Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) systems in diverse target domains, such as noise and accents. STAR is developed for prevalent speech foundation models based on Transformer-related architecture with auto-regressive decoding (e.g., Whisper, Canary). Specifically, we propose a novel indicator that empirically integrates step-wise information during decoding to assess the token-level quality of pseudo labels without ground truth, thereby guiding model updates for effective unsupervised adaptation. Experimental results show that STAR achieves an average of 13.5% relative reduction in word error rate across 14 target domains, and it sometimes even approaches the upper-bound performance of supervised adaptation. Surprisingly, we also observe that STAR prevents the adapted model from the common catastrophic forgetting problem without recalling source-domain data. Furthermore, STAR exhibits high data efficiency that only requires less than one-hour unlabeled data, and seamless generality to alternative large speech models and speech translation tasks. Our code aims to open source to the research communities.

Just rephrase it! Uncertainty estimation in closed-source language models via multiple rephrased queries

State-of-the-art large language models are sometimes distributed as open-source software but are also increasingly provided as a closed-source service. These closed-source large-language models typically see the widest usage by the public, however, they often do not provide an estimate of their uncertainty when responding to queries. As even the best models are prone to ``hallucinating" false information with high confidence, a lack of a reliable estimate of uncertainty limits the applicability of these models in critical settings. We explore estimating the uncertainty of closed-source LLMs via multiple rephrasings of an original base query. Specifically, we ask the model, multiple rephrased questions, and use the similarity of the answers as an estimate of uncertainty. We diverge from previous work in i) providing rules for rephrasing that are simple to memorize and use in practice ii) proposing a theoretical framework for why multiple rephrased queries obtain calibrated uncertainty estimates. Our method demonstrates significant improvements in the calibration of uncertainty estimates compared to the baseline and provides intuition as to how query strategies should be designed for optimal test calibration.

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

Latent generative models (e.g., Stable Diffusion) have become more and more popular, but concerns have arisen regarding potential misuse related to images generated by these models. It is, therefore, necessary to analyze the origin of images by inferring if a particular image was generated by a specific latent generative model. Most existing methods (e.g., image watermark and model fingerprinting) require extra steps during training or generation. These requirements restrict their usage on the generated images without such extra operations, and the extra required operations might compromise the quality of the generated images. In this work, we ask whether it is possible to effectively and efficiently trace the images generated by a specific latent generative model without the aforementioned requirements. To study this problem, we design a latent inversion based method called LatentTracer to trace the generated images of the inspected model by checking if the examined images can be well-reconstructed with an inverted latent input. We leverage gradient based latent inversion and identify a encoder-based initialization critical to the success of our approach. Our experiments on the state-of-the-art latent generative models, such as Stable Diffusion, show that our method can distinguish the images generated by the inspected model and other images with a high accuracy and efficiency. Our findings suggest the intriguing possibility that today's latent generative generated images are naturally watermarked by the decoder used in the source models. Code: https://github.com/ZhentingWang/LatentTracer.

Multi-View Attentive Contextualization for Multi-View 3D Object Detection

We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection. Despite remarkable progress witnessed in the field of query-based MV3D object detection, prior art often suffers from either the lack of exploiting high-resolution 2D features in dense attention-based lifting, due to high computational costs, or from insufficiently dense grounding of 3D queries to multi-scale 2D features in sparse attention-based lifting. Our proposed MvACon hits the two birds with one stone using a representationally dense yet computationally sparse attentive feature contextualization scheme that is agnostic to specific 2D-to-3D feature lifting approaches. In experiments, the proposed MvACon is thoroughly tested on the nuScenes benchmark, using both the BEVFormer and its recent 3D deformable attention (DFA3D) variant, as well as the PETR, showing consistent detection performance improvement, especially in enhancing performance in location, orientation, and velocity prediction. It is also tested on the Waymo-mini benchmark using BEVFormer with similar improvement. We qualitatively and quantitatively show that global cluster-based contexts effectively encode dense scene-level contexts for MV3D object detection. The promising results of our proposed MvACon reinforces the adage in computer vision -- ``(contextualized) feature matters".

SignLLM: Sign Languages Production Large Language Models

In this paper, we introduce the first comprehensive multilingual sign language dataset named Prompt2Sign, which builds from public data including American Sign Language (ASL) and seven others. Our dataset transforms a vast array of videos into a streamlined, model-friendly format, optimized for training with translation models like seq2seq and text2text. Building on this new dataset, we propose SignLLM, the first multilingual Sign Language Production (SLP) model, which includes two novel multilingual SLP modes that allow for the generation of sign language gestures from input text or prompt. Both of the modes can use a new loss and a module based on reinforcement learning, which accelerates the training by enhancing the model's capability to autonomously sample high-quality data. We present benchmark results of SignLLM, which demonstrate that our model achieves state-of-the-art performance on SLP tasks across eight sign languages.

Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models

Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which aims to predict the ground-truth transcription from the decoded N-best hypotheses. Thanks to the strong language generation ability of LLMs and rich information in the N-best list, GER shows great effectiveness in enhancing ASR results. However, it still suffers from two limitations: 1) LLMs are unaware of the source speech during GER, which may lead to results that are grammatically correct but violate the source speech content, 2) N-best hypotheses usually only vary in a few tokens, making it redundant to send all of them for GER, which could confuse LLM about which tokens to focus on and thus lead to increased miscorrection. In this paper, we propose ClozeGER, a new paradigm for ASR generative error correction. First, we introduce a multimodal LLM (i.e., SpeechGPT) to receive source speech as extra input to improve the fidelity of correction output. Then, we reformat GER as a cloze test with logits calibration to remove the input information redundancy and simplify GER with clear instructions. Experiments show that ClozeGER achieves a new breakthrough over vanilla GER on 9 popular ASR datasets.

Visual Attention Based Cognitive Human-Robot Collaboration for Pedicle Screw Placement in Robot-Assisted Orthopedic Surgery

Current orthopedic robotic systems largely focus on navigation, aiding surgeons in positioning a guiding tube but still requiring manual drilling and screw placement. The automation of this task not only demands high precision and safety due to the intricate physical interactions between the surgical tool and bone but also poses significant risks when executed without adequate human oversight. As it involves continuous physical interaction, the robot should collaborate with the surgeon, understand the human intent, and always include the surgeon in the loop. To achieve this, this paper proposes a new cognitive human-robot collaboration framework, including the intuitive AR-haptic human-robot interface, the visual-attention-based surgeon model, and the shared interaction control scheme for the robot. User studies on a robotic platform for orthopedic surgery are presented to illustrate the performance of the proposed method. The results demonstrate that the proposed human-robot collaboration framework outperforms full robot and full human control in terms of safety and ergonomics.

Cross-Domain Continual Learning via CLAMP

Artificial neural networks, celebrated for their human-like cognitive learning abilities, often encounter the well-known catastrophic forgetting (CF) problem, where the neural networks lose the proficiency in previously acquired knowledge. Despite numerous efforts to mitigate CF, it remains the significant challenge particularly in complex changing environments. This challenge is even more pronounced in cross-domain adaptation following the continual learning (CL) setting, which is a more challenging and realistic scenario that is under-explored. To this end, this article proposes a cross-domain CL approach making possible to deploy a single model in such environments without additional labelling costs. Our approach, namely continual learning approach for many processes (CLAMP), integrates a class-aware adversarial domain adaptation strategy to align a source domain and a target domain. An assessor-guided learning process is put forward to navigate the learning process of a base model assigning a set of weights to every sample controlling the influence of every sample and the interactions of each loss function in such a way to balance the stability and plasticity dilemma thus preventing the CF problem. The first assessor focuses on the negative transfer problem rejecting irrelevant samples of the source domain while the second assessor prevents noisy pseudo labels of the target domain. Both assessors are trained in the meta-learning approach using random transformation techniques and similar samples of the source domain. Theoretical analysis and extensive numerical validations demonstrate that CLAMP significantly outperforms established baseline algorithms across all experiments by at least $10\%$ margin.

Frame Interpolation with Consecutive Brownian Bridge Diffusion

Recent work in Video Frame Interpolation (VFI) tries to formulate VFI as a diffusion-based conditional image generation problem, synthesizing the intermediate frame given a random noise and neighboring frames. Due to the relatively high resolution of videos, Latent Diffusion Models (LDMs) are employed as the conditional generation model, where the autoencoder compresses images into latent representations for diffusion and then reconstructs images from these latent representations. Such a formulation poses a crucial challenge: VFI expects that the output is deterministically equal to the ground truth intermediate frame, but LDMs randomly generate a diverse set of different images when the model runs multiple times. The reason for the diverse generation is that the cumulative variance (variance accumulated at each step of generation) of generated latent representations in LDMs is large. This makes the sampling trajectory random, resulting in diverse rather than deterministic generations. To address this problem, we propose our unique solution: Frame Interpolation with Consecutive Brownian Bridge Diffusion. Specifically, we propose consecutive Brownian Bridge diffusion that takes a deterministic initial value as input, resulting in a much smaller cumulative variance of generated latent representations. Our experiments suggest that our method can improve together with the improvement of the autoencoder and achieve state-of-the-art performance in VFI, leaving strong potential for further enhancement.

Efficient Pretraining Model based on Multi-Scale Local Visual Field Feature Reconstruction for PCB CT Image Element Segmentation

Element segmentation is a key step in nondestructive testing of Printed Circuit Boards (PCB) based on Computed Tomography (CT) technology. In recent years, the rapid development of self-supervised pretraining technology can obtain general image features without labeled samples, and then use a small amount of labeled samples to solve downstream tasks, which has a good potential in PCB element segmentation. At present, Masked Image Modeling (MIM) pretraining model has been initially applied in PCB CT image element segmentation. However, due to the small and regular size of PCB elements such as vias, wires, and pads, the global visual field has redundancy for a single element reconstruction, which may damage the performance of the model. Based on this issue, we propose an efficient pretraining model based on multi-scale local visual field feature reconstruction for PCB CT image element segmentation (EMLR-seg). In this model, the teacher-guided MIM pretraining model is introduced into PCB CT image element segmentation for the first time, and a multi-scale local visual field extraction (MVE) module is proposed to reduce redundancy by focusing on local visual fields. At the same time, a simple 4-Transformer-blocks decoder is used. Experiments show that EMLR-seg can achieve 88.6% mIoU on the PCB CT image dataset we proposed, which exceeds 1.2% by the baseline model, and the training time is reduced by 29.6 hours, a reduction of 17.4% under the same experimental condition, which reflects the advantage of EMLR-seg in terms of performance and efficiency.