Related papers: Llamazip: Leveraging LLaMA for Lossless Text Compr…

With the booming of Large Language Models (LLMs), prompt-learning has become a promising method mainly researched in various research areas. Recently, many attempts based on prompt-learning have been made to improve the performance of text…

Large Language Models revolutionized NLP and showed dramatic performance improvements across several tasks. In this paper, we investigated the role of such language models in text classification and how they compare with other approaches…

Contrastive Language-Image Pre-training (CLIP) models have shown significant potential, particularly in zero-shot classification across diverse distribution shifts. Building on existing evaluations of overall classification robustness, this…

In speech deepfake detection, one of the critical aspects is developing detectors able to generalize on unseen data and distinguish fake signals across different datasets. Common approaches to this challenge involve incorporating diverse…

Large Multimodal Models (LMMs) such as LLaVA are typically trained with an autoregressive language modeling objective, providing only indirect supervision to visual tokens. This often yields weak internal visual representations and brittle…

We present a framework facilitating the implementation and comparison of text compression algorithms. We evaluate its features by a case study on two novel compression algorithms based on the Lempel-Ziv compression schemes that perform well…

Communication has emerged as a critical bottleneck in the distributed training of large language models (LLMs). While numerous approaches have been proposed to reduce communication overhead, the potential of lossless compression has…

Large Language Models (LLMs) have shown exceptional capabilities in Natural Language Processing (NLP) across diverse domains. However, their application in specialized tasks such as Legal Judgment Prediction (LJP) for low-resource languages…

The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misinformation, impersonation, and content forgery. Most existing detection approaches…

Recent advancements in vision-language models have enhanced performance by increasing the length of visual tokens, making them much longer than text tokens and significantly raising computational costs. However, we observe that the visual…

We introduce LAMBADA, a dataset to evaluate the capabilities of computational models for text understanding by means of a word prediction task. LAMBADA is a collection of narrative passages sharing the characteristic that human subjects are…

With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast model compression literature deleting parts of…

Training-free video large language models (LLMs) leverage pretrained Image LLMs to process video content without the need for further training. A key challenge in such approaches is the difficulty of retaining essential visual and temporal…

This work explores expanding the capabilities of large language models (LLMs) pretrained on text to generate 3D meshes within a unified model. This offers key advantages of (1) leveraging spatial knowledge already embedded in LLMs, derived…

Recently, Large Language Models (LLMs) have witnessed remarkable performance as zero-shot task planners for robotic manipulation tasks. However, the open-loop nature of previous works makes LLM-based planning error-prone and fragile. On the…

Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…

Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored.…

Learning and compression are driven by the common aim of identifying and exploiting statistical regularities in data, which opens the door for fertile collaboration between these areas. A promising group of compression techniques for…

Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks, ranging from speech recognition to general audio understanding. However, their scalability is limited by the quadratic complexity of attention and…

Large Language Models (LLMs) utilize extensive knowledge databases and show powerful text generation ability. However, their reliance on high-quality copyrighted datasets raises concerns about copyright infringements in generated texts.…