arXiv subjects

Dawei Huang

Publications and source records attributed to Dawei Huang.

14 recordsLinked to original sources

arXiv2026

ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning

Group-robust learning is crucial for maintaining accuracy on rare subpopulations when training-group labels are unavailable. However, existing methods often infer environments from a separate reference model and select representations before fitting the classifier used at deployment, leaving both decisions misaligned with the deployed predictor. In this work, we formulate group robustness without training-group labels as the endogenous environments with repair-aware selection (ERAS) problem, and propose ProME (Prototype-Margin Environments) to align both decisions with the deployed predictor. ProME splits prototype margins at their median to construct approximately balanced environments along the training trajectory, and fits a group-balanced linear head on group-annotated validation data to rank the resulting predictors by validation worst-group accuracy. We theoretically bound the worst risk across the inferred environments for a fixed predictor and partition, showing that this bound transfers to the oracle groups under an explicit alignment condition. Extensive experiments show that prototype margins enrich shortcut-conflicting examples, classifier repair reshapes candidate evaluation, and ProME achieves the highest average worst-group accuracy among the compared methods with the same group-label access.

cs.LG↗

arXiv2026

Robust Speech Emotion Recognition under Tone-Word Conflict: A Benchmark and Framework

Speech emotion recognition (SER) is a crucial component of human-computer interaction, attracting extensive attention from both industry and academia. However, existing SER systems typically assume alignment between vocal tone and lexical semantics, overlooking the real-world scenarios that involve tone-word conflict-where the emotion conveyed by speech contradicts the literal meaning of the words. To bridge this gap, we introduce TWIN-SER (Tone-Word Incongruent SER), a benchmark for systematic evaluation under acoustic-semantic incongruence, and show that state-of-the-art models degrade severely under such incongruence. To address this, we propose DAS (Disentangled Acoustic-Semantic fusion), a framework that mitigates tone-word conflict by explicitly disentangling acoustic and semantic pathways, selecting informative high-energy embeddings, and adaptively fusing them via a lightweight query-based attention mechanism. Specifically, DAS comprises three crucial modules: i) a heterogeneous feature extraction module that separately captures complementary acoustic and semantic representations from raw input; ii) a high-energy embedding selection module that identifies and retains the most discriminative embeddings; and iii) a Q-Former combination module that bridges the two pathways through cross-attention, enabling robust emotion prediction under incongruent conditions. Extensive experiments demonstrate that DAS consistently outperforms existing methods in tone-word conflict scenarios, as well as in standard in-domain and zero-shot settings. Our code and datasets are available at https://github.com/24DavidHuang/FAS

eess.AS↗

arXiv2026

SecGoal: A Benchmark for Extracting Formalizable Security Goals from Protocol Documents

Formal verification provides rigorous guarantees for cryptographic security, yet extracting formalizable security goals from natural-language protocol documents remains largely manual. We introduce SecGoal, a dedicated expert-annotated dataset and benchmark for extracting formalizable security goal statements from protocol documents, covering 15 widely deployed protocols, together with AIFG, a schema- and flow-conditioned framework for structured formal security property generation. Our evaluation shows that frontier and large LLMs achieve high property recall but low extraction precision because they often fail to distinguish formalizable security goals from non-goal protocol content. In contrast, SecGoal fine-tuning makes smaller open-source LLMs substantially more selective extractors of formalizable security goals. On the held-out test protocols, Gemma2-9B-FT improves extraction precision from 24.0\% to 66.6\% and reaches 97.6\% property recall, outperforming larger prompted LLMs and encoder baselines. In a controlled setting, AIFG shows that concise goal inputs can support high-recall structured property generation, while expert-vetted extracted inputs reveal over-generation as the main remaining bottleneck. Together, SecGoal and AIFG provide a dataset, benchmark, and framework for specification-grounded security goal extraction and property generation.

cs.CR↗

arXiv2026

When Tone and Words Disagree: Towards Robust Speech Emotion Recognition under Acoustic-Semantic Conflict

Speech Emotion Recognition (SER) systems often assume congruence between vocal emotion and lexical semantics. However, in real-world interactions, acoustic-semantic conflict is common yet overlooked, where the emotion conveyed by tone contradicts the literal meaning of spoken words. We show that state-of-the-art SER models, including ASR-based, self-supervised learning (SSL) approaches and Audio Language Models (ALMs), suffer performance degradation under such conflicts due to semantic bias or entangled acoustic-semantic representations. To address this, we propose the Fusion Acoustic-Semantic (FAS) framework, which explicitly disentangles acoustic and semantic pathways and bridges them through a lightweight, query-based attention module. To enable systematic evaluation, we introduce the Conflict in Acoustic-Semantic Emotion (CASE), the first dataset dominated by clear and interpretable acoustic-semantic conflicts in varied scenarios. Extensive experiments demonstrate that FAS consistently outperforms existing methods in both in-domain and zero-shot settings. Notably, on the CASE benchmark, conventional SER models fail dramatically, while FAS sets a new SOTA with 59.38% accuracy. Our code and datasets is available at https://github.com/24DavidHuang/FAS.

cs.SD↗

arXiv2025

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

Existing speech models suffer from competing requirements on token representations by understanding and generation tasks. This discrepancy in representation prevents speech language models from performing instruction-based free-form editing. To solve this challenge, we introduce a novel framework that unifies speech understanding, generation, and editing. The core of our unified model is a unified continuous speech tokenizer MingTok-Audio, the first continuous tokenizer to effectively integrate semantic and acoustic features, which makes it suitable for both understanding and generation tasks. Based on this unified continuous audio tokenizer, we developed the speech language model Ming-UniAudio, which achieved a balance between generation and understanding capabilities. Ming-UniAudio sets new state-of-the-art (SOTA) records on 8 out of 12 metrics on the ContextASR benchmark. Notably, for Chinese voice cloning, it achieves a highly competitive Seed-TTS-WER of 0.95. Leveraging this foundational model, we further trained a dedicated speech editing model Ming-UniAudio-Edit, the first speech language model that enables universal, free-form speech editing guided solely by natural language instructions, handling both semantic and acoustic modifications without timestamp condition. To rigorously assess the editing capability and establish a foundation for future research, we introduce Ming-Freeform-Audio-Edit, the first comprehensive benchmark tailored for instruction-based free-form speech editing, featuring diverse scenarios and evaluation dimensions spanning semantic correctness, acoustic quality, and instruction alignment. We open-sourced the continuous audio tokenizer, the unified foundational model, and the free-form instruction-based editing model to facilitate the development of unified audio understanding, generation, and manipulation.

cs.CL↗

arXiv2025

Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding

Accurate emotion understanding in videos necessitates effectively recognizing and interpreting emotional states by integrating visual, textual, auditory, and contextual cues. Although recent Large Multimodal Models (LMMs) have exhibited significant progress in general vision-language (VL) tasks, their performance often deteriorates in emotion-specific scenarios, exhibiting catastrophic forgetting when fine-tuned on emotion-centric tasks. To overcome these limitations, we propose Emotion-Qwen, a unified multimodal framework designed to simultaneously enable robust emotion understanding and preserve general VL reasoning capabilities. Emotion-Qwen introduces a novel Hybrid Compressor based on a Mixture-of-Experts (MoE) architecture, dynamically routing inputs to optimally balance emotion-specific processing and general multimodal reasoning. We further propose a carefully structured three-stage pre-training pipeline, leveraging extensive general and emotion-focused datasets to strengthen multimodal representation robustness and model adaptability. Additionally, we develop the Video Emotion Reasoning (VER) dataset, a large-scale bilingual resource containing over 40K video clips annotated with detailed context-aware emotional descriptions, significantly facilitating research on fine-grained emotional reasoning. Extensive experiments confirm that Emotion-Qwen achieves state-of-the-art performance across multiple emotion recognition and reasoning benchmarks, while maintaining highly competitive results in general VL tasks.

cs.MM↗

arXiv2024

miMamba: EEG-based Emotion Recognition with Multi-scale Inverted Mamba Models

EEG-based emotion recognition holds significant potential in the field of brain-computer interfaces. A key challenge lies in extracting discriminative spatiotemporal features from electroencephalogram (EEG) signals. Existing studies often rely on domain-specific time-frequency features and analyze temporal dependencies and spatial characteristics separately, neglecting the interaction between local-global relationships and spatiotemporal dynamics. To address this, we propose a novel network called Multi-Scale Inverted Mamba (MS-iMamba), which consists of Multi-Scale Temporal Blocks (MSTB) and Temporal-Spatial Fusion Blocks (TSFB). Specifically, MSTBs are designed to capture both local details and global temporal dependencies across different scale subsequences. The TSFBs, implemented with an inverted Mamba structure, focus on the interaction between dynamic temporal dependencies and spatial characteristics. The primary advantage of MS-iMamba lies in its ability to leverage reconstructed multi-scale EEG sequences, exploiting the interaction between temporal and spatial features without the need for domain-specific time-frequency feature extraction. Experimental results on the DEAP, DREAMER, and SEED datasets demonstrate that MS-iMamba achieves classification accuracies of 94.86%, 94.94%, and 91.36%, respectively, using only four-channel EEG signals, outperforming state-of-the-art methods.

cs.HC↗

arXiv2024

SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition

This paper presents our winning approach for the MER-NOISE and MER-OV tracks of the MER2024 Challenge on multimodal emotion recognition. Our system leverages the advanced emotional understanding capabilities of Emotion-LLaMA to generate high-quality annotations for unlabeled samples, addressing the challenge of limited labeled data. To enhance multimodal fusion while mitigating modality-specific noise, we introduce Conv-Attention, a lightweight and efficient hybrid framework. Extensive experimentation vali-dates the effectiveness of our approach. In the MER-NOISE track, our system achieves a state-of-the-art weighted average F-score of 85.30%, surpassing the second and third-place teams by 1.47% and 1.65%, respectively. For the MER-OV track, our utilization of Emotion-LLaMA for open-vocabulary annotation yields an 8.52% improvement in average accuracy and recall compared to GPT-4V, securing the highest score among all participating large multimodal models. The code and model for Emotion-LLaMA are available at https://github.com/ZebangCheng/Emotion-LLaMA.

cs.MM↗

arXiv2024

StyleBrush: Style Extraction and Transfer from a Single Image

Stylization for visual content aims to add specific style patterns at the pixel level while preserving the original structural features. Compared with using predefined styles, stylization guided by reference style images is more challenging, where the main difficulty is to effectively separate style from structural elements. In this paper, we propose StyleBrush, a method that accurately captures styles from a reference image and ``brushes'' the extracted style onto other input visual content. Specifically, our architecture consists of two branches: ReferenceNet, which extracts style from the reference image, and Structure Guider, which extracts structural features from the input image, thus enabling image-guided stylization. We utilize LLM and T2I models to create a dataset comprising 100K high-quality style images, encompassing a diverse range of styles and contents with high aesthetic score. To construct training pairs, we crop different regions of the same training image. Experiments show that our approach achieves state-of-the-art results through both qualitative and quantitative analyses. We will release our code and dataset upon acceptance of the paper.

cs.CV↗

arXiv2024

SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts

Monolithic large language models (LLMs) like GPT-4 have paved the way for modern generative AI applications. Training, serving, and maintaining monolithic LLMs at scale, however, remains prohibitively expensive and challenging. The disproportionate increase in compute-to-memory ratio of modern AI accelerators have created a memory wall, necessitating new methods to deploy AI. Composition of Experts (CoE) is an alternative modular approach that lowers the cost and complexity of training and serving. However, this approach presents two key challenges when using conventional hardware: (1) without fused operations, smaller models have lower operational intensity, which makes high utilization more challenging to achieve; and (2) hosting a large number of models can be either prohibitively expensive or slow when dynamically switching between them. In this paper, we describe how combining CoE, streaming dataflow, and a three-tier memory system scales the AI memory wall. We describe Samba-CoE, a CoE system with 150 experts and a trillion total parameters. We deploy Samba-CoE on the SambaNova SN40L Reconfigurable Dataflow Unit (RDU) - a commercial dataflow accelerator architecture that has been co-designed for enterprise inference and training applications. The chip introduces a new three-tier memory system with on-chip distributed SRAM, on-package HBM, and off-package DDR DRAM. A dedicated inter-RDU network enables scaling up and out over multiple sockets. We demonstrate speedups ranging from 2$\times$ to 13$\times$ on various benchmarks running on eight RDU sockets compared with an unfused baseline. We show that for CoE inference deployments, the 8-socket RDU Node reduces machine footprint by up to 19$\times$, speeds up model switching time by 15$\times$ to 31$\times$, and achieves an overall speedup of 3.7$\times$ over a DGX H100 and 6.6$\times$ over a DGX A100.

cs.AR↗

arXiv2019

Joins on Samples: A Theoretical Guide for Practitioners

Despite decades of research on approximate query processing (AQP), our understanding of sample-based joins has remained limited and, to some extent, even superficial. The common belief in the community is that joining random samples is futile. This belief is largely based on an early result showing that the join of two uniform samples is not an independent sample of the original join, and that it leads to quadratically fewer output tuples. However, unfortunately, this result has little applicability to the key questions practitioners face. For example, the success metric is often the final approximation's accuracy, rather than output cardinality. Moreover, there are many non-uniform sampling strategies that one can employ. Is sampling for joins still futile in all of these settings? If not, what is the best sampling strategy in each case? To the best of our knowledge, there is no formal study answering these questions. This paper aims to improve our understanding of sample-based joins and offer a guideline for practitioners building and using real-world AQP systems. We study limitations of offline samples in approximating join queries: given an offline sampling budget, how well can one approximate the join of two tables? We answer this question for two success metrics: output size and estimator variance. We show that maximizing output size is easy, while there is an information-theoretical lower bound on the lowest variance achievable by any sampling strategy. We then define a hybrid sampling scheme that captures all combinations of stratified, universe, and Bernoulli sampling, and show that this scheme with our optimal parameters achieves the theoretical lower bound within a constant factor. Since computing these optimal parameters requires shuffling statistics across the network, we also propose a decentralized variant where each node acts autonomously using minimal statistics.

cs.DB↗

arXiv2019

The Communication Complexity of Set Intersection and Multiple Equality Testing

In this paper we explore fundamental problems in randomized communication complexity such as computing Set Intersection on sets of size $k$ and Equality Testing between vectors of length $k$. Sa\u{g}lam and Tardos and Brody et al. showed that for these types of problems, one can achieve optimal communication volume of $O(k)$ bits, with a randomized protocol that takes $O(\log^* k)$ rounds. Aside from rounds and communication volume, there is a \emph{third} parameter of interest, namely the \emph{error probability} $p_{\mathrm{err}}$. It is straightforward to show that protocols for Set Intersection or Equality Testing need to send $\Omega(k + \log p_{\mathrm{err}}^{-1})$ bits. Is it possible to simultaneously achieve optimality in all three parameters, namely $O(k + \log p_{\mathrm{err}}^{-1})$ communication and $O(\log^* k)$ rounds? In this paper we prove that there is no universally optimal algorithm, and complement the existing round-communication tradeoffs with a new tradeoff between rounds, communication, and probability of error. In particular: 1. Any protocol for solving Multiple Equality Testing in $r$ rounds with failure probability $2^{-E}$ has communication volume $\Omega(Ek^{1/r})$. 2. There exists a protocol for solving Multiple Equality Testing in $r + \log^*(k/E)$ rounds with $O(k + rEk^{1/r})$ communication, thereby essentially matching our lower bound and that of Sa\u{g}lam and Tardos. Our original motivation for considering $p_{\mathrm{err}}$ as an independent parameter came from the problem of enumerating triangles in distributed ($\textsf{CONGEST}$) networks having maximum degree $\Delta$. We prove that this problem can be solved in $O(\Delta/\log n + \log\log \Delta)$ time with high probability $1-1/\operatorname{poly}(n)$.

cs.IT↗

arXiv2017

Approximate Generalized Matching: $f$-Factors and $f$-Edge Covers

In this paper we present linear time approximation schemes for several generalized matching problems on nonbipartite graphs. Our results include $O_\epsilon(m)$-time algorithms for $(1-\epsilon)$-maximum weight $f$-factor and $(1+\epsilon)$-approximate minimum weight $f$-edge cover. As a byproduct, we also obtain direct algorithms for the exact cardinality versions of these problems running in $O(m\sqrt{f(V)})$ time. The technical contributions of this work include an efficient method for maintaining {\em relaxed complementary slackness} in generalized matching problems and approximation-preserving reductions between the $f$-factor and $f$-edge cover problems.

cs.DS↗

arXiv2016

Fully Dynamic Connectivity in $O(\log n(\log\log n)^2)$ Amortized Expected Time

Dynamic connectivity is one of the most fundamental problems in dynamic graph algorithms. We present a randomized Las Vegas dynamic connectivity data structure with $O(\log n(\log\log n)^2)$ amortized expected update time and $O(\log n/\log\log\log n)$ worst case query time, which comes very close to the cell probe lower bounds of Patrascu and Demaine (2006) and Patrascu and Thorup (2011).

cs.DS↗