中文
相关论文

相关论文: Neural Steerer: Novel Steering Vector Synthesis wi…

200 篇论文

We propose a differentiable imaging framework to address uncertainty in measurement coordinates such as sensor locations and projection angles. We formulate the problem as measurement interpolation at unknown nodes supervised through the…

图像与视频处理 · 电气工程与系统科学 2023-12-21 Sidharth Gupta , Konik Kothari , Valentin Debarnot , Ivan Dokmanić

Flow matching models typically use linear interpolants to define the forward/noise addition process. This, together with the independent coupling between noise and target distributions, yields a vector field which is often non-straight.…

机器学习 · 计算机科学 2025-03-27 Shiv Shankar , Tomas Geffner

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…

计算与语言 · 计算机科学 2026-02-23 Joschka Braun

Recent advances in flow-based generative models have enabled training-free, text-guided image editing by inverting an image into its latent noise and regenerating it under a new target conditional guidance. However, existing methods…

计算机视觉与模式识别 · 计算机科学 2026-04-03 Thinh Dao , Zhen Wang , Kien T. Pham , Long Chen

Neuro-steered speaker extraction aims to extract the listener's brain-attended speech signal from a multi-talker speech signal, in which the attention is derived from the cortical activity. This activity is usually recorded using…

音频与语音处理 · 电气工程与系统科学 2023-12-13 Zexu Pan , Gordon Wichern , Francois G. Germain , Sameer Khurana , Jonathan Le Roux

Activation steering -- adding a vector to a model's residual stream to modify its behavior -- is widely used in safety evaluations as if the model cannot detect the intervention. We test this assumption, introducing steering awareness: a…

计算与语言 · 计算机科学 2026-03-20 Joshua Fonseca Rivera , David Demitri Africa

Recent works on deep non-linear spatially selective filters demonstrate exceptional enhancement performance with computationally lightweight architectures for stationary speakers of known directions. However, to maintain this performance in…

音频与语音处理 · 电气工程与系统科学 2025-07-08 Jakob Kienegger , Alina Mannanova , Huajian Fang , Timo Gerkmann

Can machines recording an audio-visual scene produce realistic, matching audio-visual experiences at novel positions and novel view directions? We answer it by studying a new task -- real-world audio-visual scene synthesis -- and a…

计算机视觉与模式识别 · 计算机科学 2023-10-17 Susan Liang , Chao Huang , Yapeng Tian , Anurag Kumar , Chenliang Xu

Neural Radiance Field (NeRF) has shown impressive performance in novel view synthesis via implicit scene representation. However, it usually suffers from poor scalability as requiring densely sampled images for each new scene. Several…

计算机视觉与模式识别 · 计算机科学 2023-10-27 Muyu Xu , Fangneng Zhan , Jiahui Zhang , Yingchen Yu , Xiaoqin Zhang , Christian Theobalt , Ling Shao , Shijian Lu

Neural fields excel at representing continuous visual signals but typically operate at a single, fixed resolution. We present a simple yet powerful method to optimize neural fields that can be prefiltered in a single forward pass. Key…

图形学 · 计算机科学 2026-02-06 Mustafa B. Yaldiz , Ishit Mehta , Nithin Raghavan , Andreas Meuleman , Tzu-Mao Li , Ravi Ramamoorthi

We show that the task of synthesizing human motion conditioned on a set of key frames can be solved more accurately and effectively if a deep learning based interpolator operates in the delta mode using the spherical linear interpolator as…

Symbolic music generation has made significant progress, yet achieving fine-grained and flexible control over composer style remains challenging. Existing training-based methods for composer style conditioning depend on large labeled…

声音 · 计算机科学 2026-04-07 Xunyi Jiang , Mingyang Yao , Jingyue Huang , Julian McAuley

We propose an independence-based joint dereverberation and separation method with a neural source model. We introduce a neural network in the framework of time-decorrelation iterative source steering, which is an extension of independent…

音频与语音处理 · 电气工程与系统科学 2022-04-04 Kohei Saijo , Robin Scheibler

Frame interpolation is an essential video processing technique that adjusts the temporal resolution of an image sequence. While deep learning has brought great improvements to the area of video frame interpolation, techniques that make use…

计算机视觉与模式识别 · 计算机科学 2022-10-27 Simon Niklaus , Ping Hu , Jiawen Chen

In the context of a voice assistant system, steering refers to the phenomenon in which a user issues a follow-up command attempting to direct or clarify a previous turn. We propose STEER, a steering detection model that predicts whether a…

Neural Radiance Fields (NeRF) achieve photo-realistic view synthesis with densely captured input images. However, the geometry of NeRF is extremely under-constrained given sparse views, resulting in significant degradation of novel view…

计算机视觉与模式识别 · 计算机科学 2022-09-13 Zheng Chen , Chen Wang , Yuan-Chen Guo , Song-Hai Zhang

The versatility of recent machine learning approaches makes them ideal for improvement of next generation video compression solutions. Unfortunately, these approaches typically bring significant increases in computational complexity and are…

图像与视频处理 · 电气工程与系统科学 2021-06-18 Luka Murn , Saverio Blasi , Alan F. Smeaton , Marta Mrak

The generation of high-fidelity view synthesis is essential for robotic navigation and interaction but remains challenging, particularly in indoor environments and real-time scenarios. Existing techniques often require significant…

计算机视觉与模式识别 · 计算机科学 2024-12-05 Sen Wang , Qing Cheng , Stefano Gasperini , Wei Zhang , Shun-Cheng Wu , Niclas Zeller , Daniel Cremers , Nassir Navab

The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines. However, traditional numerical solvers are limited by the choice of step sizes when estimating integration, resulting in a…

计算工程、金融与科学 · 计算机科学 2023-09-21 Zhongzhan Huang , Senwei Liang , Hong Zhang , Haizhao Yang , Liang Lin

Audio deepfakes are acquiring an unprecedented level of realism with advanced AI. While current research focuses on discerning real speech from spoofed speech, tracing the source system is equally crucial. This work proposes a novel audio…

声音 · 计算机科学 2025-06-04 Ajinkya Kulkarni , Sandipana Dowerah , Tanel Alumae , Mathew Magimai. -Doss