforcement-learning

arXiv Machine Learning

Jun 5

IR3DE: A Linear Router for Large Language Models

arXiv:2606. 06098v1 Announce Type: cross Abstract: Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialized tasks via domain-expert LLMs.

By Eros Fan\`i, O\u{g}uzhan Ersoy

llms

Related stories

Token-Level LLM Collaboration via FusionRoute

Adaptive Minds: Empowering Agents with LoRA-as-Tools

Tuning Language Models by Mixture-of-Depths Ensemble

TEXAS: Task-Expert-Aware Supervision for Downstream Mixture-of-Experts LLM Adaptation

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

IR3DE: A Linear Router for Large Language Models