论文检索

Deep Learning · Generative Models and Autoencoders

Taekoan Yoo, Wonkyung Jung, Kyunghun Kim, Kyeongbo Kong

Text-to-Music diffusion models are increasingly used in real-world applications, yet deployment remains challenging: generations can collapse to limited patterns even with diverse initial noise and prompts, and inference-time diversity control often harms text alignment and fidelity by distorting key prompt cues established in early denoising. To address this, we propose Padding-Annealed Diffusion Sampling, which perturbs only a padding-indexed subspace while keeping non-padding conditioning fixed, enabling controlled exploration with reduced semantic drift. However, in a text-unaware VAE latent space, such exploration is less likely to stay within genre-faithful neighborhoods, limiting genre-consistent diversity. We therefore introduce Text-Aware Latent space that aligns local neighborhoods with text-implied genre structure, promoting genre-consistent diversity. Together, the two techniques form a unified pipeline that, compared to prior methods that perturb the full conditioning, achieves a better text alignment--diversity trade-off: at comparable text alignment, it delivers 15.4\% higher diversity with a relatively small fidelity drop, and further improves within-genre diversity by 71.6\%. Generated samples are available at https://pads-tal.github.io/PADS-TAL.io

Deep Learning · Generative Models and Autoencoders

Zongye Zhang, Yuzhuo Cui, Qingjie Liu, Yunhong Wang

Generalizing motion representation across diverse characters remains challenging due to significant topological variations in skeletal structures across datasets and species, which hinders the development of scalable generative models. To bridge this gap, we propose a Semantic-Aware Topology-Agnostic framework that learns a unified latent manifold shared by disparate species. Unlike methods relying on fixed hierarchies or rigid padding strategies, our approach leverages a semantic modulation mechanism to align functional joint correspondences, thereby decoupling motion from topology. This design enables the construction of a continuous, generative-friendly motion space from large-scale, unaligned raw BVH data. Experiments on human and animal datasets demonstrate that our framework achieves high-fidelity reconstruction and supports downstream text-to-motion tasks. Notably, the model unlocks emergent capabilities, enabling zero-shot cross-species retargeting without paired data.

General Machine Learning · Representation Learning

Katharina Friedl, Noémie Jaquier, Mika Liao, Danica Kragic

Embedding physical intuition into network architectures allows the learning of dynamics that enforce fundamental properties, such as energy conservation laws, thereby leading to physically-plausible predictions. Yet, scaling these models to intrinsically high-dimensional dynamical systems remains a significant challenge. This paper introduces Reduced-order Hamiltonian Neural Network (RO-HNN), a novel physics-inspired neural network that combines the conservation laws of Hamiltonian mechanics with the scalability of model order reduction. RO-HNN is built on two core components: a novel geometrically-constrained symplectic autoencoder that learns a low-dimensional, structure-preserving symplectic submanifold, and a geometric Hamiltonian neural network that models the dynamics on the submanifold. Our experiments demonstrate that RO-HNN provides physically-consistent, stable, and generalizable predictions of complex high-dimensional dynamics, thereby effectively extending the scope of Hamiltonian neural networks to high-dimensional physical systems.

Deep Learning · Foundation Models

Keondo Park, Younghoon Na, Yourim Choi, Hyunwoo Ryu, Hyun-Woo Shin, Hyung-Sin Kim

While the shift toward unified foundation models has revolutionized many deep learning domains, sleep medicine remains largely restricted to task-specific models that focus on localized micro-structure features. These approaches often neglect the rich, multi-modal context of Polysomnography (PSG) and fail to capture the global macro-structure of a full night's sleep. To address this, we introduce SleepMaMi, a Sleep Foundation Model engineered to master both hour-long sleep architectures and fine-grained signal morphologies. Our framework utilizes a hierarchical dual-encoder design: a Macro-Encoder to model full-night temporal dependencies and a Micro-Encoder to capture short-term characteristics from biosignals. Macro-Encoder is trained via Demographic-Guided Contrastive Learning, which aligns overnight sleep patterns with objective subject metadata, such as age and sex, to refine global representations. Micro-Encoder is optimized via a hybrid Masked Autoencoder (MAE) and multi-modal contrastive objective. Pre-trained on a massive corpus of >20,000 PSG recordings (15.8K hours), SleepMaMi outperforms existing foundation models across a diverse suite of downstream tasks, demonstrating superior generalizability and label-efficient adaptation for clinical sleep analysis.

Deep Learning · Generative Models and Autoencoders

Zexi Jia, Pengcheng Luo, Zhengyao Fang, Jinchao Zhang, Jie Zhou

Classifier-Free Guidance (CFG) serves as the de facto control mechanism for conditional diffusion, yet high guidance scales notoriously induce oversaturation, texture artifacts, and structural collapse. We attribute this failure to a geometric mismatch: standard CFG performs Euclidean extrapolation in ambient space, inadvertently driving sampling trajectories off the high-density data manifold. To resolve this, we present Manifold-Optimal Guidance (MOG), a framework that reformulates guidance as a local optimal control problem. MOG yields a closed-form, geometry-aware Riemannian update that corrects off-manifold drift without requiring retraining. Leveraging this perspective, we further introduce Auto-MOG, a dynamic energy-balancing schedule that adaptively calibrates guidance strength, effectively eliminating the need for manual hyperparameter tuning. Extensive validation demonstrates that MOG yields superior fidelity and alignment compared to baselines, with virtually no added computational overhead.

Deep Learning · Large Language Models

Alex McKenzie, Keenan Pepper, Stijn Servaes, Martin Leitgab, Murat Cubuktepe, Michael Vaiana, Diogo de Lucena, Judd Rosenblatt, Michael Graziano

Large language models can resist task-misaligned activation steering during inference, sometimes recovering mid-generation to produce improved responses even when steering remains active. We term this Endogenous Steering Resistance (ESR). Using sparse autoencoder (SAE) latents to steer model activations, we find that Llama-3.3-70B shows substantial ESR, while smaller models from the Llama-3 and Gemma-2 families exhibit the phenomenon less frequently. We identify 26 ``off-topic detector'' latents that predict ESR episodes in Llama-3.3-70B. Zero-ablating these latents reduces the multi-attempt rate by 25\%, providing causal evidence for dedicated internal consistency-checking circuits. We demonstrate that ESR can be deliberately enhanced through both prompting and training: meta-prompts instructing the model to self-monitor increase the multi-attempt rate by 5$\times$ for Llama-3.3-70B, and fine-tuning on self-correction examples successfully induces ESR-like behavior in smaller models. These findings have dual implications: ESR could protect against adversarial manipulation but might also interfere with beneficial safety interventions that rely on activation steering. Understanding and controlling these resistance mechanisms is important for developing transparent and controllable AI systems.

Deep Learning · Generative Models and Autoencoders

Jing Jia, Wei Yuan, Sifan Liu, Liyue Shen, Guanyang Wang

Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard approaches usually assume a high-fidelity model trained on data that closely match the unknown signal. In practice, one often must use a mismatched or low-fidelity diffusion prior. Surprisingly, these weak priors often perform nearly as well as full-strength, in-domain baselines. We study when and why inverse solvers are robust to weak diffusion priors. Through extensive experiments, we find that weak priors succeed when measurements are highly informative (e.g., many observed pixels), and we identify regimes where they fail. Our theory, based on Bayesian consistency, gives conditions under which high-dimensional measurements make the posterior concentrate near the true signal. These results provide a principled justification on when weak diffusion priors can be used reliably. Code is available at Code is available at https://anonymous.4open.science/r/weak-diffusion-priors-inverse-problem-1043.

Deep Learning · Generative Models and Autoencoders

Xuesong Zhang, Haifeng Sun, Qi Qi, Shengkuan Li, Yuhao Li, Tianyi Kou, Zirui Zhuang, Bo He, Jianxin Liao, Jingyu Wang

Diffusion models have achieved remarkable success in graph generation, but enforcing hard constraints on generated graphs remains challenging, limiting their deployment in constraint-critical applications. Existing approaches either fail to guarantee strict constraint satisfaction or are limited to narrow constraint types, lacking the flexibility to handle diverse constraint specifications. To address this challenge, we exploit the discrete structure of graphs, which allows hard constraints to be formulated as symbolic reasoning problems. Building on this insight, we propose NSPSG, a framework that integrates unconstrained diffusion models with discrete projection operators. NSPSG employ an SMT (Satisfiability Modulo Theories)-based projector to ensure that the generated graphs strictly satisfy constraints while remaining within the training data distribution. To further accelerate generation, we employ a supervised auto-regressive neural projector to approximate the symbolic reasoning process. Across heterogeneous constraints and various graph generation datasets, NSPSG achieves 99%-100% validity rates, demonstrating state-of-the-art performance. Notably, for a complex non-linear constraint, it improves data validity by up to 43% and reaches 99% validity while maintaining comparable generation efficiency.

Social Aspects · Accountability, Transparency, and Interpretability

David Chanin, Adrià Garriga-Alonso

Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts. A core SAE training hyperparameter is L0: how many SAE features should fire per token on average. Existing work compares SAE algorithms using sparsity-reconstruction tradeoff plots, implying L0 is a free parameter with no single correct value aside from its effect on reconstruction. In this work we study the effect of L0 on SAEs, and show that if L0 is not set correctly, the SAE fails to disentangle the underlying features of the LLM. If L0 is too low, the SAE will mix correlated features to improve reconstruction. If L0 is too high, the SAE finds degenerate solutions that also mix features. Further, we present a proxy metric that can help guide the search for the correct L0 for an SAE on a given training distribution. We show that our method finds the correct L0 in toy models and coincides with peak sparse probing performance in LLM SAEs. We find that most commonly used SAEs have an L0 that is too low. Our work shows that L0 must be set correctly to train SAEs with correct features.

Deep Learning · Generative Models and Autoencoders

Michael Hersche, Nicolas Menet, Ronan Tanios, Abbas Rahimi

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models, offering sub-linear generation latency and bidirectional capabilities that are particularly appealing for code generation and editing. Achieving sub-linear latency in discrete DLMs requires predicting multiple tokens in parallel. However, standard DLMs sample tokens independently from conditional marginal distributions, failing to capture the joint dependencies among concurrently generated tokens. As a result, they often lead to syntactic inconsistencies and break multi-token structures. In this work, we introduce CoDiLA (Coherent Diffusion with Local Autoregression), a method that reconciles parallel sampling with local dependency modeling. Rather than forcing the DLM to resolve fine-grained syntax, CoDiLA delegates local decoding to a small, auxiliary AR model operating on the diffusion latents. This design allows for parallel block generation while ensuring sequential validity within each block and maintaining core DLM capabilities, including bidirectional modeling across blocks. We demonstrate that using a highly compact auxiliary AR model (e.g., 0.6B parameters) effectively eliminates coherence artifacts, establishing a new Pareto frontier for accuracy and speed in code generation benchmarks.

Social Aspects · Accountability, Transparency, and Interpretability

Min Xue, Artur Andrzejak

Mechanistic interpretability of Transformer models commonly relies on training auxiliary proxy models, such as Sparse Autoencoders or Cross-Layer Transcoders. While effective, these post-hoc approaches introduce approximation bias and incur substantial computational overhead. We propose an alternative, training-free interpretability framework that directly exploits the Singular Value Decomposition (SVD) of weight matrices in Transformer MLP sublayers. By operating natively on model parameters, our method improves scalability while preserving fidelity to the original weights. We show that the projection matrices of MLP sublayers admit a natural decomposition into orthogonal, interpretable rank-1 subspaces, which we term **Detector-Effector Units** (DEUs). Within each unit, a singular vector functions as a detector of input patterns and modulates a coupled effector vector that encodes output semantics. Building on this structure, we introduce **Subspace Contribution Analysis** (SCA), a diagnostic method that quantifies the direct causal contribution of individual native subspaces to model predictions. Experiments across the GPT-2 family demonstrate that our framework, **Native Network Anatomy** (NaNA), identifies dominant functional pathways with orders-of-magnitude efficiency gains over training-based interpretability baselines, while maintaining weight fidelity. Our results suggest that SVD-based analyses provide a scalable and faithful alternative to learned proxy approaches for mechanistic interpretability.

Deep Learning · Generative Models and Autoencoders

Sol Yarkoni, Mahmood Sharif, Roi Livni

Recent advances in generative models, such as diffusion models, have raised concerns related to privacy, copyright infringement, and data curation. Prior work has shown that training data can be reconstructed from such models, but existing attacks typically rely on substantial computational resources, access to the training set, or carefully engineered prompts. In this work, we present a low-resource reconstruction attack that operates through seemingly benign prompts and requires little to no access to the training data. Our attack targets **template-memorized images (TMI)**, where recurring layouts and visual structures are memorized during training. We show that such memorization manifests under potentially realistic usage. This raises a possibility of unintentional reconstruction by naive users that don't carry explicit adversarial intent. For example, we observe that a simple prompt such as "blue Unisex T-Shirt" can reproduce visual content depicting a real individual. Beyond extraction, we observe novel phenomena occurring in TMI (e.g., interpolation), raising questions about the novelty of generated content and the effectiveness of established methods for detecting memorized content.

Deep Learning · Generative Models and Autoencoders

Minh-Quan Le, Gaurav Mittal, Cheng Zhao, Xianfeng GU, Samaras Dimitris, Mei Chen

Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training has emerged as a promising direction to improve the quality and semantic alignment of generated videos. However, recent methods either rely on large-scale human preference annotations or operate on misaligned embeddings from pre-trained vision-language models, leading to limited scalability or suboptimal supervision. We present $\texttt{PISCES}$, an annotation-free post-training algorithm that addresses these limitations via a novel Dual Optimal Transport (OT)-aligned Rewards module. To align reward signals with human judgment, $\texttt{PISCES}$ uses OT to bridge text and video embeddings at both distributional and discrete token levels, enabling reward supervision to fulfill two objectives: (i) a Distributional OT-aligned Quality Reward that captures overall visual quality and temporal coherence; and (ii) a Discrete Token-level OT-aligned Semantic Reward that enforces semantic, spatio-temporal correspondence between text and video tokens. To our knowledge, $\texttt{PISCES}$ is the first to improve annotation-free reward supervision in generative post-training through the lens of OT. Experiments on both short- and long-video generation show that $\texttt{PISCES}$ outperforms both annotation-based and annotation-free methods on VBench across Quality and Semantic scores, with human preference studies further validating its effectiveness. We show that the Dual OT-aligned Rewards module is compatible with multiple optimization paradigms, including direct backpropagation and reinforcement learning fine-tuning.

Social Aspects · Accountability, Transparency, and Interpretability

Hwiyeong Lee, Ingyu Bang, Uiji Hwang, Hyelim Lim, Taeuk Kim

While sparse autoencoders yield features easier to study than individual neurons, their reliable interpretation remains challenging. We propose Query Lens, which extends Logit Lens to provide more comprehensive and faithful interpretations of sparse features. By jointly considering encoder-side key features and decoder-side value features, we characterize both the inputs that activate a feature and the outputs it promotes. We also account for indirect, module-mediated effects that arise when the feature is processed by downstream modules, going beyond the direct effect captured by Logit Lens. In experiments, we find that Query Lens yields coherent token signatures for features that were previously uninterpretable under Logit Lens. Finally, we propose the Subspace Channel Hypothesis, suggesting that downstream modules read features through layer-specific subspaces.

Applications · Health / Medicine

Salma Ahmed, Emad Mohammed, Azam Bidgoli

Modern segmentation models achieve strong predictive performance but remain largely opaque, limiting our ability to diagnose failures, understand dataset shift, or intervene in a principled manner. We introduce $\textbf{Med-SegLens}$, a model-diffing framework that decomposes segmentation model activations into interpretable latent features using sparse autoencoders trained on SegFormer and U-Net. Through cross-architecture and cross-dataset latent alignment across healthy, adult, pediatric, and sub-Saharan African glioma cohorts, we identify a stable backbone of shared representations, while dataset shift is driven by differential reliance on population-specific latents. We show that these latents act as causal bottlenecks for segmentation failures, and that targeted latent-level interventions can correct errors and improve cross-dataset adaption without retraining, recovering performance in 70% of failure cases and improving Dice score from 39.4% to 74.2%. Our results demonstrate that latent-level model diffing provides a practical and mechanistic tool for diagnosing failures and mitigating dataset shift in segmentation models.

Deep Learning · Generative Models and Autoencoders

Zhiyuan Ouyang, Simei Huang, Zuokai Wen, Xiangyun Zhang, Junchi Yan

A probability distribution $\mathbb{P}$ is a measure on a $\sigma$-algebra, assigning mass to sets rather than points. This poses a challenge for the training of neural networks, which often struggle to reconstruct the global topology of continuous manifolds from sparse samples. We mitigate this issue by innovatively transforming $\mathbb{P}$ into a continuous function via spectral methods, providing theoretical guarantees for the convergence of the learned distribution to the true distribution. Specifically, we introduce a network, PriSpecNet, with a single-function evaluation (1-NFE) Pseudoinverse Lévy Inversion (PiLI) solver that regards generation as a fast analytical problem, eliminating the need for iterative numerical integration. By reformulating the generation in the spectral domain, we bypass the computationally expensive sampling trajectory while maintaining full compatibility with the stochastic interpolants. We test our PriSpecNet in two applications. For time series, it unifies generation and forecasting, outperforming state-of-the-art (SOTA) baselines with Context-FID reductions of 50.0\%, 41.5\%, 80.6\%, and 63.1\% on Sines, Solar, ETTh, and Stock benchmarks, respectively, also decreasing forecasting MSE by 29.8\% on Solar and 23.8\% on Stock. For vision on ImageNet $256 \times 256$, 1-NFE PiLI achieves a competitive FID of **1.66** using only **26** Gflops, representing a **170** $\times$ reduction in total Gflops compared to the 4,436 Gflops required by the advanced 25-NFE DPM-Solver++.

Deep Learning · Generative Models and Autoencoders

Lunjie Zhu, Yushi Huang, Xingtong Ge, Yufei Xue, Zhening Liu, Yumeng Zhang, Zehong Lin, Jun Zhang

Latent diffusion models have enabled high-quality video synthesis, yet their inference remains costly and time-consuming. As diffusion transformers become increasingly efficient, the latency bottleneck inevitably shifts to VAE decoders. To reduce their latency while maintaining quality, we propose a universal acceleration framework for VAE decoders that preserves full alignment with the original latent distribution. Specifically, we propose (1) an *independence-aware channel pruning* method to effectively mitigate severe channel redundancy, and (2) a *stage-wise dominant operator optimization* strategy to address the high inference cost of the widely used causal 3D convolutions in VAE decoders. Based on these innovations, we construct a **Flash-VAED** family. Moreover, we design a *three-phase dynamic distillation* framework that efficiently transfers the capabilities of the original VAE decoder to Flash-VAED. Extensive experiments on Wan and LTX-Video VAE decoders demonstrate that our method outperforms baselines in both quality and speed, achieving approximately a **6$\times$ speedup** while maintaining the reconstruction performance up to **96.9%**. Notably, Flash-VAED accelerates the end-to-end generation pipeline by up to **36%** with negligible quality drops on VBench-2.0.

Deep Learning · Generative Models and Autoencoders

Ming Yang, Xin Zheng, Yi Li, YIZHEN ZHENG, Huan Yee Koh, Yanqing Guo, Xiaofeng Cao, Shirui Pan

Multi-objective protein design is essential for meeting the complex demands of synthetic biology. To adapt to shifting multi-functional targets without the prohibitive cost of retraining, test-time scaling has emerged as a flexible, training-free alternative. However, current test-time diffusion methods face critical challenges: i) ineffective learning from interaction history leading to repetitive design errors, ii) over-reliance on successful cases as the reward signal, and iii) difficulties in balancing multi-objective functional trade-offs . To address these limitations, we propose MoMST, a framework for Multi-objective protein design via Memory-aware Self-contrastive learning with Test-time scaling in diffusion models. At test time, we develop a memory bank to extract generalizable reasoning experience from historical iterations. Building on this powerful experience learner, we derive rich residue-level relative preference signals from both successful and failed cases via self-contrastive learning for guiding protein generation. To ensure balance among competing multi-objective functions, we present an inference-time Pareto alignment strategy to resolve objective conflicts. Evaluations on both single-objective and complex multi-objective tasks demonstrate that MoMST exhibits remarkable performance.

Deep Learning · Generative Models and Autoencoders

Yu-Yang Qian, Junda Su, Lanxiang Hu, Peiyuan Zhang, Zhijie Deng, Peng Zhao, Hao Zhang

Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently face an *accuracy-parallelism trade-off*. Despite increasing interest, existing methods typically focus on only one-side of the coin, targeting either efficiency or performance. To address this limitation, we propose d3LLM (*Pseudo-Distilled Diffusion Large Language Model*), striking a balance between accuracy and parallelism: (i) during training, we introduce *pseudo-trajectory distillation* to teach the model which tokens can be decoded confidently at early steps, thereby improving parallelism; (ii) during inference, we employ *entropy-based multi-block decoding* with a KV-cache refresh mechanism to achieve high parallelism while maintaining accuracy. To better evaluate dLLMs, we also introduce AUP (*Accuracy Under Parallelism*), a new metric that jointly measures accuracy and parallelism. Experiments demonstrate that our d3LLM achieves up to $10\times$ speedup over vanilla LLaDA/Dream, and up to $5\times$ speedup over the AR models (Qwen-2.5-7B) without much accuracy degradation.

Deep Learning · Generative Models and Autoencoders

Nicolas Dufour, Lucas Degeorge, Arijit Ghosh, Vicky Kalogeiton, David Picard

The default paradigm of post-training text-to-image generators includes post-hoc selection of generated images, and subsequent training with one reward model to align the generator to the reward, typically user preference. This discards informative data as well as optimizes only for a single reward, hence harming diversity, semantic fidelity and efficiency. Instead, we propose MIRO, a method that conditions the model on multiple rewards during training, thus letting the model learn user preferences directly. MIRO pre-training both improves the visual quality of the generated images and speeds up the training, achieving state of the art on the GenEval compositional benchmark and user-preference scores (PickAScore, ImageReward, HPSv2).