SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation

We introduce SeaDAG, a semi-autoregressive diffusion model for conditional generation of Directed Acyclic Graphs (DAGs). Considering their inherent layer-wise structure, we simulate layer-wise autoregressive generation by designing different denoising speed for different layers. Unlike conventional autoregressive generation that lacks a global graph structure view, our method maintains a complete graph structure at each diffusion step, enabling operations such as property control that require the full graph structure. Leveraging this capability, we evaluate the DAG properties during training by employing a graph property decoder. We explicitly train the model to learn graph conditioning with a condition loss, which enhances the diffusion model's capacity to generate graphs that are both realistic and aligned with specified properties. We evaluate our method on two representative conditional DAG generation tasks: (1) circuit generation from truth tables, where precise DAG structures are crucial for realizing circuit functionality, and (2) molecule generation based on quantum properties. Our approach demonstrates promising results, generating high-quality and realistic DAGs that closely align with given conditions.

Cross-attention Inspired Selective State Space Models for Target Sound Extraction

The Transformer model, particularly its cross-attention module, is widely used for feature fusion in target sound extraction which extracts the signal of interest based on given clues. Despite its effectiveness, this approach suffers from low computational efficiency. Recent advancements in state space models, notably the latest work Mamba, have shown comparable performance to Transformer-based methods while significantly reducing computational complexity in various tasks. However, Mamba's applicability in target sound extraction is limited due to its inability to capture dependencies between different sequences as the cross-attention does. In this paper, we propose CrossMamba for target sound extraction, which leverages the hidden attention mechanism of Mamba to compute dependencies between the given clues and the audio mixture. The calculation of Mamba can be divided to the query, key and value. We utilize the clue to generate the query and the audio mixture to derive the key and value, adhering to the principle of the cross-attention mechanism in Transformers. Experimental results from two representative target sound extraction methods validate the efficacy of the proposed CrossMamba.

DENSE: Dynamic Embedding Causal Target Speech Extraction

Target speech extraction (TSE) focuses on extracting the speech of a specific target speaker from a mixture of signals. Existing TSE models typically utilize static embeddings as conditions for extracting the target speaker's voice. However, the static embeddings often fail to capture the contextual information of the extracted speech signal, which may limit the model's performance. We propose a novel dynamic embedding causal target speech extraction model to address this limitation. Our approach incorporates an autoregressive mechanism to generate context-dependent embeddings based on the extracted speech, enabling real-time, frame-level extraction. Experimental results demonstrate that the proposed model enhances short-time objective intelligibility (STOI) and signal-to-distortion ratio (SDR), offering a promising solution for target speech extraction in challenging scenarios.

PoseTalk: Text-and-Audio-based Pose Control and Motion Refinement for One-Shot Talking Head Generation

While previous audio-driven talking head generation (THG) methods generate head poses from driving audio, the generated poses or lips cannot match the audio well or are not editable. In this study, we propose \textbf{PoseTalk}, a THG system that can freely generate lip-synchronized talking head videos with free head poses conditioned on text prompts and audio. The core insight of our method is using head pose to connect visual, linguistic, and audio signals. First, we propose to generate poses from both audio and text prompts, where the audio offers short-term variations and rhythm correspondence of the head movements and the text prompts describe the long-term semantics of head motions. To achieve this goal, we devise a Pose Latent Diffusion (PLD) model to generate motion latent from text prompts and audio cues in a pose latent space. Second, we observe a loss-imbalance problem: the loss for the lip region contributes less than 4\% of the total reconstruction loss caused by both pose and lip, making optimization lean towards head movements rather than lip shapes. To address this issue, we propose a refinement-based learning strategy to synthesize natural talking videos using two cascaded networks, i.e., CoarseNet, and RefineNet. The CoarseNet estimates coarse motions to produce animated images in novel poses and the RefineNet focuses on learning finer lip motions by progressively estimating lip motions from low-to-high resolutions, yielding improved lip-synchronization performance. Experiments demonstrate our pose prediction strategy achieves better pose diversity and realness compared to text-only or audio-only, and our video generator model outperforms state-of-the-art methods in synthesizing talking videos with natural head motions. Project: https://junleen.github.io/projects/posetalk.

OpenResearcher: Unleashing AI for Accelerated Scientific Research

The rapid growth of scientific literature imposes significant challenges for researchers endeavoring to stay updated with the latest advancements in their fields and delve into new areas. We introduce OpenResearcher, an innovative platform that leverages Artificial Intelligence (AI) techniques to accelerate the research process by answering diverse questions from researchers. OpenResearcher is built based on Retrieval-Augmented Generation (RAG) to integrate Large Language Models (LLMs) with up-to-date, domain-specific knowledge. Moreover, we develop various tools for OpenResearcher to understand researchers' queries, search from the scientific literature, filter retrieved information, provide accurate and comprehensive answers, and self-refine these answers. OpenResearcher can flexibly use these tools to balance efficiency and effectiveness. As a result, OpenResearcher enables researchers to save time and increase their potential to discover new insights and drive scientific breakthroughs. Demo, video, and code are available at: https://github.com/GAIR-NLP/OpenResearcher.

RS-BNN: A Deep Learning Framework for the Optimal Beamforming Design of Rate-Splitting Multiple Access

Rate splitting multiple access (RSMA) relies on beamforming design for attaining spectral efficiency and energy efficiency gains over traditional multiple access schemes. While conventional optimization approaches such as weighted minimum mean square error (WMMSE) achieve suboptimal solutions for RSMA beamforming optimization, they are computationally demanding. A novel approach based on fractional programming (FP) has unveiled the optimal beamforming structure (OBS) for RSMA. This method, combined with a hyperplane fixed point iteration (HFPI) approach, named FP-HFPI, provides suboptimal beamforming solutions with identical sum rate performance but much lower computational complexity compared to WMMSE. Inspired by such an approach, in this work, a novel deep unfolding framework based on FP-HFPI, named rate-splitting-beamforming neural network (RS-BNN), is proposed to unfold the FP-HFPI algorithm. Numerical results indicate that the proposed RS-BNN attains a level of performance closely matching that of WMMSE and FP-HFPI, while dramatically reducing the computational complexity.

TSE-PI: Target Sound Extraction under Reverberant Environments with Pitch Information

Target sound extraction (TSE) separates the target sound from the mixture signals based on provided clues. However, the performance of existing models significantly degrades under reverberant conditions. Inspired by auditory scene analysis (ASA), this work proposes a TSE model provided with pitch information named TSE-PI. Conditional pitch extraction is achieved through the Feature-wise Linearly Modulated layer with the sound-class label. A modified Waveformer model combined with pitch information, employing a learnable Gammatone filterbank in place of the convolutional encoder, is used for target sound extraction. The inclusion of pitch information is aimed at improving the model's performance. The experimental results on the FSD50K dataset illustrate 2.4 dB improvements of target sound extraction under reverberant environments when incorporating pitch information and Gammatone filterbank.

Beware of Overestimated Decoding Performance Arising from Temporal Autocorrelations in Electroencephalogram Signals

Researchers have reported high decoding accuracy (>95%) using non-invasive Electroencephalogram (EEG) signals for brain-computer interface (BCI) decoding tasks like image decoding, emotion recognition, auditory spatial attention detection, etc. Since these EEG data were usually collected with well-designed paradigms in labs, the reliability and robustness of the corresponding decoding methods were doubted by some researchers, and they argued that such decoding accuracy was overestimated due to the inherent temporal autocorrelation of EEG signals. However, the coupling between the stimulus-driven neural responses and the EEG temporal autocorrelations makes it difficult to confirm whether this overestimation exists in truth. Furthermore, the underlying pitfalls behind overestimated decoding accuracy have not been fully explained due to a lack of appropriate formulation. In this work, we formulate the pitfall in various EEG decoding tasks in a unified framework. EEG data were recorded from watermelons to remove stimulus-driven neural responses. Labels were assigned to continuous EEG according to the experimental design for EEG recording of several typical datasets, and then the decoding methods were conducted. The results showed the label can be successfully decoded as long as continuous EEG data with the same label were split into training and test sets. Further analysis indicated that high accuracy of various BCI decoding tasks could be achieved by associating labels with EEG intrinsic temporal autocorrelation features. These results underscore the importance of choosing the right experimental designs and data splits in BCI decoding tasks to prevent inflated accuracies due to EEG temporal autocorrelation.

Multimodal Semantic-Aware Automatic Colorization with Diffusion Prior

Colorizing grayscale images offers an engaging visual experience. Existing automatic colorization methods often fail to generate satisfactory results due to incorrect semantic colors and unsaturated colors. In this work, we propose an automatic colorization pipeline to overcome these challenges. We leverage the extraordinary generative ability of the diffusion prior to synthesize color with plausible semantics. To overcome the artifacts introduced by the diffusion prior, we apply the luminance conditional guidance. Moreover, we adopt multimodal high-level semantic priors to help the model understand the image content and deliver saturated colors. Besides, a luminance-aware decoder is designed to restore details and enhance overall visual quality. The proposed pipeline synthesizes saturated colors while maintaining plausible semantics. Experiments indicate that our proposed method considers both diversity and fidelity, surpassing previous methods in terms of perceptual realism and gain most human preference.

Learn to Sing by Listening: Building Controllable Virtual Singer by Unsupervised Learning from Voice Recordings

The virtual world is being established in which digital humans are created indistinguishable from real humans. Producing their audio-related capabilities is crucial since voice conveys extensive personal characteristics. We aim to create a controllable audio-form virtual singer; however, supervised modeling and controlling all different factors of the singing voice, such as timbre, tempo, pitch, and lyrics, is extremely difficult since accurately labeling all such information needs enormous labor work. In this paper, we propose a framework that could digitize a person's voice by simply "listening" to the clean voice recordings of any content in a fully unsupervised manner and predict singing voices even only using speaking recordings. A variational auto-encoder (VAE) based framework is developed, which leverages a set of pre-trained models to encode the audio as various hidden embeddings representing different factors of the singing voice, and further decodes the embeddings into raw audio. By manipulating the hidden embeddings for different factors, the resulting singing voices can be controlled, and new virtual singers can also be further generated by interpolating between timbres. Evaluations of different types of experiments demonstrate the proposed method's effectiveness. The proposed method is the critical technique for producing the AI choir, which empowered the human-AI symbiotic orchestra in Hong Kong in July 2022.