论文检索

Deep Learning · Generative Models and Autoencoders

Hao Fu, Tianyu Su, Meng Liu, Chenfang Yang, Tian Gan

Diffusion models have shown impressive capabilities in text-to-image synthesis, but multi-concept personalized generation remains challenging, particularly in aligning multiple reference concepts while preserving fidelity. In this work, we propose a novel framework that addresses this challenge with a two-stage Sketch-to-Rendering process, utilizing Dual Optimal Transport (OT) for structural alignment and texture injection. Our approach consists of two key components: Structural Guidance via OT: Ensures shape alignment by using mass-preserving OT for spatial consistency, and Texture Injection via Geometry-Guided OT: Leverages low-frequency structure alignment to inject high-frequency texture details via OT-based residual transfer, preserving texture fidelity without distorting structure. Extensive experiments demonstrate that our method significantly enhances both conceptual fidelity and visual quality in multi-concept generation. Ablation studies further confirm the effectiveness of the proposed optimal transport guidance and the decoupling of structure and texture during the generation process.

Deep Learning · Theory

Konstantin Nikolaou, Jonas Scheunemann, Sven Krippendorf, Samuel Tovey, Christian Holm

Neural scaling laws describe predictable power-law relationships between model size, dataset size, compute cost, and performance. While these laws are applied to improve the performance of modern foundation models, the mechanisms underpinning them are less understood, in part due to the absence of scalable analysis tools. To this end, we introduce a framework for efficiently measuring the alignment between the empirical neural tangent kernel (eNTK) and loss residuals. Applying this framework to scaling experiments reveals a consistent pattern: larger and better-performing models exhibit *lower* kernel alignment throughout training. We interpret this *unalignment* through the lens of *spectral reach*: the capacity of a model to learn from progressively weaker spectral modes in its eNTK. This interpretation allows us to explain why larger models achieve lower losses: they sustain learning on weaker signals that smaller models cannot access. We further demonstrate that feature learning improves spectral reach and provide a mechanistic explanation of how this occurs, suggesting practical avenues for performance improvement.

Deep Learning · Generative Models and Autoencoders

Tong Yang, Moonkyung Ryu, Chih-wei Hsu, Guy Tennenholtz, Yuejie Chi, Craig Boutilier, Bo Dai

Controllable diffusion generation often relies on various heuristics that are seemingly disconnected without a unified understanding. We bridge this gap with Diffusion Controller (DiffCon), a unified control-theoretic view that casts reverse diffusion sampling as state-only stochastic control within (generalized) linearly-solvable Markov Decision Processes (LS-MDPs). Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost. From the resulting optimality conditions, we derive practical reinforcement learning methods for diffusion fine-tuning: (i) $f$-divergence-regularized policy-gradient updates, including a PPO-style rule, and (ii) a regularizer-determined reward-weighted regression objective with a minimizer-preservation guarantee under the Kullback–Leibler (KL) divergence. The LS-MDP framework further implies a principled model form: the optimal score decomposes into a fixed pretrained baseline plus a lightweight control correction, motivating a side-network parameterization conditioned on exposed intermediate denoising outputs, enabling effective \emph{gray-box adaptation} with a frozen backbone. Experiments on Stable Diffusion v1.4 across supervised and reward-driven finetuning show consistent gains in preference-alignment win rates and improved quality–efficiency trade-offs versus gray-box baselines and even the parameter-efficient white-box adapter LoRA.

Deep Learning · Generative Models and Autoencoders

Jaeyeon Kim, Seunggeun Kim, Taekyun Lee, David Pan, Hyeji Kim, Sham Kakade, Sitan Chen

A natural desideratum for generative models is \emph{self-correction}--detecting and revising low-quality tokens at inference. While Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces, their capacity for self-correction remains poorly understood. Prior attempts to incorporate self-correction into MDMs either require overhauling MDM architectures/training or rely on imprecise proxies for token quality, limiting their applicability. Motivated by this, we introduce PRISM--Plug-in Remasking for Inference-time Self-correction of Masked Diffusions--a lightweight, model-agnostic approach that applies to any pretrained MDM. Theoretically, PRISM defines a self-correction loss that provably learns per-token quality scores, without RL or a verifier. These quality scores are computed in the same forward pass with MDM and used to detect low-quality tokens. Empirically, PRISM advances MDM inference across domains and scales: Sudoku; unconditional text (170M); and code with LLaDA (8B).

Reinforcement Learning · Deep RL

Haitong Ma, Ofir Nabati, Aviv Rosenberg, Bo Dai, Oran Lang, Craig Boutilier, Na Li, Shie Mannor, Lior Shani, Guy Tennenholtz

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these complex settings. Our key innovation is an efficient online training process that ensures stable and effective policy improvement. By leveraging policy mirror descent (PMD) to define an ideal, regularized target policy distribution, we frame the policy update as a distributional matching problem, training the expressive diffusion model to replicate this stable target. This decoupled approach stabilizes learning and significantly enhances training performance. Our method achieves state-of-the-art results and superior sample efficiency across a diverse set of challenging combinatorial benchmarks, including DNA sequence generation, RL with macro-actions, and multi-agent systems. Experiments demonstrate that our diffusion policies attain superior performance compared to other baselines. Crucially, our extensive empirical analysis reveals a key trade-off: FKL demonstrates superior sample efficiency and faster initial convergence, whereas RKL ensures greater training stability and higher asymptotic performance.

Optimization · Non-Convex

Shutong Ding, Yimiao Zhou, Ke Hu, Xi Yao, Junchi Yan, Xiaoying Tang, Ye Shi

Recent advances in diffusion models show promising potential to accelerate nonconvex problem solving by leveraging their multimodality. However, most existing diffusion-based optimization approaches rely on supervised learning and lack a mechanism to enforce constraint satisfaction, which is required in real-world applications. In that case, we investigate and theoretically analyze the inherent problem of supervised diffusion solvers and identify the distributional misalignment problem, i.e., the generated solution distribution often exhibits low probability mass on the feasible region. To resolve this issue, we propose DiOpt, a new diffusion-based learning framework for constrained nonconvex optimization, which effectively learns the mapping from noise to the constraint region. Specifically, this framework operates in two distinct phases: an initial warm-start phase, implemented via supervised learning, followed by a bootstrapping training phase. This dual-phase architecture is designed to iteratively refine solutions, thereby improving the objective function with high constraint satisfaction. Finally, we also employ a solution selection technique in inference for better optimality. Notably, DiOpt is the first successful integration of the diffusion solver in constrained nonconvex optimization. Evaluations on diverse nonconvex tasks demonstrate the superiority of DiOpt in both optimality and constraint satisfaction.

Reinforcement Learning · Deep RL

Youssef Mroueh

Group Relative Policy Optimization (GRPO) was introduced recently and used to train DeepSeek\textendash R1 for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean{+}variance calibration of these rewards induces a contrastive loss in which the contrastive samples are synthetic data drawn from the previous policy. While GRPO was originally paired with clipping to keep updates near the old policy, we analyze variants that differ in reward normalization (mean-only vs.\ mean{+}variance) and in how they regularize updates using KL divergence: either penalizing divergence from the previous model (\emph{mirror}), penalizing divergence from a fixed reference model $\pi_{\mathrm{ref}}$, or combining both forms of regularization. For each, the optimal policy $\pi_n$ admits an explicit form in terms of the binary reward and the first and second order statistics of the reward under $\pi_{n-1}$, as well as the policies $\pi_{n-1}$ and $\pi_{\mathrm{ref}}$. Iterating results in a sequence $\{\pi_n\}$ whose \emph{probability of success (PoS)} obeys a simple recurrence that converges to a fixed point determined by the reference PoS and the regularization strength. We further show that this fixed point exceeds the reference, demonstrating that GRPO amplifies the policy's probability of success.

Applications · Health / Medicine

Ana Sanchez Fernandez, Thomas Pinetz, Werner Zellinger, Günter Klambauer

Biomedical imaging data presents enormous potential for deep learning models to predict invaluable properties, such as diseases and drug effects. However, unavoidable alterations of the technical conditions cause *batch effects*: variations between groups of samples that are not due to any biological signal of interest. Batch effects greatly hinder the generalization abilities of deep learning models, preventing their practical use in the real world. Unsupervised Domain Adaptation (UDA) methods have been proposed to mitigate batch effects, but they usually assume that the data is comprised of only one source domain and one target domain, whereas biological datasets are comprised of multiple domains, both at training and at inference time. While Batch Normalization–based test-time and meta-learning adaptation methods offer a promising mechanism for domain alignment, we show that existing approaches exhibit degraded performance under the usual inference scenarios of small target batch sizes and label shift. We address these limitations by leveraging negative control samples, which are consistently present in every experimental batch in biological datasets, as stable context for adaptation. We propose CS-ARM-BN, a meta-learning BN adaptation method that uses controls both during training and inference to stabilize domain statistics. We perform a suite of experiments of Mechanism-Of-Action (MoA) classification, a crucial task for drug discovery, on the large JUMP-CP imaging dataset. Our experiments show that CS-ARM-BN substantially improves robustness to batch size and class distribution shifts, enabling practical use of deep learning models for biomedical images.

Deep Learning · Large Language Models

Yu Li, Lehui Li, Lin Chen, Qingmin Liao, Fengli Xu, Yong Li

In modern AI research, baseline and dataset selection is a high-stakes decision in experimental design. It operationalizes a research idea into a concrete evaluation protocol and largely determines the validity and comparability of empirical conclusions. However, making appropriate choices is increasingly difficult as baselines and datasets proliferate, while suitability is inherently context-dependent and rarely captured by baseline and dataset metadata. To address these challenges, we present \textbf{AgentExpt}, a comprehensive framework for baseline and dataset recommendation. We first curate a large-scale, high-quality knowledge base that links 108{,}825 accepted papers to their used baselines and datasets. Based on this resource, we design a \textit{collective perception-enhanced retriever} that represents each baseline or dataset by integrating first-person self-descriptions with third-person citation contexts, thereby effectively positioning them within the scholarly network. We further design a \textit{reasoning-augmented reranker} that encodes baseline-dataset interaction chains as a reasoning prior to fine-tune an LLM, producing refined rankings with interpretable justifications. Experiments show that our framework outperforms the strongest baseline, with average gains of +5.85\% in Recall@20 and +7.90\% in HitRate@10, and ablation studies confirm the effectiveness of our designed components. Overall, AgentExpt advances the efficient and reliable automation of experimental design. Our code is available at \url{https://anonymous.4open.science/r/Agentexpt-DD3E}.

Reinforcement Learning · Online

Shutong Ding, Zejia Zhong, Zhongyi Wang, Ke Hu, Bikang Pan, Jingya Wang, Ye Shi

Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representative branch focuses on the weighted-based policy optimization. This design enables better exploration capability of diffusion model, particularly at the beginning of training, but suffer from the low exploitation in Q-value information, resulting in a slow policy convergence. Another branch pay attention to gradient-based policy optimization, which sufficiently exploit the gradient of Q function yet tend to collapse into a unimodal policy with low diversity. To address this issue, we propose CGPO, \textbf{C}ritic-\textbf{G}uided diffusion \textbf{P}olicy \textbf{O}ptimization, which effectively balances exploration and exploitation with the training-free guidance technique integrated into the denoising process of diffusion policy. Concretely, CGPO steers action generation toward high-value regions defined by the critic network and uses the guided actions as regression objectives. In this manner, CGPO reduces the time required to obtain high-quality actions and improves final performance with better balance between exploration-exploitation tradeoff. We validate the effectiveness of CGPO on 5 MuJoCo locomotion tasks, and CGPO achieves state-of-the-art performance compared with existing diffusion-based RL methods. Notably, CGPO is the first success to incorporate diffusion policy into real-world RL, with its superior performance on Franka robot arm grasping tasks.

Lehui Li, Yuyao Wang, Jisheng Yan, Wei Zhang, Jinliang Deng, Haoliang Sun, Zhongyi Han, Yongshun Gong

Incorporating textual information into time-series forecasting holds promise for addressing event-driven non-stationarity; however, a fundamental modality gap hinders effective fusion: textual descriptions express temporal impacts implicitly and qualitatively, whereas forecasting models rely on explicit and quantitative signals. Through controlled semi-synthetic experiments, we show that existing methods over-attend to redundant tokens and struggle to reliably translate textual semantics into usable numerical cues. To bridge this gap, we propose \method{}, which introduces a Temporal Evolution Semantic Space as an intermediate bottleneck between modalities. This space consists of interpretable, numerically grounded temporal primitives—mean shift, volatility, shape, and lag—extracted from text by an LLM via structured prompting and filtered through confidence-aware gating. Experiments on four real-world datasets demonstrate up to a 29\% reduction in forecasting error compared to state-of-the-art uni-modal and multimodal baselines. The code is available at https://anonymous.4open.science/r/MMTSF.

Deep Learning · Large Language Models

Dharshan Kumaran, Arthur Conmy, Federico Barbero, Simon Osindero, Viorica Patraucean, Petar Veličković

Verbal confidence—prompting LLMs to state their confidence as a number or category—is widely used to extract uncertainty estimates from black-box models. However, how LLMs internally generate such scores remains unknown. We address two questions: first, when confidence is computed -- just-in-time when requested, or automatically during answer generation and cached for later retrieval; and second, what verbal confidence represents -- token log-probabilities, or a richer evaluation of answer quality? Focusing on Gemma 3 27B and Qwen 2.5 7B, we provide convergent evidence for cached retrieval. Activation steering, patching, noising, and swap experiments reveal that confidence representations emerge at answer-adjacent positions before appearing at the verbalization site. Attention blocking pinpoints the information flow: confidence is gathered from answer tokens, cached at the first post-answer position, then retrieved for output. Critically, linear probing and variance partitioning reveal that these cached representations explain substantial variance in verbal confidence beyond token log-probabilities, suggesting a richer answer-quality evaluation rather than a simple fluency readout. These findings demonstrate that verbal confidence reflects automatic, sophisticated self-evaluation—not post-hoc reconstruction—with implications for understanding metacognition in LLMs and improving calibration.

General Machine Learning · Representation Learning

Daniil Karzanov, Marcin Detyniecki

Deep neural networks for image classification often exhibit overconfidence on out-of-distribution (OOD) samples. To address this, we introduce Geometrically Constrained Outlier Synthesis (GCOS), a training-time regularization framework aimed at improving OOD robustness during inference. GCOS addresses a limitation of prior synthesis methods by generating virtual outliers in the hidden feature space that respect the learned manifold structure of in-distribution (ID) data. The synthesis proceeds in two stages: (i) a dominant-variance subspace extracted from the training features identifies geometrically informed, off-manifold directions; (ii) a conformally-inspired shell, defined by the empirical quantiles of a nonconformity score from a calibration set, adaptively controls the synthesis magnitude to produce boundary samples. The shell ensures that generated outliers are neither trivially detectable nor indistinguishable from in-distribution data, facilitating smoother learning of robust features. This is combined with a contrastive regularization objective that promotes separability of ID and OOD samples in a chosen score space, such as Mahalanobis or energy-based. Experiments demonstrate that GCOS outperforms state-of-the-art methods using standard energy-based inference on near-OOD benchmarks, defined as tasks where outliers share the same semantic domain as in-distribution data. As an exploratory extension, the framework naturally transitions to conformal OOD inference, which translates uncertainty scores into statistically valid p-values and enables thresholds with formal error guarantees, providing a pathway toward more predictable and reliable OOD detection.

Deep Learning · Large Language Models

Suizhi Huang, Mei Li, Han Yu, Xiaoxiao Li

Textual Gradient-style optimizers (TextGrad) enable gradient-like feedback propagation through compound AI systems. However, they do not work well for deep chains. The root cause of this limitation stems from the *Semantic Entanglement* problem in these extended workflows. In standard textual backpropagation, feedback signals mix local critiques with upstream contexts, leading to *Attribution Ambiguity*. To address this challenge, we propose TextResNet, a framework that reformulates the optimization process to achieve precise signal routing via four key innovations. Firstly, in the forward pass, it enforces Additive Semantic Deltas to preserve an Identity Highway for gradient flow. Secondly, in the backward pass, it introduces Semantic Gradient Decomposition via a Semantic Projector to disentangle feedback into causally independent subspaces. Thirdly, it implements Causal Routing, which routes projected signals to their specific components. Finally, it performs Density-Aware Optimization Scheduling to leverage the disentangled signals to dynamically allocate resources to key system bottlenecks. Our results show that TextResNet not only achieves superior performance compared to TextGrad, but also exhibits remarkable stability for agentic tasks in compound AI systems where baselines collapse. The code will be made public after the review.

Xiaoda Yang, Majun Zhang, Changhao Pan, Nick Huang, Yang Yuguang, fan zhuo, Pengfei Zhou, Jin Zhou, Sizhe Shan, Shan Yang 等

Unified audio--visual generation is rapidly gaining industrial and creative relevance, enabling applications in virtual production and interactive media. However, when moving from general audio--video synthesis to music–dance co-generation, the task becomes substantially harder: musical rhythm, phrasing, and accents must drive choreographic motion at fine temporal resolution, and such rhythmic coupling is not captured by unimodal metrics or generic audiovisual consistency scores used in current evaluation practice. We introduce TMD-Bench, a benchmark for text-driven music–dance co-generation that assesses systems across unimodal generation quality, instruction adherence, and cross-modal rhythmic alignment. The benchmark integrates computable physical metrics with perceptual multimodal judgments, and is supported by a curated rhythm-aligned music–dance dataset and a fine-grained Music Captioner for structured music semantics. TMD-Bench further reveals that (i) modern commercial audio--visual models (e.g., Veo 3, Sora 2) produce high-quality music and video, while rhythmic coupling remains less consistently optimized and leaves room for improvement, and (ii) our unified baseline RhyJAM trained on rhythm-aligned data achieves competitive beat-level synchronization while maintaining competitive unimodal fidelity. This presents prospects for building next-generation music–dance models that explicitly optimize rhythmic and kinetic coherence.

Applications · Computer Vision

Xiaoda Yang, Yuxiang Liu, Shenzhou Gao, Can Wang, Jingyang Xue, Lixin Yang, Yao Mu, Tao Jin, Shuicheng YAN, Zhimeng Zhang 等

Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for embodied, egocentric tasks. A major source of failure is their reliance on temporal priors learned from passive video data, which often leads to spatiotemporal hallucinations and poor generalization in dynamic environments. To address this, we present EgoTSR, a curriculum-based framework for learning task-oriented spatiotemporal reasoning. EgoTSR is built on the premise that embodied reasoning should evolve from explicit spatial understanding to internalized task-state assessment and finally to long-horizon planning. To support this paradigm, we construct EgoTSR-Data, a large-scale dataset comprising 46 million samples organized into three stages: Chain-of-Thought supervision for explicit reasoning, weakly supervised tagging for internalizing reasoning, and long-horizon sequences composed of orthogonal atomic subtasks. We further introduce a Reasoning-Enhanced Task Decomposition mechanism that explicitly models causal dependencies between actions and objects, enabling controllable planning from high-level task descriptions. To rigorously validate our approach, we establish a Dual-Level Evaluation Framework that covers both atomic spatial perception and logical planning. Extensive experiments demonstrate that EgoTSR effectively eliminates chronological biases, achieving 92.4% accuracy on long-horizon logical reasoning tasks while maintaining 88.2% fine-grained perceptual precision, significantly outperforming existing open-source and closed-source state-of-the-art models.

Applications · Chemistry, Physics, and Earth Sciences

Hongfei Wu, Lijun Wu, Guoqing Liu, Zhirong Liu, Bin Shao, Zun Wang

In this paper, we develop SE3Set, an SE(3) equivariant hypergraph neural network architecture tailored for advanced molecular representation learning. Hypergraphs are not merely an extension of traditional graphs; they are pivotal for modeling high-order relationships, a capability that conventional equivariant graph-based methods lack due to their inherent limitations in representing intricate many-body interactions. To achieve this, we first construct hypergraphs by proposing a new fragmentation method that considers both chemical and three-dimensional spatial information of the molecular system. We then design SE3Set, which incorporates equivariance into the hypergraph neural network. This ensures that the learned molecular representations are invariant to spatial transformations, thereby providing robustness essential for the accurate prediction of molecular properties. SE3Set has shown performance on par with state-of-the-art (SOTA) models for small molecule datasets like QM9 and MD17. It demonstrates outstanding performance on the MD22 dataset, achieving a remarkable ~20\% improvement in accuracy across all molecules. Furthermore, on the OE62 dataset, SE3Set outperforms all short-range models. We also conducted a detailed analysis of OE62, highlighting the prevalence of complex many-body interactions in large molecules. This exceptional performance of SE3Set across diverse molecular structures underscores its transformative potential in computational chemistry, offering a route to more accurate and physically nuanced modeling. The code of this work is available at https://github.com/Navantock/SE3Set.

Applications · Health / Medicine

Ivan Svatko, Maxime Sanchez, Ihab Bendidi, Gilles Cottrell, Auguste Genovesio

Representation learning has driven major advances in natural image analysis by enabling models to acquire high-level semantic features. In microscopy imaging, however, it remains unclear what current representation learning methods actually learn. In this work, we conduct a systematic study of representation learning for the two most widely used and broadly available microscopy data types, representing critical scales in biology: cell culture and tissue imaging. To this end, we introduce a set of simple yet revealing baselines on curated benchmarks, including untrained models and simple structural representations of cellular tissue. Our results show that, surprisingly, state-of-the-art methods perform comparably to these baselines. We further show that, in contrast to natural images, existing models fail to consistently acquire high-level, biologically meaningful features. Moreover, we demonstrate that commonly used benchmark metrics are insufficient to assess representation quality and often mask this limitation. In addition, we investigate how detailed comparisons with these benchmarks provide ways to interpret the strengths and weaknesses of models for further improvements. Together, our results suggest that progress in microscopy image representation learning requires not only stronger models, but also more diagnostic benchmarks that measure what is actually learned.

Deep Learning · Large Language Models

Ming Zhong, Xiang Zhou, Ting-Yun Chang, Qingze Wang, Nan Xu, Xiance Si, Dan Garrette, Shyam Upadhyay, Jeremiah Zhe Liu, Jiawei Han 等

Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their *vibe check*. *Vibe check* reflects human preference and goes beyond functionality: the solution should feel right, read cleanly, preserve intent, and remain correct. However, current code evaluation remains anchored to pass@k and captures only functional correctness, overlooking non-functional instructions that users routinely apply. In this paper, we hypothesize that instruction following is the missing piece underlying *vibe check* besides functional correctness. To quantify models' code instruction-following capabilities with measurable signals, we present **VeriCode**, a taxonomy of 30 verifiable code instructions together with deterministic verifiers. We use the taxonomy to augment established evaluation suites, resulting in **Vibe Checker**, a testbed to assess both instruction following and functional correctness. Evaluating 31 LLMs, we show that even the strongest models struggle to comply with multiple instructions and exhibit functional regression. Most importantly, *a composite score of functional correctness and instruction following correlates best with human preference*, with instruction following emerging as the primary differentiator among LLMs.

General Machine Learning · Methodology

Terry Tong, Yu Feng, Surbhi Goel, Dan Roth

Large language models can solve algorithmic problems either through direct natural language (NL) reasoning or by generating executable code delegated to an external solver. However, little progress has been made on **understanding why**. Comparing NL reasoning and solver-based pipelines directly is ill-posed: they differ simultaneously in representation space and execution mechanism. We introduce a three-route framework that makes this comparison tractable by introducing an intermediary step---code generation with LLM-based execution. This enables our empirical analysis, which shows a statistically significant gap supporting code $>$ NL by +28.9\% across 48 different algorithmic tasks and 6 models. A statistical analysis indicates that natural-language reasoning does not provide additional decision-relevant information beyond what is already captured by code representations. Consequently, replacing NL traces with code traces incurs minimal performance loss while enabling deterministic execution. A systematic comparison of LLM-based reasoning and external execution further shows that execution, rather than trace representation, is the primary performance bottleneck.