English
Related papers

Related papers: Training-Driven Representational Geometry Modulari…

200 papers

Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a notable property: fine-tuned models preserve the geometric…

Machine Learning · Computer Science 2025-11-25 Thong Bach , Thanh Nguyen-Tang , Dung Nguyen , Thao Minh Le , Truyen Tran

Inferring geometrically consistent dense 3D scenes across a tuple of temporally consecutive images remains challenging for self-supervised monocular depth prediction pipelines. This paper explores how the increasingly popular transformer…

Computer Vision and Pattern Recognition · Computer Science 2021-10-18 Patrick Ruhkamp , Daoyi Gao , Hanzhi Chen , Nassir Navab , Benjamin Busam

Recent years have witnessed the prevalent application of pre-trained language models (PLMs) in NLP. From the perspective of parameter space, PLMs provide generic initialization, starting from which high-performance minima could be found.…

Computation and Language · Computer Science 2022-10-26 Yujia Qin , Cheng Qian , Jing Yi , Weize Chen , Yankai Lin , Xu Han , Zhiyuan Liu , Maosong Sun , Jie Zhou

This paper demonstrates that progressive localization, the gradual increase of attention locality from early distributed layers to late localized layers, represents the optimal architecture for creating interpretable large language models…

Artificial Intelligence · Computer Science 2025-12-16 Joachim Diederich

Neurons in the brain are spatially organized such that neighbors on tissue often exhibit similar response profiles. In the human language system, experimental studies have observed clusters for syntactic and semantic categories, but the…

Computation and Language · Computer Science 2025-05-16 Neil Rathi , Johannes Mehrer , Badr AlKhamissi , Taha Binhuraib , Nicholas M. Blauch , Martin Schrimpf

Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based…

Computation and Language · Computer Science 2025-04-08 Samuele Marro , Davide Evangelista , X. Angelo Huang , Emanuele La Malfa , Michele Lombardi , Michael Wooldridge

Recent studies suggest that the representations learned by large language models (LLMs) are partially aligned to those of the human brain. However, whether and why this alignment score arises from a similar sequence of computations remains…

Machine Learning · Computer Science 2025-12-02 Joséphine Raugel , Stéphane d'Ascoli , Jérémy Rapin , Valentin Wyart , Jean-Rémi King

Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling…

Computation and Language · Computer Science 2025-09-25 Benedikt Roth , Stephan Rappensperger , Tianming Qiu , Hamza Imamović , Julian Wörmann , Hao Shen

Solving complex long-horizon robotic manipulation problems requires sophisticated high-level planning capabilities, the ability to reason about the physical world, and reactively choose appropriate motor skills. Vision-language models…

Robotics · Computer Science 2025-02-25 Yunhai Feng , Jiaming Han , Zhuoran Yang , Xiangyu Yue , Sergey Levine , Jianlan Luo

Audio Large Language Models (Audio LLMs) have demonstrated strong capabilities in integrating speech perception with language understanding. However, whether their internal representations align with human neural dynamics during…

Sound · Computer Science 2026-02-04 Haoyun Yang , Xin Xiao , Jiang Zhong , Yu Tian , Dong Xiaohua , Yu Mao , Hao Wu , Kaiwen Wei

Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human,…

Computation and Language · Computer Science 2025-05-29 Tom Kouwenhoven , Max Peeperkorn , Roy de Kleijn , Tessa Verhoef

Recent work using auxiliary prediction task classifiers to investigate the properties of LSTM representations has begun to shed light on why pretrained representations, like ELMo (Peters et al., 2018) and CoVe (McCann et al., 2017), are so…

Computation and Language · Computer Science 2019-01-08 Kelly W. Zhang , Samuel R. Bowman

We characterize how memorization is represented in transformer models and show that it can be disentangled in the weights of both language models (LMs) and vision transformers (ViTs) using a decomposition based on the loss landscape…

Computation and Language · Computer Science 2025-11-03 Jack Merullo , Srihita Vatsavaya , Lucius Bushnaq , Owen Lewis

Large Language Models (LLMs) do not differentially represent numbers, which are pervasive in text. In contrast, neuroscience research has identified distinct neural representations for numbers and words. In this work, we investigate how…

Artificial Intelligence · Computer Science 2024-01-10 Raj Sanjay Shah , Vijay Marupudi , Reba Koenen , Khushi Bhardwaj , Sashank Varma

Pretrained language models are remarkably effective in aligning with human brain responses elicited by natural language stimuli, positioning them as promising model organisms for studying language processing in the brain. However, existing…

Computation and Language · Computer Science 2025-10-27 Omer Moussa , Mariya Toneva

Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory…

Machine Learning · Computer Science 2025-10-13 Kaiyan Zhao , Tsuguchika Tabaru , Kenichi Kobayashi , Takumi Honda , Masafumi Yamazaki , Yoshimasa Tsuruoka

Pretrained models have produced great success in both Computer Vision (CV) and Natural Language Processing (NLP). This progress leads to learning joint representations of vision and language pretraining by feeding visual and linguistic…

Computer Vision and Pattern Recognition · Computer Science 2022-05-05 Siqu Long , Feiqi Cao , Soyeon Caren Han , Haiqin Yang

Pretraining data has a direct impact on the behaviors and quality of language models (LMs), but we only understand the most basic principles of this relationship. While most work focuses on pretraining data's effect on downstream task…

Computation and Language · Computer Science 2025-04-18 Jack Merullo , Noah A. Smith , Sarah Wiegreffe , Yanai Elazar

Following the impressive development of LLMs, vision-language alignment in LLMs is actively being researched to enable multimodal reasoning and visual IO. This direction of research is particularly relevant to medical imaging because…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Suhyeon Lee , Won Jun Kim , Jinho Chang , Jong Chul Ye

When we read, we make predictions about upcoming words; these predictions influence our reading behavior. The success of large language models (LLMs), which, like humans, make predictions about upcoming words, has motivated their use as…

Computation and Language · Computer Science 2026-05-27 Byung-Doh Oh , Tal Linzen