Blog(8)

• RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs

  The rapid advancement of Large Language Model (LLM) capabilities has been accompanied by a significant increase in model parameter scale.

• A Class-Balanced Soft-Voting System for Detecting Multi-Generator Machine-Generated Text

  SemEval-2024 Task 8 provides a challenge to detect human-written and machine-generated text. There are 3 subtasks for different detection scenarios. This paper proposes a system that mainly deals with Subtask B.

• Towards LLM-Based Automatic Boundary Detection for Human-Machine Mixed Text

  Large Language Models (LLMs), particularly the debut of ChatGPT, have made significant advancement and demonstrated the ability to produce coherent and natural-sounding text across a wide range of applications.

View More

Research Areas(0)

Publications(32)

• K-Merge: Online Continual Merging of Adapters for On-device Large Language Models

  AuthorOndrej Bohdal, Mete Ozay

  PublishedThe 64th Annual Meeting of the Association for Computational Linguistics (ACL)

  Date2026-07-02

• VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions

  AuthorAdrian Bulat, Alberto Baldrati, Ioannis Maniadis Metaxas, Yassine Ouali, Georgios Tzimiropoulos

  PublishedThe IEEE/CVF Conference on Computer Vision and Pattern (CVPR) Recognition 2026

  Date2026-06-05

• Two-Stage Grid Optimization for Group-wise Quantization of LLMs

  AuthorGukryeol Lee, Jeewook Kim, Yongkweon Jeon

  PublishedIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

  Date2026-05-04

View More

News(15)

• [Blog] LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment

  Large Language Models (LLMs) continue to deliver remarkable capabilities, but their memory footprint remains a rigid barrier to deployment.

• [Blog] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

  Weight-only quantization of Large Language Models (LLMs) aims to make LLM serving efficient by reducing parameter precision.

• [Blog] RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs

  The rapid advancement of Large Language Model (LLM) capabilities has been accompanied by a significant increase in model parameter scale.

View More

Others(0)