Automating design-to-code translation remains a longstanding goal in software engineering. While Multimodal Large Language Models (MLLMs) have shown promise in design-to-code tasks, existing benchmarks rely solely on screenshots, discarding the structured metadata indispensable in real-world design handoff workflows. Furthermore, current evaluation paradigms are deficient, as code-level metrics fail to account for implementation variability and visual metrics overlook fine-grained defects, while standardized assessments for responsive behaviors remain absent. To address these limitations, we introduce FigmaBench, an industrial-grade benchmark for multimodal design-to-code generation. We collect raw design files from the Figma Community and apply a multi-stage pipeline to curate 1,234 high-quality samples, each comprising high-resolution screenshots and complete JSON metadata. We further propose a comprehensive evaluation framework with four complementary metrics: visual consistency (VCS), structural layout alignment (SLA), textual and stylistic fidelity (TSF), and responsive quality score (RQS). Through extensive evaluation of state-of-the-art MLLMs, we uncover a critical fidelity-responsiveness paradox: models achieving high visual fidelity tend to generate rigid, non-responsive code. We trace this phenomenon to a metadata trap, where models shortcut layout reasoning by directly transcribing absolute coordinates rather than generating fluid structures. Our data and code are available at https://anonymous.4open.science/r/FigmaBench-6C84/.

Speculative decoding (SD) has emerged as a promising approach to accelerate LLM inference without sacrificing output quality. Existing SD methods tailored for video-LLMs primarily focus on pruning redundant visual tokens to mitigate the computational burden of massive visual inputs. However, existing methods do not achieve inference acceleration comparable to text-only LLMs. We observe from extensive experiments that this phenomenon mainly stems from two limitations: (i) their pruning strategies inadequately preserve visual semantic tokens, degrading draft quality and acceptance rates; (ii) even with aggressive pruning (e.g., 90% visual tokens removed), the draft model’s remaining inference cost limits overall speedup. To address these limitations, we propose HIPPO, a general holistic-aware parallel speculative decoding framework. Specifically, HIPPO proposes: (i) a semantic-aware token preservation method, which fuses global attention scores with local visual semantics to retain semantic information at high pruning ratios; (ii) a video parallel SD algorithm that decouples and overlaps draft generation and target verification phases. Experiments on four video-LLMs across six benchmarks demonstrate HIPPO’s effectiveness, yielding up to 3.51× speedup compared to vanilla auto-regressive decoding.

Audio often serves as an auxiliary modality in video understanding tasks of audio-visual large language models (LLMs), merely assisting in the comprehension of visual information. However, a thorough understanding of videos significantly depends on auditory information, as audio offers critical context, emotional cues, and semantic meaning that visual data alone often lacks. This paper proposes an audio-centric video understanding benchmark (AVUT) to evaluate the video comprehension capabilities of multimodal LLMs with a particular focus on auditory information. AVUT introduces a suite of carefully designed audio-centric tasks, holistically testing the understanding of both audio content and audio-visual interactions in videos. Moreover, this work points out the text shortcut problem that largely exists in other benchmarks where the correct answer can be found from question text alone without needing videos. AVUT addresses this problem by proposing a answer permutation-based filtering mechanism.A thorough evaluation across a diverse range of open-source and proprietary multimodal LLMs is performed, followed by the analyses of deficiencies in audio-visual LLMs. Demos and data are available at https://github.com/lark-png/AVUT.

This paper introduces DNCASR, a novel end-to-end trainable system designed for joint neural speaker clustering and automatic speech recognition (ASR), enabling speaker-attributed transcription of long multi-party meetings. DNCASR uses two separate encoders to independently encode global speaker characteristics and local waveform information, along with two linked decoders to generate speaker-attributed transcriptions. The use of linked decoders allows the entire system to be jointly trained under a unified loss function. By employing a serialised training approach, DNCASR effectively addresses overlapping speech in real-world meetings, where the link improves the prediction of speaker indices in overlapping segments. Experiments on the AMI-MDM meeting corpus demonstrate that the jointly trained DNCASR outperforms a parallel system that does not have links between the speaker and ASR decoders. Using cpWER to measure the speaker-attributed word error rate, DNCASR achieves a 9.0% relative reduction on the AMI-MDM Eval set.

This paper explores a novel perspective to speech quality assessment by leveraging natural language descriptions, offering richer, more nuanced insights than traditional numerical scoring methods. Natural language feedback provides instructive recommendations and detailed evaluations, yet existing datasets lack the comprehensive annotations needed for this approach. To bridge this gap, we introduce QualiSpeech, a comprehensive low-level speech quality assessment dataset encompassing 11 key aspects and detailed natural language comments that include reasoning and contextual insights. Additionally, we propose the QualiSpeech Benchmark to evaluate the low-level speech understanding capabilities of auditory large language models (LLMs). Experimental results demonstrate that finetuned auditory LLMs can reliably generate detailed descriptions of noise and distortion, effectively identifying their types and temporal characteristics. The results further highlight the potential for incorporating reasoning to enhance the accuracy and reliability of quality assessments. The dataset can be found at https://huggingface.co/datasets/tsinghua-ee/QualiSpeech.

Affect recognition, encompassing emotions, moods, and feelings, plays a pivotal role in human communication. In the realm of conversational artificial intelligence, the ability to discern and respond to human affective cues is a critical factor for creating engaging and empathetic interactions. This study investigates the capacity of large language models (LLMs) to recognise human affect in conversations, with a focus on both open-domain chit-chat dialogues and task-oriented dialogues. Leveraging three diverse datasets, namely IEMOCAP (Busso et al., 2008), EmoWOZ (Feng et al., 2022), and DAIC-WOZ (Gratch et al., 2014), covering a spectrum of dialogues from casual conversations to clinical interviews, we evaluate and compare LLMs’ performance in affect recognition. Our investigation explores the zero-shot and few-shot capabilities of LLMs through in-context learning as well as their model capacities through task-specific fine-tuning. Additionally, this study takes into account the potential impact of automatic speech recognition errors on LLM predictions. With this work, we aim to shed light on the extent to which LLMs can replicate human-like affect recognition capabilities in conversations.

Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation tasks such as data annotation and system assessment. It is important to incorporate the variability present in human evaluation into HAS, since it helps capture diverse subjective interpretations and mitigate potential biases and over-representation. This work introduces a novel framework for modelling variability in HAS. Conditional softmax flow (S-CNF) is proposed to model the distribution of subjective human annotations, which leverages diverse human annotations via meta-learning. This enables efficient generation of annotations that exhibit human variability for unlabelled input. In addition, a wide range of evaluation metrics are adopted to assess the capability and efficiency of HAS systems in predicting the aggregated behaviours of human annotators, matching the distribution of human annotations, and simulating the inter-annotator disagreements. Results demonstrate that the proposed method achieves state-of-the-art performance on two real-world human evaluation tasks: emotion recognition and toxic speech detection.

Recently, advancements in large language models (LLMs) have shown an unprecedented ability across various language tasks. This paper investigates the potential application of LLMs to slot filling with noisy ASR transcriptions, via both in-context learning and task-specific fine-tuning. Dedicated prompt designs and noise-robust LoRA fine-tuning are proposed to improve the robustness of LLMs for slot filling with noisy ASR transcriptions. Moreover, a linearised knowledge injection (LKI) scheme is also proposed to integrate dynamic external knowledge into LLMs. Experiments were performed on SLURP to quantify the performance of LLMs, including GPT-3.5-turbo, GPT-4, LLaMA-13B, LLaMA-2-13B and Vicuna-13B (v1.1 and v1.5) with different ASR error rates. The use of the noise-robust fine-tuning together with LKI for Vicuna-13B-v1.5 achieved 6.7% and 17.6% absolute SLU-F1 improvements compared to a fully fine-tuned Flan-T5-XL model on the limited data setup and the zero-shot setup respectively.

Large language models (LLMs) can adapt to new tasks through in-context learning (ICL) based on a few examples presented in dialogue history without any model parameter update. Despite such convenience, the performance of ICL heavily depends on the quality of the in-context examples presented, which makes the in-context example selection approach a critical choice. This paper proposes a novel eBayesian in-Context example Selection method (ByCS) for ICL. Extending the inference probability conditioned on in-context examples based on Bayes’ theorem, ByCS focuses on the inverse inference conditioned on test input. Following the assumption that accurate inverse inference probability (likelihood) will result in accurate inference probability (posterior), in-context examples are selected based on their inverse inference results. Diverse and extensive cross-tasking and cross-modality experiments are performed with speech, text, and image examples. Experimental results show the efficacy and robustness of our ByCS method on various models, tasks and modalities.

Publishing open-source academic video recordings is an emergent and prevalent approach to sharing knowledge online. Such videos carry rich multimodal information including speech, the facial and body movements of the speakers, as well as the texts and pictures in the slides and possibly even the papers. Although multiple academic video datasets have been constructed and released, few of them support both multimodal content recognition and understanding tasks, which is partially due to the lack of high-quality human annotations. In this paper, we propose a novel multimodal, multigenre, and multipurpose audio-visual academic lecture dataset (M³AV), which has almost 367 hours of videos from five sources covering computer science, mathematics, and medical and biology topics. With high-quality human annotations of the slide text and spoken words, in particular high-valued name entities, the dataset can be used for multiple audio-visual recognition and understanding tasks. Evaluations performed on contextual speech recognition, speech synthesis, and slide and script generation tasks demonstrate that the diversity of M³AV makes it a challenging dataset.

The subjective perception of emotion leads to inconsistent labels from human annotators. Typically, utterances lacking majority-agreed labels are excluded when training an emotion classifier, which cause problems when encountering ambiguous emotional expressions during testing. This paper investigates three methods to handle ambiguous emotion. First, we show that incorporating utterances without majority-agreed labels as an additional class in the classifier reduces the classification performance of the other emotion classes. Then, we propose detecting utterances with ambiguous emotions as out-of-domain samples by quantifying the uncertainty in emotion classification using evidential deep learning. This approach retains the classification accuracy while effectively detects ambiguous emotion expressions. Furthermore, to obtain fine-grained distinctions among ambiguous emotions, we propose representing emotion as a distribution instead of a single class label. The task is thus re-framed from classification to distribution estimation where every individual annotation is taken into account, not just the majority opinion. The evidential uncertainty measure is extended to quantify the uncertainty in emotion distribution estimation. Experimental results on the IEMOCAP and CREMA-D datasets demonstrate the superior capability of the proposed method in terms of majority class prediction, emotion distribution estimation, and uncertainty estimation.

“Speech and language computational models have been instrumental in advancing Artificial In-telligence in recent years. However, it remains an open question whether the human brain isemploying similar approaches to these models. This tutorial aims to provide an accessible intro-duction to the extensive research on this topic, specifically focusing on studies that seek to es-tablish quantitative correlations between neuroimaging data from human subjects and the outputof language models or automatic speech recognition systems. The tutorial covers various aspectsof this research, including a brief overview of brain-computer interfaces and neuroscience, com-mon techniques for data processing and pattern analysis, and representative research examples. Finally, the tutorial addresses the main limitations and technical challenges encountered in thisfield, as well as the relationship between brain mechanism research and brain-inspired artificialintelligence.”

In automatic emotion recognition (AER), labels assigned by different human annotators to the same utterance are often inconsistent due to the inherent complexity of emotion and the subjectivity of perception. Though deterministic labels generated by averaging or voting are often used as the ground truth, it ignores the intrinsic uncertainty revealed by the inconsistent labels. This paper proposes a Bayesian approach, deep evidential emotion regression (DEER), to estimate the uncertainty in emotion attributes. Treating the emotion attribute labels of an utterance as samples drawn from an unknown Gaussian distribution, DEER places an utterance-specific normal-inverse gamma prior over the Gaussian likelihood and predicts its hyper-parameters using a deep neural network model. It enables a joint estimation of emotion attributes along with the aleatoric and epistemic uncertainties. AER experiments on the widely used MSP-Podcast and IEMOCAP datasets showed DEER produced state-of-the-art results for both the mean values and the distribution of emotion attributes.