Jun Luo

Yishan Lv, Jing Luo, Xinyu Yang et al.

Singing Quality Assessment (SQA) has become increasingly important for practical multimedia applications and Music AI systems, yet existing studies predominantly focus on short singing clips and remain insufficient for full-length songs. Unlike clip-level assessment, full-length song SQA requires modeling how singing quality varies across different audio segments and how these local variations influence the overall evaluation of vocal performance. Moreover, the scarcity of segment-level annotations makes effective supervision challenging, as directly assigning a single overall score label to every segment tends to treat different segment qualities as equivalent. To address these challenges, we propose SongSQA, a two-stage framework for full-length song SQA. In the first stage, a Segment Score Predictor is trained with pseudo labels generated by a pre-trained teacher model, enabling segment-level singing quality prediction without requiring manual segment annotations. In the second stage, a Song Quality Aggregator integrates segment features and predicted segment scores into unified segment embeddings, and employs a learnable song embedding together with self-attention to capture the connection between segment-level vocal performance and overall song quality. In this way, SongSQA dynamically aggregates critical quality cues across the song to produce a holistic quality prediction, while also generating a temporal segment-level quality curve. Experimental results demonstrate the effectiveness of SongSQA for full-length song SQA, achieving up to a 13.95% relative improvement in KTAU over the strongest baseline, while consistently improving other evaluation metrics across all datasets.

Jie Luo, Qi Jin, Xinming Zhang

Multi-modal Sequential Recommendation (SR) incorporates rich side information (e.g., textual and visual features) to enhance dynamic user preference modeling. However, existing frameworks inevitably suffer from a \textbf{Dual-Noise Dilemma}: (1) \textit{Feature-level redundancy} stemming from the semantic gap between generic pre-trained representations and fine-grained recommendation intent; and (2) \textit{Sequence-level stochasticity} induced by spurious interactions such as accidental clicks. To break this bottleneck, we propose \textbf{DDMSR}, a novel \textbf{D}ual-level \textbf{D}enoising \textbf{M}ulti-modal \textbf{S}equential \textbf{R}ecommendation framework that systematically purifies signals from both feature-topological and sequence-frequency perspectives. Specifically, we first design a graph-based feature denoising module that leverages Laplacian smoothing on item semantic graphs as a structural low-pass filter, effectively suppressing high-frequency semantic noise while preserving salient features. For sequence purification, we introduce a frequency-domain sequence denoising module, utilizing the Fast Fourier Transform and a learnable frequency filter to adaptively modulate the interaction spectrum and attenuate anomalous signals. Furthermore, a multi-modal contrastive alignment objective is incorporated to bridge the heterogeneity gap and enforce cross-modal semantic consistency. Extensive experiments on four public benchmark datasets demonstrate that DDMSR consistently outperforms state-of-the-art baselines, providing a highly robust and efficient solution for multi-modal sequential recommendation. The source code is available at: ~\href{https://github.com/jluo00/DDMSR}{\textcolor{blue}{https://github.com/jluo00/DDMSR}}.

Han Jiang, Sunbeom Kwon, Jinwen Luo et al.

AI benchmarks increasingly leverage item-level statistical models, particularly item response theory (IRT), to estimate model capabilities, rank systems, select informative examples, and diagnose benchmark quality. However, AI benchmark data often departs from the data regime of human testing, for which standard IRT estimation tools were originally developed: benchmarks typically involve fewer evaluated models, far more items, and capability distributions that may be skewed, clustered, or multimodal. We examine how these regime mismatches challenge the reliability of IRT modeling for AI evaluation. Using item parameters and capability distributions derived from six widely used LLM benchmarks, we simulate response matrices under three common IRT models and compare four estimation tools used in recent benchmark studies: marginal maximum likelihood, Markov chain Monte Carlo, variational inference, and a neural pseudo-Siamese estimator. Across 18,000 simulation conditions, we systematically evaluate computational feasibility, scalability, and the reliability of IRT inferences about model rankings, predicted performance, and item characteristics. Results show that classical estimators can become infeasible in large benchmark settings, whereas scalable estimators can produce unreliable item-level and ranking inferences with small or nonnormally distributed model sets. This study identifies when latent trait models reliably support or risk distorting AI benchmarking claims, and what sample sizes and diagnostics are needed for trustworthy use.

Xiangyu Chen, Jixiang Luo, Yuankai Fan et al.

Under the AI Flow framework, communication is shifting from transmitting fidelity-oriented information flows toward delivering task-oriented and perception-oriented token flows across heterogeneous network resources. Video communication is a fundamental component of modern information networks. However, under ultra-low-bandwidth and weak-network conditions, conventional video coding and transmission methods, which are primarily optimized for pixel-level fidelity, often struggle to balance visual usability, transmission efficiency, and robustness to unstable links. With the rapid advancement of generativemodels, video communication is also moving from precise signal reconstruction toward receiver-side perceptual utility and system-level usability. In this paper, we propose Generative Transmission (GenTrans) for video communication under ultra-low-bandwidth and weak-network conditions. Built upon Generative Video Compression (GVC), GenTrans formulates video transmission as a joint optimization problem involving bandwidth, computation, and memory, rather than treating it merely as a signal coding task. By leveraging generative priors, cross-clip memory reuse, runtime state reuse, and weak-network-aware transport, GenTrans significantly reduces transmission overhead while enabling visually coherent and practically useful reconstruction. Experimental results show that GenTrans supports effective video transmission under ultra-low-bitrate and weak-network conditions, achieving improved transmission efficiency, decoding efficiency, and robustness while preserving perceptual quality.

Jiamu Luo, Shane Steinert-Threlkeld

Coordination, a fundamental linguistic structure, remains a subject of intense debate, and its exact nature continues to elude theoretical linguistics. A common view holds that only same-category constituents can be conjoined, which has been challenged by the many grammatical unlike coordinations found in natural language. Treating language models as a computational testbed, we investigate whether the acquisition of unlike coordination requires direct exposure in the training data, or whether it can emerge organically from general compositional abilities. Using Filtered-Corpus Training (FiCT), we train GPT-2 models on corpora from which all instances of unlike coordination have been removed. We find that direct exposure is not necessary: models trained on filtered data successfully generalize to unlike coordination, achieving perplexity and grammaticality judgments comparable to models trained on unfiltered text. Furthermore, our analyses of internal representations indicate that language models process unlike coordination by treating the conjoined elements as belonging to similar structural categories or through a mechanism akin to deletion, both of which appear learnable from exposure to alike coordination alone. This work contributes to the growing understanding of how language models internally represent linguistic structures, while also adding to the broader debate on coordination by showing how models generalize and process unlike coordination without direct exposure.

Cheng-You Ho, Justin Luo, Henry Ng et al.

Dissipative cat qubits exponentially suppress one Pauli error channel with the mean photon number, leaving the conjugate bit-flip error as the dominant failure mode. This strong noise bias makes the full machinery of general quantum error correction unnecessary: a code need only protect against a single error type, and any classical linear code can be promoted to a Clifford stabilizer code that does exactly this. We use this observation to build a Clifford-only quantum Reed-Solomon (RS) code. Starting from the [7,3,5] RS code over $GF(2^{3})$ which is maximum distance separable, we expand each field symbol into three bits to obtain the [21,9,6] linear code over $GF(2)$, realized as a [[21,9, $d_{X}=6$, $d_{Z}=1$]] bit-flip code whose stabilizers are products of Z operators. Because no phase-flip correction is attempted, the construction avoids the non-Clifford quantum Fourier transform required by the Grassl-Beth quantum RS codes and is fully simulable in Stim. Errors are decoded by a lookup table of minimum-weight corrections. We then introduce a Tornado architecture: a two-layer concatenation that wraps every position of the outer RS code in an inner distance-three repetition code, yielding a [[63, 9, 18]] code decoded in two stages, a majority vote within each repetition block followed by the outer lookup table. Monte Carlo simulations show that at a physical bit-flip rate $p=0.1$ the Tornado code reaches a logical error rate $p_{L}\approx5.3\times10^{-3}$, below both parent codes, and that its logical error rate scales as $p_{L}\propto p^{6}$ at low p, in contrast to $p^{2}$ for the repetition code and $p^{3}$ for the standalone RS code. We give the exact construction, the error and circuit model, an asymptotic scaling analysis, and an account of the overhead cost and of the assumptions behind the noise model.

Wen Fang, Xianxian Li, Jun Liu et al.

Self-reference and solution independence are core properties underlying intractability. This paper establishes a finite combinatorial analogue of Gödel's incompleteness theorems within Boolean $K$-SAT. While standard random $K$-SAT has assignment correlations that disrupt solution independence, we resolve this via a logarithmic-width ensemble ($K = O(\log N)$). Here, satisfying assignments converge to a Poisson distribution, letting unsatisfiable and uniquely satisfiable formulas coexist. By executing a single-clause substitution conditioned on the unique solution, we construct structurally irreducible SAT/UNSAT pairs that are indistinguishable via local evaluation. Using algorithmic information theory and Shannon channels, we prove that deductive pipelines restricted to a sublinear window suffer from an informational blind spot, forcing a descriptive lower bound of $K(\mathcal{A}) \geq Ω(N^{1-δ})$. This deficit forces any Resolution refutation of the UNSAT instance to utilize wide clauses ($w(π) \geq Ω(N^{1-δ})$), triggering an exponential proof-tree explosion ($S(ϕ) \geq \exp(Ω(N^{1-2δ}))$). As $δ\rightarrow 0^+$, this bound converges to the worst-case $2^N$ threshold, reframing the Strong Exponential Time Hypothesis (SETH) as a direct projection of Gödel incompleteness onto finite computation. We diagnose the decades-long stagnation in complexity theory. Transitioning from Turing's class separation to a Gödelian paradigm of instance indistinguishability, we introduce a multi-dimensional comparative framework that contrasts these two historical lineages across distinct perspectives. The self-referential hardness exhibits physical invariance: it precludes quantum shortcuts due to the necessity of global semantic analysis and delineates a scaling bottleneck for machine learning architectures operating on lossy, local compression.