English
Related papers

Related papers: CAST: Compositional Analysis via Spectral Tracking…

200 papers

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of…

Computation and Language · Computer Science 2026-05-04 Gaofei Shen , Martijn Bentum , Tom Lentz , Afra Alishahi , Grzegorz Chrupała

Neurons in auto-regressive language models like GPT-2 can be interpreted by analyzing their activation patterns. Recent studies have shown that techniques such as dictionary learning, a form of post-hoc sparse coding, enhance this…

Computation and Language · Computer Science 2025-02-28 Hao Bai , Yi Ma

Audio-visual video segmentation~(AVVS) aims to generate pixel-level maps of sound-producing objects within image frames and ensure the maps faithfully adhere to the given audio, such as identifying and segmenting a singing person in a…

Computer Vision and Pattern Recognition · Computer Science 2023-09-21 Kexin Li , Zongxin Yang , Lei Chen , Yi Yang , Jun Xiao

Analyzing the similarity of internal representations has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such…

Artificial Intelligence · Computer Science 2025-05-26 Jiachen Jiang , Jinxin Zhou , Zhihui Zhu

Linear recurrent models offer linear-time sequence processing but often suffer from suboptimal long-range memory. We trace this to the decay spectrum: for $N$ channels, random initialization collapses the minimum spectral gap to…

Machine Learning · Computer Science 2026-04-10 Yang Cao

We introduce a new approach to systematically map features discovered by sparse autoencoder across consecutive layers of large language models, extending earlier work that examined inter-layer feature links. By using a data-free cosine…

Machine Learning · Computer Science 2025-07-28 Daniil Laptev , Nikita Balagansky , Yaroslav Aksenov , Daniil Gavrilov

To achieve deep natural language understanding, syntactic constituent parsing plays a crucial role and is widely required by many artificial intelligence systems for processing both text and speech. A recent approach involves using standard…

Computation and Language · Computer Science 2026-05-14 Daniel Fernández-González , Cristina Outeiriño Cid

Recovering high-quality 3D scenes from a single RGB image is a challenging task in computer graphics. Current methods often struggle with domain-specific limitations or low-quality object generation. To address these, we propose CAST…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Kaixin Yao , Longwen Zhang , Xinhao Yan , Yan Zeng , Qixuan Zhang , Wei Yang , Lan Xu , Jiayuan Gu , Jingyi Yu

Transformer framework has been showing superior performances in visual object tracking for its great strength in information aggregation across the template and search image with the well-known attention mechanism. Most recent advances…

Computer Vision and Pattern Recognition · Computer Science 2023-01-27 Zikai Song , Run Luo , Junqing Yu , Yi-Ping Phoebe Chen , Wei Yang

Convolution and cross-correlation are the basis of filtering and pattern or template matching in multimedia signal processing. We propose two throughput scaling options for any one-dimensional convolution kernel in programmable processors…

Multimedia · Computer Science 2012-01-17 Mohammad Ashraful Anam , Yiannis Andreopoulos

Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum,via a naive convolution…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-16 Liming Zhou , Yongyu Gao , Ziluo Wang , Jiwei Li , Wenbin Zhang

Recent advances in diffusion-based generative models have achieved remarkable visual fidelity, yet a detailed understanding of how specific perceptual attributes - such as color and shape - are internally represented remains limited. This…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Guillem Arias , Ariadna Solà , Martí Armengod , Maria Vanrell

Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges as a solution, enabling the simultaneous generation and…

Computation and Language · Computer Science 2026-02-27 Yinrong Hong , Zhiquan Tan , Kai Hu

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…

Computer Vision and Pattern Recognition · Computer Science 2022-06-01 Peng Dai , Yiqiang Feng , Renliang Weng , Changshui Zhang

Transformers are powerful neural architectures that allow integrating different modalities using attention mechanisms. In this paper, we leverage the neural transformer architectures for multi-channel speech recognition systems, where the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-09 Feng-Ju Chang , Martin Radfar , Athanasios Mouchtaris , Brian King , Siegfried Kunzmann

Large-scale molecular representation methods have revolutionized applications in material science, such as drug discovery, chemical modeling, and material design. With the rise of transformers, models now learn representations directly from…

Computational Engineering, Finance, and Science · Computer Science 2024-10-17 Indra Priyadarsini , Seiji Takeda , Lisa Hamada , Emilio Vital Brazil , Eduardo Soares , Hajime Shinohara

As video content creation shifts toward long-form narratives, composing short clips into coherent storylines becomes increasingly important. However, prevailing retrieval formulations remain context-agnostic at inference time, prioritizing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yanqing Liu , Yingcheng Liu , Fanghong Dong , Budianto Budianto , Cihang Xie , Yan Jiao

Transformer architectures have emerged as promising deep learning (DL) tools for modeling complex sequence-to-sequence interactions in channel decoding. However, current transformer-based decoders for error correction codes (ECCs)…

Signal Processing · Electrical Eng. & Systems 2025-07-22 Hongzhi Zhu , Wei Xu , Xiaohu You

Semantic segmentation involves assigning a specific category to each pixel in an image. While Vision Transformer-based models have made significant progress, current semantic segmentation methods often struggle with precise predictions in…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Guoan Xu , Wenfeng Huang , Tao Wu , Ligeng Chen , Wenjing Jia , Guangwei Gao , Xiatian Zhu , Stuart Perry

Despite the strong performance of large audio language models (LALMs) in various tasks, exactly how and where they integrate acoustic features with textual context remains unclear. We adapt causal tracing to investigate the internal…

Sound · Computer Science 2026-03-17 Wei-Chih Chen , Chien-yu Huang , Hung-yi Lee