Blog(6)

• 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.

• LittleBit: Ultra Low-Bit Quantization via Latent Factorization

  Large Language Models (LLMs) have transformed technology, but their massive size presents a significant barrier to deployment. The huge memory and computational costs, especially GPU VRAM, make it difficult to run these powerful models on consumer-grade or edge devices.

View More

Research Areas(0)

Publications(20)

• Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition

  AuthorTitouan Parcollet, Rogier van Dalen, Shucong Zhang

  PublishedIEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)

  Date2025-12-06

• Compress & Cache: Vision token compression for efficient generation and retrieval

  AuthorAdrian Bulat, Yassine Ouali, Georgios Tzimiropoulos

  PublishedNeural Information Processing Systems (NeurIPS)

  Date2025-12-03

• LittleBit: Ultra-Low Bit Quantization via Latent Factorization

  AuthorBanseok Lee, Dongkyu Kim, Youngcheon You, Youngmin Kim

  PublishedNeural Information Processing Systems (NeurIPS)

  Date2025-12-02

View More

News(8)

• [Blog] LittleBit: Ultra Low-Bit Quantization via Latent Factorization

  Large Language Models (LLMs) have transformed technology, but their massive size presents a significant barrier to deployment. The huge memory and computational costs, especially GPU VRAM, make it difficult to run these powerful models on consumer-grade or edge devices.

• [Blog] Efficient Compositional Multi-tasking for On-device Large Language Models

  Adapter parameters [2] provide a mechanism to modify the behaviour of machine learning models and have gained significant popularity in the context of large language models (LLMs) and generative AI.

• [Blog] SemEval-2025 Task 8: LLM Ensemble Methods for QA over Tabular Data

  Question answering using Large Language Models has gained significant popularity in both everyday communication and at the workplace. However|certain tasks|such as querying tables|still pose challenges for commercial and open-source chatbots powered by advanced deep learning models.

View More

Others(0)