Searcharxiv⌕ Search

arXiv subjects

Lin Yao

Publications and source records attributed to Lin Yao.

At least 19 recordsLinked to original sources
arXiv2026

A Ticket from Marginals to Joints: Coupled-Noise Distillation for One-Step Block Generation in Diffusion Language Models

Autoregressive language models commit one token per forward pass; diffusion language models commit a block of tokens over several steps. We ask whether a block can be committed in a single forward pass. We study this with a noise-conditioned masked denoiser: a data-independent Gaussian noise field is added to the mask embeddings so that, in principle, each sampled field selects one joint mode of the block. The established way of training such a model is to sample several fields per example and let them compete for the data, by winner-take-all or importance weighting. This gives the noise only coarse control: in our experiments, the information it carries grows roughly with the logarithm of the number of competing fields, and one-step outputs remain rarely coherent across the model sizes tested. We propose CONDOR (Coupled-Noise Distillation for One-Step Readout). A noise-conditioned teacher is trained with a random number of masked positions and winner-take-all. A student proposes a one-step block, retains selected tokens, and learns from the block obtained when the teacher refills the other positions in several steps under the same noise field; a noise-free masked-LM term on the ground truth anchors the student. Human evaluation on TinyStories shows a large gain in one-step legality while different noise fields still yield different blocks, at one forward pass per block.

cs.CL↗
arXiv2026

Interpretable EEG biomarkers with bag-of-waves: Spatial and temporal waveform dictionaries for low-data regimes

Electroencephalography (EEG) is widely used to diagnose neurological conditions, but its analysis usually relies on either predefined spectral features or deep neural networks. Predefined features carry a strong bias, since they fix in advance what counts as informative, while deep neural networks and foundation models are hard to interpret and need large amounts of data and compute. We present bag-of-waves, an interpretable framework that learns a small dictionary of recurring EEG waveform templates, called atoms, using shift-invariant k-means without labels. The continuous EEG is then turned into a sequence of atom tokens, whose counts feed a simple downstream classifier or clustering step. We extend this representation in two ways: we add atom-to-atom transitions, which we call n- grams, to capture temporal structure, and we move from single-channel atoms to regional and cross-channel spatial atoms for the multichannel case. We test the method on three complementary datasets, each probing a different aspect: single-channel mouse genotype clustering with only sixteen animals (the low-data and temporal case), resting-state dementia classification (the spatial case), and the TUEV benchmark, a six-way classification of clinical EEG events (a high-data comparison against strong deep and foundation baselines). Across all three datasets, bag-of-waves achieves performance competitive with state-of-the-art deep and foundation models. Yet, it operates with a fraction of the parameter count and provides full interpretability: because every atom corresponds to an inspectable waveform, the method explicitly recovers known clinical morphologies that a neurophysiologist can directly validate. Its main advantage is that it works in the low-data regime where heavier models are a poor fit.

cs.LG↗
arXiv2026

TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue

The sycophancy of large language models can increase the safety risk in intervention dialogue for autistic children. Supervised fine-tuning can somewhat reduce sycophancy, but relying solely on positive examples is often insufficient to identify and correct failure patterns. We observe that sycophancy behaviors can often be localized to a limited span within the model response. In this regime, sequence-level preference optimization can over-update preference-irrelevant tokens and degrade intervention ability. To address this, we propose the \textbf{M}inimal \textbf{E}dit \textbf{D}ata \textbf{A}ugmentation (MEDA) strategy to construct controlled, stable, minimal edit preference pairs and \textbf{T}oken-level \textbf{D}ifference \textbf{D}irect \textbf{P}reference \textbf{O}ptimization (TD-DPO), which upweights difference tokens between chosen and rejected responses while downweighting shared tokens to suppress background drift. Extensive experiments across multiple backbones and evaluators show that TD-DPO achieves a better trade-off between sycophancy mitigation and intervention ability retention in our offline settings, highlighting its potential as a practical alignment approach for autism intervention.

cs.LG↗
arXiv2026

xHC: Expanded Hyper-Connections

Hyper-Connections (HC) expand the residual stream of Transformers into $N$ parallel streams, providing a form of memory scaling beyond model width and depth. Manifold-Constrained HC (mHC) stabilizes this formulation at scale. The large gains from $N{=}1$ to $N{=}4$ suggest residual-stream expansion as a promising scaling axis. However, existing HC-family methods typically stop at $N{=}4$. Our experiments reveal why: scaling mHC beyond this point yields diminishing performance gains and rapidly increasing training cost. We attribute this limitation to two bottlenecks: insufficient write-back information for an expanding number of streams and residual-mixing generation whose cost scales cubically with $N$. To address both bottlenecks, we propose xHC (Expanded Hyper-Connections), the first HC-family method to achieve meaningful expansion beyond $N{=}4$. xHC combines temporal feature augmentation for richer write-back with a sparse residual-stream architecture that updates only $k=4$ of the $N=16$ streams while retaining dense access to the full residual state. Across 18B and 28B MoE models, xHC delivers strong and consistent downstream improvements. On an 18B MoE model, xHC improves the average downstream score by 4.0 points over mHC, while adding only modest training FLOPs over the vanilla baseline. Scaling-law experiments show that the vanilla and mHC require $1.50\times$ and $1.19\times$ the compute of xHC, respectively, to reach the same loss. Practical large-$N$ training also requires controlling memory traffic from the expanded residual state. We therefore introduce xHC-Flash, which reduces the per-sublayer memory traffic from $73.5C$ to $40C$, comparable to the $34C$ required by mHC at $N{=}4$, while retaining the gains of full xHC. Together, xHC and xHC-Flash make large-$N$ residual-stream expansion effective and practical for LLM pre-training.

cs.LG↗
arXiv2026

TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories

Pediatric electronic health records capture developmentally structured clinical trajectories, yet their potential for generative healthcare foundation models remains largely unexplored. Here we present TEDDY (Temporal Event Decoder for Disease in Youth), a 1.84-million-parameter decoder transformer trained on approximately 73 million ICD-10 diagnoses from 1.6 million children at a single pediatric institution. TEDDY models longitudinal diagnosis trajectories and visit timing. Predictions were made before visit codes were revealed, limited to first occurrences, and evaluated against sex- and age-matched controls. Across 797 disease-onset prediction tasks spanning 16 ICD-10 chapters, TEDDY achieved a median AUC of 72.0%, outperforming same-data DenseNet (50.0%), CNN (57.2%), RNN (60.1%), and LSTM (62.7%) baselines on 96-99% of tasks. Performance held across sex and age and was strongest among lower-prevalence diagnoses; 202 of the 225 rarest conditions (90%) had 95% confidence intervals above chance. Predictive signal remained detectable more than two years before first recorded diagnosis, with median AUCs of 59.7% in the unrestricted analysis and 64.4% in a fixed-cohort sensitivity analysis. In asthma and attention-deficit/hyperactivity disorder benchmarks, AUCs were 79.3% and 84.7%, compared with 62.7% and 71.7% for the strongest comparators, including a general-purpose language model three orders of magnitude larger. Visit-timing predictions had a 3.0-day mean absolute restricted mean survival-time error over 365 days, although median and long-tail return intervals remained miscalibrated. Together, these results establish pediatric diagnostic histories as a substrate for compact generative models supporting broad, rare-disease, and long-horizon risk forecasting without population-scale data or billion-parameter models.

cs.LG↗
arXiv2026

Don't Commit Alone: Joint Token Commitment in Diffusion Language Models

Diffusion language models (dLLMs) commit multiple tokens per denoising step by decoding each selected position independently from a shared context. When these positions are dependent, this factorization introduces an error captured by conditional total correlation, which confidence-based selection cannot infer from marginal probabilities alone. We propose CoCommit, a marker-gated coordination pass that delays commitment. After the usual bundle selection, a learned marker identifies the commit set, and the backbone's last n layers are re-applied to coordinate the marked positions before greedy argmax writes the tokens. This approximates joint-mode decoding while reusing existing weights, requiring only one partial forward pass and no auxiliary model. On LLaDA 2.1 with LoRA adapters and greedy inference, joint commitment improves five of the seven evaluated benchmarks over the released factorized decoder. The largest gains occur on code and reasoning tasks, while the remaining tasks are near parity.

cs.CL↗
arXiv2026

Self-Generated Error Training for Token Editing in Diffusion Language Models

Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at inference the editor sees the model's own fluent, high-confidence draft errors instead. We study this training-inference mismatch and propose self-generated T2T, which performs a no-gradient draft pass, fills masked positions with predicted tokens, and supervises recovery in a second pass under these self-generated corruptions. We implement the update as a short LoRA continued-pretraining pass on LLaDA2.1-mini and evaluate on several benchmarks under the official Q-Mode T2T procedure with unchanged inference parameters. The method generally improves accuracy while reducing T2T edit intensity, mitigating failure modes such as final-digit transcription errors after otherwise correct reasoning and excessive self-correction before short factual answers.

cs.CL↗
arXiv2026

Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform Spreading

Order-agnostic language models (OALMs), including discrete diffusion language models (dLLMs), are trained to predict masked tokens under arbitrary conditioning sets, allowing sequences to be generated or scored under arbitrary reveal orders at inference time. In LLaDA-2.1, we report three findings. First, the learned conditionals are not exact factorizations of a coherent joint distribution: changing only the reveal order shifts target log-likelihood by up to 0.49 nats/token, so likelihood alone mixes content difficulty with path-dependent artifacts. Second, although confidence-first (CF) decoding is order-agnostic, its reveal orders are close to left-to-right (L2R) on content tokens. Third, we propose a complementary diagnostic based on the shape of the confidence trace. A uniform-spreading theorem shows that, at fixed total likelihood, target recoverability is maximized when per-step confidence is spread uniformly; the resulting deviation motivates $\mathrm{Var}(\log q_t)$ as a diagnostic for comparing decoding paths. Across C4 and four downstream benchmarks, low variance separates structured paths from random ordering, and variance is consistently associated with downstream correctness. These results support reporting mean confidence and confidence variance jointly when comparing OALM decoding paths.

cs.CL↗
arXiv2026

Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Models

Diffusion language models (dLLMs) generate text through iterative denoising, filling multiple masked positions at each step. Positions filled in the same step are predicted without conditioning on one another's newly filled values and can therefore be mutually inconsistent; once retained, these inconsistencies become context for later predictions. We introduce \emph{Token-to-Mask} (T2M), a training-free inference-time correction method that identifies low-confidence positions using the model's probability of the current token, remasks them, and reconstructs them in later denoising steps. On dLLMs equipped with correction mechanisms, a single T2M configuration transfers across tasks and models without retuning and broadly improves task metrics over each model's native correction mechanism. In controlled experiments, we decompose correction methods into a detector that identifies suspicious tokens and an action that determines how to revise them. Holding the detector fixed, remasking yields higher task metrics than replacement; across the tested detector--action combinations, current-token-probability detection paired with remasking performs best. Compared with direct editing, T2M converts additional inference compute into performance gains more effectively and, on most tasks, retains a sequential-step advantage over autoregressive token-by-token decoding.

cs.CL↗
arXiv2026

From Synthesis to Clinical Assistance: A Strategy-Aware Agent Framework for Autism Intervention based on Real Clinical Dataset

The development of AI-assisted Early Intensive Behavioral Intervention (EIBI) for Autism Spectrum Disorder (ASD) is severely constrained by data scarcity. Furthermore, while Applied Behavior Analysis (ABA) serves as the gold standard for clinical intervention, general-purpose Large Language Models (LLMs) struggle to strictly adhere to its standardized procedures, often resulting in interactions that are linguistically fluent but strategically inconsistent. To address these challenges, we introduce \textsc{ASDAgent}, a strategy-aware framework designed to unify high-fidelity intervention dialogue synthesis and clinical decision support. \textsc{ASDAgent} incorporates two specialized components to solve distinct problems: (i) a \textsc{DoctorAgent} equipped with an Observe-Think-Act-Correct (O-T-A-C) reasoning loop, which resolves the issue of strategy collapse in LLMs by making ABA execution explicit and controllable; and (ii) a \textsc{ChildAgent} that utilizes probabilistic behavior modeling to mitigate data homogeneity, simulating diverse and non-deterministic ASD response patterns. Experiments demonstrate that dialogues generated by \textsc{ASDAgent} closely mirror the strategy distribution of human therapists (KL divergence: 0.083). In real autism intervention, \textsc{ASDAgent} achieves nearly 80\% strategic consistency with human experts. Moreover, we show that synthetic data produced by \textsc{ASDAgent} effectively distills professional clinical knowledge into small language models (SLMs), significantly enhancing their therapeutic capabilities.

cs.LG↗
arXiv2026

Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models

Discrete masked diffusion language models such as LLaDA generate text through iterative denoising, where mask tokens are progressively replaced with predicted tokens. LLaDA2.1 introduced a Token-to-Token (T2T) editing mechanism that accelerates generation by directly replacing committed tokens suspected of being incorrect. However, we identify fundamental limitations of T2T editing: it couples error detection with replacement, pollutes the generation context with potentially incorrect tokens, and introduces a train-inference noise mismatch where systematic model-generated errors differ from the random perturbations seen during training. We propose Token-to-Mask (T2M) remasking, a training-free, drop-in replacement for T2T editing that resets suspected erroneous tokens back to the mask state, allowing the diffusion process to re-predict them under cleaner context. We design and empirically validate three complementary error detection strategies -- probability-based, trigger-mirrored, and temporal-difference-based -- and provide a unified theoretical analysis showing that T2M remasking purifies the generation context, converts systematic inference errors back to the model's native mask noise type, and enables delayed commitment for joint multi-position optimization. Comprehensive experiments across 12 benchmarks spanning knowledge, reasoning, mathematics, coding, and instruction following show that T2M generally improves performance on tasks requiring precise token-level output, with the largest gain on mathematics (+5.92% on CMATH). Error analysis on CMATH reveals that the dominant failure mode is last-mile token corruption -- where correct reasoning produces a corrupted final answer -- and that T2M repairs 59.4% of such cases.

cs.CL↗
arXiv2026

Experimental Powder X-ray Diffraction Crystal Structure Determination with RealPXRD-Solver

Determining crystal structures from experimental powder X-ray diffraction data remains challenging because peak overlap, preferred orientation, and impurity phases obscure atomic arrangements. We present RealPXRD-Solver, a generative model trained on 6,250,238 theoretical structures with experiment-mimicking augmentations and a universal encoder of d-spacing--intensity fingerprints, enabling both lattice-conditioned and lattice-free inference. RealPXRD-Solver reaches a 98.3% Top-20 match rate on a 10,000-structure theoretical benchmark and achieves Top-1/Top-20 accuracies of 77.9%/91.9% on CNRS and 78.8%/92.9% on RRUFF experimental datasets, and it solved 39 previously unreported Powder Diffraction File entries.

cond-mat.mtrl-sci↗
arXiv2026

JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation

LLMs have traditionally scaled along dense dimensions, where performance is coupled with near-linear increases in computational cost. While MoE decouples capacity from compute, it introduces large memory overhead and hardware efficiency challenges. To overcome these, we propose token-indexed parameters as a novel, orthogonal scaling axis that decouple model capacity from FLOPs. Specifically, we introduce Joint-Token (JTok) and Mixture of Joint-Token (JTok-M), which augment Transformer layers with modulation vectors retrieved from auxiliary embedding tables. These vectors modulate the backbone via lightweight, element-wise operations, incurring negligible FLOPs overhead. Extensive experiments on both dense and MoE backbones, spanning from 650M (190M + 460M embedding) to 61B (17B + 44B embedding) total parameters, demonstrate that our approach consistently reduces validation loss and significantly improves downstream task performance (e.g., +4.1 on MMLU, +8.3 on ARC, +8.9 on CEval). Rigorous isoFLOPs analysis further confirms that JTok-M fundamentally shifts the quality-compute Pareto frontier, achieving comparable model quality with 35% less compute relative to vanilla MoE architectures, and we validate that token-indexed parameters exhibit a predictable power-law scaling behavior. Moreover, our efficient implementation ensures that the overhead introduced by JTok and JTok-M remains marginal.

cs.LG↗
arXiv2026

Innovator-VL: A Multimodal Large Language Model for Scientific Discovery

We present Innovator-VL, a scientific multimodal large language model designed to advance understanding and reasoning across diverse scientific domains while maintaining excellent performance on general vision tasks. Contrary to the trend of relying on massive domain-specific pretraining and opaque pipelines, our work demonstrates that principled training design and transparent methodology can yield strong scientific intelligence with substantially reduced data requirements. (i) First, we provide a fully transparent, end-to-end reproducible training pipeline, covering data collection, cleaning, preprocessing, supervised fine-tuning, reinforcement learning, and evaluation, along with detailed optimization recipes. This facilitates systematic extension by the community. (ii) Second, Innovator-VL exhibits remarkable data efficiency, achieving competitive performance on various scientific tasks using fewer than five million curated samples without large-scale pretraining. These results highlight that effective reasoning can be achieved through principled data selection rather than indiscriminate scaling. (iii) Third, Innovator-VL demonstrates strong generalization, achieving competitive performance on general vision, multimodal reasoning, and scientific benchmarks. This indicates that scientific alignment can be integrated into a unified model without compromising general-purpose capabilities. Our practices suggest that efficient, reproducible, and high-performing scientific multimodal models can be built even without large-scale data, providing a practical foundation for future research.

cs.CV↗
arXiv2025

LA-MARRVEL: A Knowledge-Grounded, Language-Aware LLM Framework for Clinically Robust Rare Disease Gene Prioritization

Rare disease diagnosis requires matching variant-bearing genes to complex patient phenotypes across large and heterogeneous evidence sources. This process remains time-intensive in current clinical interpretation pipelines. To overcome these limitations, We present LA-MARRVEL, a knowledge-grounded, language-aware LLM framework and designed for clinical robustness and practical deployment. LA-MARRVEL delivers a 12-15 percentage-point absolute improvement in Recall@1 over established gene prioritization approaches, showing that architectural design can drive substantial accuracy gains. We found that the central contributor is structured, phenotype-rich prompt construction that explicitly encodes patient and disease phenotypes, preserving clinically meaningful context more effectively than disease labels alone. Across three real-world cohorts, LA-MARRVEL consistently improves gene-ranking performance, including in challenging cases where the causal gene was initially ranked lower by first-stage prioritization. For each candidate gene, the system delivers clinically relevant, ACMG-aligned reasoning that integrates phenotype concordance, inheritance patterns, and variant-level evidence into auditable explanations, enabling streamlined clinical review. These findings suggest that knowledge-grounded LLM layer can enhance existing rare-disease gene prioritization workflows without altering established diagnostic pipelines.

q-bio.GN↗
arXiv2025

Deep learning the sources of MJO predictability: a spectral view of learned features

The Madden-Julian oscillation (MJO) is a planetary-scale, intraseasonal tropical rainfall phenomenon crucial for global weather and climate; however, its dynamics and predictability remain poorly understood. Here, we leverage deep learning (DL) to investigate the sources of MJO predictability, motivated by a central difference in MJO theories: which spatial scales are essential for driving the MJO? We first develop a deep convolutional neural network (DCNN) to forecast the MJO indices (RMM and ROMI). Our model predicts RMM and ROMI up to 21 and 33 days, respectively, achieving skills comparable to leading subseasonal-to-seasonal models such as NCEP. To identify the spatial scales most relevant for MJO forecasting, we conduct spectral analysis of the latent feature space and find that large-scale patterns dominate the learned signals. Additional experiments show that models using only large-scale signals as the input have the same skills as those using all the scales, supporting the large-scale view of the MJO. Meanwhile, we find that small-scale signals remain informative: surprisingly, models using only small-scale input can still produce skillful forecasts up to 1-2 weeks ahead. We show that this is achieved by reconstructing the large-scale envelope of the small-scale activities, which aligns with the multi-scale view of the MJO. Altogether, our findings support that large-scale patterns--whether directly included or reconstructed--may be the primary source of MJO predictability.

physics.ao-ph↗
arXiv2025

A brain-inspired paradigm for scalable quantum vision

One of the fundamental tasks in machine learning is image classification, which serves as a key benchmark for validating algorithm performance and practical potential. However, effectively processing high-dimensional, detail-rich images, a capability that is inherent in biological vision, remains a persistent challenge. Inspired by the human brain's efficient ``Forest Before Trees'' cognition, we propose a novel Guiding Paradigm for image recognition, leveraging classical neural networks to analyze global low-frequency information and guide targeted quantum circuit towards critical high-frequency image regions. We present the Brain-Inspired Quantum Classifier (BIQC), implementing this paradigm via a complementarity architecture where a quantum pathway analyzes the localized intricate details identified by the classical pathway. Numerical simulations on diverse datasets, including high-resolution images, show the BIQC's superior accuracy and scalability compared to existing methods. This highlights the promise of brain-inspired, hybrid quantum-classical approach for developing next-generation visual systems.

quant-ph↗
arXiv2025

Membership Inference Attack with Partial Features

Machine learning models are vulnerable to membership inference attack, which can be used to determine whether a given sample appears in the training data. Most existing methods assume the attacker has full access to the features of the target sample. This assumption, however, does not hold in many real-world scenarios where only partial features are available, thereby limiting the applicability of these methods. In this work, we introduce Partial Feature Membership Inference (PFMI), a scenario where the adversary observes only partial features of each sample and aims to infer whether this observed subset was present in the training set. To address this problem, we propose MRAD (Memory-guided Reconstruction and Anomaly Detection), a two-stage attack framework that works in both white-box and black-box settings. In the first stage, MRAD leverages the latent memory of the target model to reconstruct the unknown features of the sample. We observe that when the known features are absent from the training set, the reconstructed sample deviates significantly from the true data distribution. Consequently, in the second stage, we use anomaly detection algorithms to measure the deviation between the reconstructed sample and the training data distribution, thereby determining whether the known features belong to a member of the training set. Empirical results demonstrate that MRAD is effective across various datasets, and maintains compatibility with off-the-shelf anomaly detection techniques. For example, on STL-10, our attack exceeds an AUC of around 0.75 even with 60% of the missing features.

cs.LG↗