arXiv subjects

Kun Wei

Publications and source records attributed to Kun Wei.

At least 19 recordsLinked to original sources

arXiv2026

Multiple Hypothesis Flow Estimation for Video Frame Interpolation under Matching Ambiguity

Many flow-based video frame interpolation (VFI) methods synthesize an intermediate frame by estimating optical flow fields, warping the two input frames, and blending the warped observations. These latent flow fields are typically learned through image-level reconstruction supervision without direct flow annotations. In ambiguous regions containing repetitive or stochastic textures, rotating symmetric structures, or fast motion with blur, the matching evidence for a single query may contain multiple comparable and spatially separated peaks. Although the ground-truth intermediate frame provides indirect supervision, it may not uniquely identify the latent correspondence in ambiguous regions.When several locations provide multiple plausible matches, a single-flow estimator can retain only one displacement and discard the remaining candidates. If the selected match is incorrect or inconsistent with those of neighboring pixels, warping samples content from mismatched locations, producing ghosting, structural distortion, or blur.To address this limitation, we propose a multiple hypothesis flow estimation framework that preserves top-K candidate correspondences and selects one per location through a reliability-guided router. Each hypothesis is initialized from a coarse matching anchor and refined separately through anchor-centered local attention. Frame synthesis is thus conditioned on one selected flow-appearance hypothesis rather than a soft combination of candidate motions.Experiments on the proposed MA-HD benchmark and public VFI benchmarks show that our method achieves the best LPIPS and DISTS among the compared methods.

cs.CV↗

arXiv2026

DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language Models

Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi-domain task-incremental learning, large domain shifts intensify the stability-plasticity dilemma. Most existing methods rely on fixed architectures with statically allocated parameters, which limits adaptation to new domains and aggravates catastrophic forgetting. To address these challenges, we propose DIMoE-Adapters, a Dynamic Incremental Mixture-of-Experts Adapters framework that introduces a dynamic expert evolution paradigm to balance stability and plasticity. This paradigm is implemented through two collaborative components: Self-Calibrated Expert Evolution (SCEE) and Prototype-Guided Expert Selection (PGES). SCEE constructs and evolves a sparse expert pool through expert optimization dynamics, improving plasticity while reducing redundant capacity. PGES controls expert utilization based on the pool shaped by SCEE, improving stability across both previously encountered and unseen tasks. Extensive experiments show that DIMoE-Adapters outperforms previous state-of-the-art methods across various settings.

cs.CV↗

arXiv2026

Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models

Class-incremental learning aims to continuously acquire new knowledge while preserving previously learned information, thereby mitigating catastrophic forgetting. Existing methods primarily restrict parameter updates but often overlook their structural properties in high-dimensional spaces. From a subspace perspective, updates induced by different tasks tend to lie in multiple overlapping low-rank subspaces, leading to cross-task subspace interference and severe forgetting. To address this issue, we propose HDSD, a Hierarchical Dual-Subspace Decoupling framework for continual learning in vision-language models. Specifically, we introduce a lightweight Feature Modulation Module (FMM) that explicitly decomposes the parameter space into general and task-specific subspaces. Building on this design, we develop two complementary components. First, a General Fusion Module (GFM) evaluates relative parameter changes across tasks and uses an adaptive threshold to capture stable and transferable knowledge. Second, a Hierarchical Learning Module (HLM) performs structured parameter decomposition via Singular Value Decomposition (SVD) and uses a scaling mechanism to constrain updates within distinct subspace scales. Together, these designs reduce subspace interference and parameter drift. Extensive experiments on conventional benchmarks show that HDSD achieves state-of-the-art results.

cs.CV↗

arXiv2026

SPG-Codec: Exploring the Role and Boundaries of Semantic Priors in Ultra-Low-Bitrate Neural Speech Coding

Conventional neural speech codecs suffer from severe intelligibility degradation at ultra-low bitrates, where the bottleneck transitions from acoustic distortion to semantic loss. To address this issue, this paper conducts a systematic investigation into the role and fundamental limits of integrating frozen semantic priors -- specifically HuBERT and Whisper -- into neural speech coding. We introduce and quantitatively validate a novel Semantic Retirement phenomenon: while semantic constraints reduce the Word Error Rate (WER) by up to ~10% relatively at 1.5 kbps, their benefits rapidly diminish beyond 6 kbps, indicating a practical capacity boundary. We further uncover a clear trade-off between different prior types: acoustic-rich priors (HuBERT) better preserve prosodic and timbral details, whereas high-level linguistic priors (Whisper) effectively suppress phonetic hallucinations in noisy environments (reducing hallucination rates by 26 percent) and substantially narrow the generalization gap for unseen speakers. Building on these findings, we propose a bitrate-aware regulation strategy that dynamically adjusts prior strength to optimize the trade-off between semantic consistency and perceptual naturalness. Extensive experimental evaluations confirm that our approach achieves competitive intelligibility and noise robustness compared to existing baselines, offering a principled pathway toward ultra-low-bitrate generative speech coding.

eess.AS↗

arXiv2026

Physics-Informed Neural Network with Adaptive Clustering Learning Mechanism for Information Popularity Prediction

With society entering the Internet era, the volume and speed of data and information have been increasing. Predicting the popularity of information cascades can help with high-value information delivery and public opinion monitoring on the internet platforms. The current state-of-the-art models for predicting information popularity utilize deep learning methods such as graph convolution networks (GCNs) and recurrent neural networks (RNNs) to capture early cascades and temporal features to predict their popularity increments. However, these previous methods mainly focus on the micro features of information cascades, neglecting their general macroscopic patterns. Furthermore, they also lack consideration of the impact of information heterogeneity on spread popularity. To overcome these limitations, we propose a physics-informed neural network with adaptive clustering learning mechanism, PIACN, for predicting the popularity of information cascades. Our proposed model not only models the macroscopic patterns of information dissemination through physics-informed approach for the first time but also considers the influence of information heterogeneity through an adaptive clustering learning mechanism. Extensive experimental results on three real-world datasets demonstrate that our model significantly outperforms other state-of-the-art methods in predicting information popularity.

cs.SI↗

arXiv2026

Covo-Audio Technical Report

In this work, we present Covo-Audio, a 7B-parameter end-to-end LALM that directly processes continuous audio inputs and generates audio outputs within a single unified architecture. Through large-scale curated pretraining and targeted post-training, Covo-Audio achieves state-of-the-art or competitive performance among models of comparable scale across a broad spectrum of tasks, including speech-text modeling, spoken dialogue, speech understanding, audio understanding, and full-duplex voice interaction. Extensive evaluations demonstrate that the pretrained foundation model exhibits strong speech-text comprehension and semantic reasoning capabilities on multiple benchmarks, outperforming representative open-source models of comparable scale. Furthermore, Covo-Audio-Chat, the dialogue-oriented variant, demonstrates strong spoken conversational abilities, including understanding, contextual reasoning, instruction following, and generating contextually appropriate and empathetic responses, validating its applicability to real-world conversational assistant scenarios. Covo-Audio-Chat-FD, the evolved full-duplex model, achieves substantially superior performance on both spoken dialogue capabilities and full-duplex interaction behaviors, demonstrating its competence in practical robustness. To mitigate the high cost of deploying end-to-end LALMs for natural conversational systems, we propose an intelligence-speaker decoupling strategy that separates dialogue intelligence from voice rendering, enabling flexible voice customization with minimal text-to-speech (TTS) data while preserving dialogue performance. Overall, our results highlight the strong potential of 7B-scale models to integrate sophisticated audio intelligence with high-level semantic reasoning, and suggest a scalable path toward more capable and versatile LALMs.

cs.SD↗

arXiv2026

DSCD-Nav: Dual-Stance Cooperative Debate for Object Navigation

Adaptive navigation in unfamiliar indoor environments is crucial for household service robots. Despite advances in zero-shot perception and reasoning from vision-language models, existing navigation systems still rely on single-pass scoring at the decision layer, leading to overconfident long-horizon errors and redundant exploration. To tackle these problems, we propose Dual-Stance Cooperative Debate Navigation (DSCD-Nav), a decision mechanism that replaces one-shot scoring with stance-based cross-checking and evidence-aware arbitration to improve action reliability under partial observability. Specifically, given the same observation and candidate action set, we explicitly construct two stances by conditioning the evaluation on diverse and complementary objectives: a Task-Scene Understanding (TSU) stance that prioritizes goal progress from scene-layout cues, and a Safety-Information Balancing (SIB) stance that emphasizes risk and information value. The stances conduct a cooperative debate and make policy by cross-checking their top candidates with cue-grounded arguments. Then, a Navigation Consensus Arbitration (NCA) agent is employed to consolidate both sides' reasons and evidence, optionally triggering lightweight micro-probing to verify uncertain choices, preserving NCA's primary intent while disambiguating. Experiments on HM3Dv1, HM3Dv2, and MP3D demonstrate consistent improvements in success and path efficiency while reducing exploration redundancy.

cs.RO↗

arXiv2025

AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning

Extending large language models (LLMs) to the speech domain has recently gained significant attention. A typical approach connects a pretrained LLM with an audio encoder through a projection module and trains the resulting model on large-scale, task-specific instruction-tuning datasets. However, curating such instruction-tuning data for specific requirements is time-consuming, and models trained in this manner often generalize poorly to unseen tasks. In this work, we first formulate that the strongest generalization of a speech-LLM is achieved when it is trained with Self-Generated Instruction-Free Tuning (SIFT), in which supervision signals are generated by a frozen LLM using textual representations of speech as input. Our proposed SIFT paradigm eliminates the need for collecting task-specific question-answer pairs and yields the theoretically best generalization to unseen tasks. Building upon this paradigm, we introduce AZeroS (Auden Zero-instruction-tuned Speech-LLM), which is trained on speech-text pairs derived from publicly available corpora, including approximately 25,000 hours of speech with ASR transcripts and 3,000 hours of speech with paralinguistic labels. Built upon Qwen2.5-7B-Instruct, the model updates only two lightweight projection modules (23.8 million parameters each), while keeping both the LLM and audio encoders frozen. Despite the minimal training cost and modest data scale, AZeroS achieves state-of-the-art performance on both semantic and paralinguistic benchmarks, including VoiceBench, AIR-Bench Foundation (Speech), and AIR-Bench Chat (Speech).

cs.CL↗

arXiv2025

LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering

3D Gaussian Splatting SLAM has emerged as a widely used technique for high-fidelity mapping in spatial intelligence. However, existing methods often rely on a single representation scheme, which limits their performance in large-scale dynamic outdoor scenes and leads to cumulative pose errors and scale ambiguity. To address these challenges, we propose \textbf{LVD-GS}, a novel LiDAR-Visual 3D Gaussian Splatting SLAM system. Motivated by the human chain-of-thought process for information seeking, we introduce a hierarchical collaborative representation module that facilitates mutual reinforcement for mapping optimization, effectively mitigating scale drift and enhancing reconstruction robustness. Furthermore, to effectively eliminate the influence of dynamic objects, we propose a joint dynamic modeling module that generates fine-grained dynamic masks by fusing open-world segmentation with implicit residual constraints, guided by uncertainty estimates from DINO-Depth features. Extensive evaluations on KITTI, nuScenes, and self-collected datasets demonstrate that our approach achieves state-of-the-art performance compared to existing methods.

cs.CV↗

arXiv2025

A Bridge from Audio to Video: Phoneme-Viseme Alignment Allows Every Face to Speak Multiple Languages

Speech-driven talking face synthesis (TFS) focuses on generating lifelike facial animations from speech input. Current TFS models perform well in English but struggle with non-English languages, producing inaccurate mouth shapes and rigid facial expressions. These limitations are mainly caused by English-dominated training datasets and the lack of cross-language generalization ability.To address these challenges, we propose Multilingual Experts (MuEx), a novel framework featuring a Phoneme-Guided Mixture-of-Experts (PG-MoE) architecture that employs phonemes and visemes as universal intermediaries to bridge the gap between audio and visual modalities, enabling lifelike multilingual TFS. We extract speech and visual features as phonemes and visemes, respectively, which represent the basic units of speech sounds and mouth movements, to alleviate linguistic differences and dataset bias.Furthermore, we introduce the Phoneme-Viseme Alignment Mechanism (PV-Align), which establishes robust cross-modal correspondences between phonemes and visemes to improve audiovisual synchronization. In addition, we construct a Multilingual Talking Face Dataset (MTFD) comprising 12 diverse languages with 95.04 hours of high-quality videos for training and evaluating multilingual TFS performance.Extensive experiments demonstrate that MuEx achieves superior performance across all languages in MTFD and exhibits effective zero-shot generalization to unseen languages without additional training.

cs.CV↗

arXiv2025

Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space

As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention. Machine unlearning is introduced to seek to mitigate these risks by removing the influence of undesirable data. However, existing methods not only rely on the retained dataset to preserve model utility, but also suffer from cumulative catastrophic utility loss under continuous unlearning requests. To solve this dilemma, we propose a novel method, called Rotation Control Unlearning (RCU), which leverages the rotational salience weight of RCU to quantify and control the unlearning degree in the continuous unlearning process. The skew symmetric loss is designed to construct the existence of the cognitive rotation space, where the changes of rotational angle can simulate the continuous unlearning process. Furthermore, we design an orthogonal rotation axes regularization to enforce mutually perpendicular rotation directions for continuous unlearning requests, effectively minimizing interference and addressing cumulative catastrophic utility loss. Experiments on multiple datasets confirm that our method without retained dataset achieves SOTA performance.

cs.LG↗

arXiv2025

Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive Agents

Long videos, characterized by temporal complexity and sparse task-relevant information, pose significant reasoning challenges for AI systems. Although existing Large Language Model (LLM)-based approaches have advanced long video understanding, they remain bottlenecked by task-agnostic, fixed-granularity perception pipelines and suffer from vision-language hallucinations. Inspired by human adaptive perception and active verification, we propose CogniGPT, a framework leveraging an interactive loop between a Multi-Granular Perception Agent (MPA) and an Active Verification Agent (AVA). Specifically, instead of predetermined heuristics, MPA adaptively determines the optimal perception granularity and strategy based on the evolving context, while AVA actively mines multi-perspective visual evidence to cross-verify key observations and eliminate hallucinations. This interaction allows CogniGPT to efficiently identify a minimal set of reliable task-related clues. Extensive experiments on EgoSchema, Video-MME, NExT-QA, and MovieChat demonstrate its superiority in accuracy and efficiency. Notably, on EgoSchema, it surpasses existing training-free methods using only 11.2 frames and achieves performance comparable to Gemini 1.5-Pro.

cs.CV↗

arXiv2025

DAIEN-TTS: Disentangled Audio Infilling for Environment-Aware Text-to-Speech Synthesis

This paper presents DAIEN-TTS, a zero-shot text-to-speech (TTS) framework that enables ENvironment-aware synthesis through Disentangled Audio Infilling. By leveraging separate speaker and environment prompts, DAIEN-TTS allows independent control over the timbre and the background environment of the synthesized speech. Built upon F5-TTS, the proposed DAIEN-TTS first incorporates a pretrained speech-environment separation (SES) module to disentangle the environmental speech into mel-spectrograms of clean speech and environment audio. Two random span masks of varying lengths are then applied to both mel-spectrograms, which, together with the text embedding, serve as conditions for infilling the masked environmental mel-spectrogram, enabling the simultaneous continuation of personalized speech and time-varying environmental audio. To further enhance controllability during inference, we adopt dual classifier-free guidance (DCFG) for the speech and environment components and introduce a signal-to-noise ratio (SNR) adaptation strategy to align the synthesized speech with the environment prompt. Experimental results demonstrate that DAIEN-TTS generates environmental personalized speech with high naturalness, strong speaker similarity, and high environmental fidelity.

eess.AS↗

arXiv2025

Efficient Scaling for LLM-based ASR

Large language model (LLM)-based automatic speech recognition (ASR) achieves strong performance but often incurs high computational costs. This work investigates how to obtain the best LLM-ASR performance efficiently. Through comprehensive and controlled experiments, we find that pretraining the speech encoder before integrating it with the LLM leads to significantly better scaling efficiency than the standard practice of joint post-training of LLM-ASR. Based on this insight, we propose a new multi-stage LLM-ASR training strategy, EFIN: Encoder First Integration. Among all training strategies evaluated, EFIN consistently delivers better performance (relative to 21.1% CERR) with significantly lower computation budgets (49.9% FLOPs). Furthermore, we derive a scaling law that approximates ASR error rates as a computation function, providing practical guidance for LLM-ASR scaling.

cs.SD↗

arXiv2025

Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR

Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models' (LLMs) exceptional long-context understanding and reasoning abilities enable LLM-based ASR (LLM-ASR) to leverage historical context for recognizing conversational speech, which has a high degree of contextual relevance. However, existing conversational LLM-ASR methods use a fixed number of preceding utterances or the entire conversation history as context, resulting in significant ASR confusion and computational costs due to massive irrelevant and redundant information. This paper proposes a multi-modal retrieval-and-selection method named MARS that augments conversational LLM-ASR by enabling it to retrieve and select the most relevant acoustic and textual historical context for the current utterance. Specifically, multi-modal retrieval obtains a set of candidate historical contexts, each exhibiting high acoustic or textual similarity to the current utterance. Multi-modal selection calculates the acoustic and textual similarities for each retrieved candidate historical context and, by employing our proposed near-ideal ranking method to consider both similarities, selects the best historical context. Evaluations on the Interspeech 2025 Multilingual Conversational Speech Language Model Challenge dataset show that the LLM-ASR, when trained on only 1.5K hours of data and equipped with the MARS, outperforms the state-of-the-art top-ranking system trained on 179K hours of data.

cs.SD↗

arXiv2025

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition

Despite improvements in automatic speech recognition, performance drops with accented speech. Generative error correction (GER) leverages the linguistic knowledge of large language models (LLMs), outperforming typical language model methods. However, it lacks specificity in accented speech scenarios. Accents represent deviations from standard pronunciation, making multi-granularity pronunciation and semantic information essential for accented speech recognition. Moreover, accents exhibit considerable diversity, with each accent possessing distinct characteristics. In this study, we leverage GER to improve transcription accuracy by addressing the two primary features. We propose the multi-modal GER, which integrates pronunciation information from the speech modality, and the multi-granularity GER, which incorporates fine-grained phoneme-level pronunciation information. These methods enable the LLM to utilize the pronunciation information of accented speech and the semantic information from word-level hypotheses for accurate transcription predictions through low-rank adaptation (LoRA) fine-tuning. We employ a three-stage strategy to train separate multi-modal GER models for each accent to obtain mono-accent LoRA experts. By adopting our proposed HDMoLE method, which incorporates hierarchical routing and dynamic thresholds within the mixture of LoRA experts, we effectively merge mono-accent LoRA experts within a single multi-modal GER to overcome accent diversity challenges. Furthermore, multi-granularity GER leverages N-best word-level and phoneme-level hypotheses from the HDMoLE model to predict final transcriptions. Experiments on a multi-accent English dataset show that our methods reduce word error rate by 67.35% compared to the baseline vanilla Whisper-large-v3 model.

cs.SD↗

arXiv2025

Will the Technological Singularity Come Soon? Modeling the Dynamics of Artificial Intelligence Development via Multi-Logistic Growth Process

We are currently in an era of escalating technological complexity and profound societal transformations, where artificial intelligence (AI) technologies exemplified by large language models (LLMs) have reignited discussions on the 'Technological Singularity'. 'Technological Singularity' is a philosophical concept referring to an irreversible and profound transformation that occurs when AI capabilities surpass those of humans comprehensively. However, quantitative modeling and analysis of the historical evolution and future trends of AI technologies remain scarce, failing to substantiate the singularity hypothesis adequately. This paper hypothesizes that the development of AI technologies could be characterized by the superposition of multiple logistic growth processes. To explore this hypothesis, we propose a multi-logistic growth process model and validate it using two real-world datasets: AI Historical Statistics and Arxiv AI Papers. Our analysis of the AI Historical Statistics dataset assesses the effectiveness of the multi-logistic model and evaluates the current and future trends in AI technology development. Additionally, cross-validation experiments on the Arxiv AI Paper, GPU Transistor and Internet User dataset enhance the robustness of our conclusions derived from the AI Historical Statistics dataset. The experimental results reveal that around 2024 marks the fastest point of the current AI wave, and the deep learning-based AI technologies are projected to decline around 2035-2040 if no fundamental technological innovation emerges. Consequently, the technological singularity appears unlikely to arrive in the foreseeable future.

physics.soc-ph↗

arXiv2025

OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia

Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of Speech Understanding Language Models (SULMs) to enable comprehensive speech-based interactions. However, most advanced SULMs are developed by the industry, leveraging large-scale datasets and computational resources that are not readily available to the academic community. Moreover, the lack of transparency in training details creates additional barriers to further innovation. In this study, we present OSUM, an Open Speech Understanding Model designed to explore the potential of training SLUMs under constrained academic resources. The OSUM model combines a Whisper encoder with a Qwen2 LLM and supports a wide range of speech tasks, including speech recognition (ASR), speech recognition with timestamps (SRWT), vocal event detection (VED), speech emotion recognition (SER), speaking style recognition (SSR), speaker gender classification (SGC), speaker age prediction (SAP), and speech-to-text chat (STTC). By employing an ASR+X training strategy, OSUM achieves efficient and stable multi-task training by simultaneously optimizing ASR alongside target tasks. Beyond delivering strong performance, OSUM emphasizes transparency by providing openly available data preparation and training methodologies, offering valuable insights and practical guidance for the academic community. By doing so, we aim to accelerate research and innovation in advanced SULM technologies.

cs.SD↗