论文检索

Theory · Learning Theory

Tomoya Wakayama, Taiji Suzuki

This paper develops a finite-sample statistical theory for in-context learning (ICL), analyzed within a meta-learning framework that accommodates mixtures of diverse task types. We leverage a Bayes risk identity that separates the total ICL risk into two orthogonal components: Bayes Gap and Posterior Variance. The Bayes Gap quantifies how well the trained model approximates the Bayes-optimal in-context predictor. For a uniform-attention Transformer, we derive a non-asymptotic upper bound on this gap, which explicitly clarifies the dependence on the number of pretraining prompts and their context length. The Posterior Variance is a model-independent risk representing the intrinsic task uncertainty. Our key finding is that this term is determined solely by the difficulty of the true underlying task, while the uncertainty arising from the task mixture vanishes exponentially fast with only a few in-context examples. Together, these results provide a unified view of ICL: the uniform-attention Transformer selects the optimal meta-algorithm during pretraining and rapidly converges to the optimal algorithm for the true task at test time.

Theory · Learning Theory

Tomoya Wakayama

Test-time training (TTT) adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts. Yet, its performance often suffers from instability and sensitivity to hyperparameters such as update steps and subspace. We explain this behavior through a decision-theoretic lens, treating TTT as implicit Bayesian inference in the kernel regime. Under a Gaussian process benchmark, we show that TTT reduces prediction error when updates are spectrally matched to the prompt's signal-to-noise ratio and aligned with query-relevant eigen-directions. This perspective underpins the following results: (1) we show when fixed update steps and subspaces fail under distribution shifts, motivating adaptive strategies; (2) we prove that selecting update steps via prompt evidence admits a PAC-Bayes guarantee against overfitting; and (3) we characterize the Bayes-optimal update subspace under a linear-Gaussian correction model, yielding a scoring rule for selecting Transformer blocks and heads. Our theory helps explain the empirical instability of TTT, taking a step toward principled guidance for when, how far, and which directions to adapt.

Applications · Computer Vision

Xuanhao Qi, Tom Luan, Yukang Zhang, Jinkai Zheng, su zhou, Shuwei Li, Lei Tan

Despite significant progress in multi-modal Re-Identification (ReID), existing methods tend to emphasize low-frequency cues. Consequently, they focus on attributes such as color, illumination, and coarse appearance, while overlooking mid- and high-frequency structures that encode geometric, textural, and identity-discriminative details. This imbalance leads to incomplete spectral representations and unstable cross-modal alignment. To overcome these limitations, we introduce FUSE, a frequency-domain framework that reformulates multi-modal ReID as a two-stage process of spectral disentanglement and energy alignment. The proposed Spectral Decomposition Module (SDM) adaptively partitions features into low, mid, and high-frequency subspaces, enabling hierarchical spectral modeling. The Cross-Modal Alignment Module (CAM) further enforces energy alignment and subspace complementarity across modalities via frequency-consistency regularization. In addition, FUSE incorporates learnable frequency modulation to enhance robustness under varying illumination and heterogeneous sensor conditions. Extensive experiments on RGBNT201, RGBNT100, and MSVR310 show that FUSE achieves 9.1% mAP and 9.5% Rank-1 improvements, establishing an interpretable frequency-domain paradigm for multi-modal representation learning.

Applications · Computer Vision

Yan Song, Zhihao Li, Chenglong Li, Li He, Yan Wang, Wenqiang Zhang

Active 3D reconstruction relies on active view selection to maximize reconstruction fidelity under limited capture budgets. However, most existing methods rely on surrogate signals—such as parameter uncertainty or geometric heuristics—which are often misaligned with the ultimate goal: the fidelity of rendered predictions. We propose GO-PRE, a goal-oriented next-best-view selection framework that explicitly targets information gain in the prediction space. Specifically, we formulate the objective as maximizing the reduction of the average marginal predictive entropy over a user-specified target view manifold. GO-PRE supports interactive goal specification and yields an efficient acquisition rule that enables real-time computation of information gain. Extensive experiments across benchmarks demonstrate that GO-PRE consistently improves active reconstruction performance and provides more reliable uncertainty quantification compared to state-of-the-art methods.

Deep Learning · Generative Models and Autoencoders

Junhyuk So, Hyunho Kook, Chaeyeon Jang, Eunhyeok Park

Autoregressive (AR) modeling has recently emerged as a promising new paradigm in visual generation, but its practical adoption is severely constrained by the slow inference speed of per-token generation, which often requires thousands of steps to produce a single sample. While several Speculative Decoding (SD)-based methods have been proposed to solve this problem by generating multiple tokens in a single forward step, they suffer from limited speedup, degraded quality, or require the training of a draft model. To solve these problems, we propose a new training-free, lossless SD framework, Speculative Coupled Decoding (SCD), by extending the recently proposed Speculative Jacobi Decoding (SJD). While SJD shows strong potential for accelerating AR generation by combining Jacobi iteration and SD, we found that its acceptance rate is still significantly limited due to the instability arising from the independent sampling process used during draft token generation. To overcome this, we introduce an information-theoretic approach, Coupling, which stabilizes the drafting trajectory of SJD by maximizing the probability of sampling identical draft tokens across consecutive iterations, significantly enhancing the acceptance rate while preserving its lossless property. Remarkably, this method requires only a single-line modification to the existing algorithm with almost zero overhead, yet achieves substantial performance gains, delivering up to a 4.2× speedup in image generation and 13.6× speedup in video generation compared to standard AR decoding, without any degradation or the need for additional training.

Reinforcement Learning · Multi-agent

Shiyang Li, Zijian Zhang, Winson Chen, Yuebo Luo, Mingyi Hong, Caiwen Ding

Modern machine learning (ML) workloads increasingly rely on GPUs, yet achieving high end-to-end performance remains challenging due to dependencies on both GPU kernel efficiency and host-side settings. Although LLM-based methods show promise on automated GPU kernel generation, prior works mainly focus on single-kernel optimization and do not extend to end-to-end programs, hindering practical deployment. To address the challenge, in this work, we propose \textsc{StitchCUDA}, a multi-agent framework for end-to-end GPU program generation, with three specialized agents: a \textit{Planner} to orchestrate whole system design, a \textit{Coder} dedicated to implementing it step-by-step, and a \textit{Verifier} for correctness check and performance profiling using Nsys/NCU. To fundamentally improve the \textit{Coder}'s ability in end-to-end GPU programming, \textsc{StitchCUDA} integrates rubric-based agentic reinforcement learning over two atomic skills, task-to-code generation and feedback-driven code optimization, with combined rubric reward and rule-based reward from real executions. Therefore, the \textit{Coder} learns how to implement advanced CUDA programming techniques (e.g., custom kernel fusion, cublas epilogue), and we also effectively prevent \textit{Coder}'s reward hacking (e.g., just copy PyTorch code or hardcoding output) during benchmarking. Experiments on KernelBench show that \textsc{StitchCUDA} achieves nearly 100\% success rate on end-to-end GPU programming tasks, with 1.72$\times$ better speedup over the multi-agent baseline and 2.73$\times$ than the RL model baselines.

Applications · Computer Vision

Yu Li, Zhengran Shen, Yachun Mi, Puchao Zhou, Shaohui Liu

Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contrastive pretraining of CLIP inherently prioritizes semantic invariance, which often suppresses subtle perceptual signals, a phenomenon we term perceptual submergence. Furthermore, standard preprocessing techniques (e.g., cropping and interpolation) further exacerbate the loss of critical high-frequency quality cues. In this paper, we propose the Cross-modal Perception Alignment Adapter (CMPA), a manifold-aware framework designed to disentangle perceptual distortions from dominant semantics. CMPA introduces a Perception-Sensitive Feature Extractor (PFE) that projects CLIP features into a compact, low-dimensional subspace, explicitly magnifying distortion-induced off-manifold deviations. Subsequently, a Cross-Modal Perception Alignment Injector (PAI) aligns these features with quality-aware text anchors and re-injects them into the backbone. To ensure input fidelity, we also devise a Residual-enhanced Perceptual Downscaling strategy that adaptively compensates for resolution-induced information loss using Just Noticeable Difference (JND) guided frequency re-injection. Extensive evaluations on several benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, effectively recovering the perceptual signals submerged in semantic-dense representations.

Applications · Neuroscience, Cognitive Science

Haoyu Wang, Wei Dai, Jialun Ma, Jiawei Zhang, Jinqi Liu, Mingchen Jiang, Mingqing Xiao, Yansen Wang, Dongqi Han, Dongsheng Li 等

Lateral connections (LCs) are ubiquitous in the cortical circuits. While modern deep learning architectures have rich intralayer interactions (e.g., convolutional mixing, normalization, or attention) to support feature selectivity and contextual modulation, explicit excitatory and inhibitory (E-I) LCs remain underexplored and unjustified additions for encoding models in both deep learning and neuroscience. In this work, we analyze and train stabilized supralinear networks (SSNs) with sufficiently strong recurrent excitation and feedback inhibition, using local unsupervised plasticity rules under natural image stimulation. We demonstrate that these LCs support a transition between dynamical regimes under different input conditions. During the transition, the network shifts from employing population coding to sparse coding balancing cost and performance: population coding extracts robust features from low-contrast or noisy inputs by recruiting more neurons while sparse coding encodes high-contrast, proper inputs efficiently with minimal cost. These results are then compared against sparse coding and ICA-based models. Our findings frame explicit E-I recurrent neural networks through the lens of dynamic coding strategies and provide insights into designing more adaptive and robust systems with a concrete example in vision.

Applications · Chemistry, Physics, and Earth Sciences

Natan Kaminsky, Daniel Freedman, Kira Radinsky

Physics-informed neural networks (PINNs) can be unreliable on PDEs with oscillatory, multiscale, stiff, or long-time solutions, and these difficulties worsen in high dimensions where collocation-based training yields large numerical integration error and high-variance gradients. We propose Low-Rank Fourier Sums (LoRFS), representing the solution as a low-rank sum of separable Fourier expansions (products of one-dimensional Fourier series across coordinates). This makes high-frequency structure explicit and enables closed-form evaluation of common physics-based objectives and their gradients (e.g., $L^2$ residual and variational losses), replacing sampling-based collocation estimates with analytic loss evaluation and eliminating sampling noise. We further provide theoretical results that clarify why LoRFS is particularly well suited to high-dimensional regimes. Across canonical PINN failure-mode benchmarks and their high-dimensional extensions, LoRFS consistently outperforms strong PINN baselines and remains stable in regimes where competing methods degrade.

Deep Learning · Large Language Models

Yilang Zhang, Xiaodong Yang, Yiwei Cai, Georgios B. Giannakis

As large language models (LLMs) continue to scale in size, the computational overhead has become a major bottleneck for task-specific fine-tuning. While low-rank adaptation (LoRA) effectively curtails this cost by confining the weight updates to a low-dimensional subspace, such a restriction can hinder effectiveness and slow convergence. This contribution deals with these limitations by accumulating progressively a high-rank weight update from consecutive low-rank increments. Specifically, the per update optimal low-rank matrix is identified to minimize the loss function and closely approximate full fine-tuning. To endow efficient and seamless optimization without restarting, this optimal choice is formed by appropriately scaling the columns of the original low-rank matrix. Rigorous performance guarantees reveal that the optimal scaling can be found analytically. Extensive numerical tests with popular LLMs scaling up to 12 billion parameters demonstrate a consistent performance gain and fast convergence relative to state-of-the-art LoRA variants on diverse tasks including natural language understanding, commonsense reasoning, and mathematical problem solving.

Deep Learning · Algorithms

Mingqing Xiao, Yansen Wang, Dongqi Han, Caihua Shan, Dongsheng Li

Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized to support flexible coordination such as feature binding. By contrast, most deep learning architectures represent and propagate information through activation values, neglecting the joint dynamics of rate and phase. In this work, we introduce Kuramoto oscillatory Phase Encoding (KoPE) as an additional, evolving phase state to Vision Transformers, incorporating a neuro-inspired synchronization mechanism to advance learning efficiency. We show that KoPE can improve training, parameter, and data efficiency of vision models through synchronization-enhanced structure learning. Moreover, KoPE benefits tasks requiring structured understanding, including semantic and panoptic segmentation, representation alignment with language, and few-shot abstract visual reasoning (ARC-AGI). Theoretical analysis and empirical verification further suggest that KoPE can accelerate attention concentration for learning efficiency. These results indicate that synchronization can serve as a scalable, neuro-inspired mechanism for advancing state-of-the-art neural network models.

Applications · Computer Vision

Wei Zhang, Chen Jia, Xu Cheng, Fan Shi, Hui Liu, Shengyong Chen

Pixel-level semantic segmentation of 4D light field (LF) data remains a considerable challenge, primarily due to the conflict between modeling complex spatial-angular dependencies and maintaining linear computational efficiency. Current linear models like VRWKV offer scalability but often fail to capture intrinsic geometric structures, leading to the structural collapse of Epipolar Plane Image (EPI) cues. To overcome these limitations, we propose E²I-VRWKV, an EPI-Enhanced and Interaction-aware network that generates high-quality segmentation maps by embedding explicit geometric priors into a linear-complexity backbone. Specifically, we introduce the Light Field Epipolar-Aware Cross-Modal Attention (LF-ECMA) block. The key innovation lies in the integration of an EPI Geometric Prior Generator, which explicitly extracts disparity-sensitive biases to enforce geometric consistency, and a Geometric-Context Gating (GC-Gate) mechanism. This mechanism functions as a geometrically modulated aperture to dynamically calibrate the fusion of spatial and angular manifolds. Experiments on the UrbanLF benchmark demonstrate that our method outperforms other state-of-the-art (SOTA) methods, achieving 86.55% mIoU on UrbanLF-Real while maintaining a superior balance between accuracy and linear efficiency.

Applications · Computer Vision

Xiaojing Wei, Ting Zhang, Wei He, Jingdong Wang, Hua Huang

High-quality geometric diagram generation presents both a challenge and an opportunity: it demands strict spatial accuracy while offering well-defined constraints to guide generation. Inspired by recent advances in geometry problem solving that employ formal languages and symbolic solvers for enhanced correctness and interpretability, we propose GeoLoom, a novel framework for text-to-diagram generation in geometric domains. GeoLoom comprises two core components: an autoformalization module that translates natural language into a specifically designed generation-oriented formal language GeoLingua, and a coordinate solver that maps formal constraints to precise coordinates using the efficient Monte Carlo optimization. To support this framework, we introduce GeoNF, a dataset aligning natural language geometric descriptions with formal GeoLingua descriptions. We further propose a constraint-based evaluation metric that quantifies structural deviation, offering mathematically grounded supervision for iterative refinement. Empirical results demonstrate that GeoLoom significantly outperforms state-of-the-art baselines in structural fidelity, providing a principled foundation for interpretable and scalable diagram generation.

Applications · Computer Vision

Zijie Wu, Na Zhao

Outdoor LiDAR generation has shown strong potential for autonomous driving and large-scale 3D perception. However, existing approaches remain computationally intensive and primarily static, lacking explicit modeling of temporal dynamics. This limitation weakens spatiotemporal coherence and reduces the realism of 4D LiDAR generation. We propose a hierarchical recoupling generation framework that explicitly disentangles and reconstructs large-scale geometry and motion within a unified hierarchical structure. First, we design a multi-resolution feature scaffold that predicts time-correlated unsigned distance fields and spatial gradients, enabling hierarchical decomposition of 4D dynamics into static and motion-varying components. Next, to achieve compact yet expressive modeling, we introduce a neural contourlet representation that prunes redundant scaffolds into minimal directional bases, efficiently capturing essential geometric and motion cues. Finally, we progressively re-couple these hierarchical components to generate realistic and temporally coherent 4D LiDAR data. Extensive experiments demonstrate that our method outperforms baselines in both quality and consistency, achieving 3.3\%, 25.0\%, 17.8\% improvements in FRD, MMD, and JSD, respectively, over the strong competitors, LiDMs and RangeLDM.

Applications · Computer Vision

Haifeng Zhao, Wenbo Zhao, Xuemei Luo, Lei-Lei Ma, Dengdi Sun

Scene Graph Generation (SGG) paradigms predominantly model relationships as static, unidirectional mappings ($s \to o$), effectively treating objects as passive recipients of actions. This formulation suffers from an inherent \textit{unidirectional bias}, violating the physical reality that visual interactions are intrinsically reciprocal. Consequently, existing models often fail to maintain logical self-consistency when the reasoning anchor shifts from the subject to the object. To rectify this cognitive deficiency, we establish the Mutual-Perspective Inverse Relations (MPIR) principle, positing that a robust visual representation must satisfy logical consistency across dual perspectives. Guided by this principle, we propose the \textbf{Reciprocal Perspective Calibration (RPC)} framework, a model-agnostic framework that operationalizes MPIR via a novel Adaptive Inverse-Relation Augmentation (AIRA) strategy. Furthermore, we introduce Hypernym-Guided Prompts (HGP) to bridge the gap between semantic context and computational efficiency in vision-language models, enabling precise modeling of inverse relations. Extensive experiments demonstrate that RPC not only achieves competitive performance on standard benchmarks but also significantly enhances the model's capability to understand inverse relations, as verified by a new inverse consistency evaluation protocol, demonstrating the cognitive robustness of our method.

Applications · Computer Vision

Yifan Gao, Lu Zou, Zhangjin Huang, Guoping Wang

Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. However, pronounced geometric heterogeneity across categories entangles incompatible optimization signals in shared modules, resulting in gradient conflicts and negative transfer during training. To address this challenge, we first introduce gradient-based diagnostics to quantify module-level cross-category contention. Building on results of diagnostics, we propose DecomPose, a difficulty-aware decomposition framework that mitigates optimization contention via: (1) difficulty-aware gradient decoupling, which groups categories using a data-driven difficulty proxy and routes each instance to a group-specific correspondence branch to isolate incompatible updates; and (2) stability-driven asymmetric branching, which assigns higher-capacity branches to structurally simple categories as stable optimization anchors while constraining complex categories with lightweight branches to suppress noisy updates and alleviate negative transfer. Extensive experiments on REAL275, CAMERA25, and HouseCat6D demonstrate that DecomPose effectively reduces cross-category optimization contention and achieves state-of-the-art performance.

Applications · Chemistry, Physics, and Earth Sciences

Xudong Ling, Lichaorong, Huang Tianxi, Qian Dong, Guiduo Duan

Short-term precipitation nowcasting is inherently under-constrained due to limited historical observation windows: identical observations can lead to multiple plausible future trajectories, especially for extreme events. Existing generative methods rely solely on visual features and lack explicit constraints on precipitation motion semantics, resulting in ambiguous dynamics, blurred details, and unstable predictions. We propose LangPrecip, the first language-guided precipitation nowcasting framework, and contribute LangPrecip-160K, a large-scale radar-text paired dataset with 160K annotated sequences. LangPrecip addresses the under-constrained challenge by leveraging natural-language motion descriptions as explicit semantic constraints to reduce motion ambiguity and introducing a dual-path wavelet consistency unfolding decoder that enforces physical data fidelity during latent-to-pixel reconstruction. By reformulating nowcasting as semantically constrained trajectory generation under the Rectified Flow paradigm with model-based decoder optimization, LangPrecip produces sharper and more physically consistent forecasts. Experiments on Swedish and MRMS benchmarks demonstrate substantial improvements over state-of-the-art vision-only methods, achieving over 60\% and 19\% relative gains in heavy-rainfall CSI at 80-minute lead time with enhanced spatial detail preservation.

Deep Learning · Generative Models and Autoencoders

Eitan Kosman, Gabriele Serussi, Chaim Baskin

Modality translation is inherently under-constrained, as multiple cross-modal mappings may yield the same marginals. Recent work has shown that diffusion bridges are effective for this task. However, most existing approaches rely on fully paired datasets, thereby imposing a single data-driven constraint. We propose a diffusion-bridge framework that characterizes the space of admissible solutions and restricts it via alignment constraints, treating paired supervision as an optional heuristic rather than a prerequisite. We validate our method on synthetic and real modality translation benchmarks across unpaired, semi-paired, and paired regimes, showing consistent performance across supervision levels. Notably, it achieves near fully-paired quality with a substantial relaxation in pairing requirements, and remaining applicable in the unpaired regime. These results highlight diffusion bridges as a flexible foundation for modality translation beyond fully paired data.

Deep Learning · Large Language Models

Maxx Richard Rahman, Mostafa Hammouda, Wolfgang Maass

Large Language Models have shown strong generalization across natural language tasks but remain underexplored for longitudinal clinical profiles. In sports anti-doping, biological profiles are analyzed to support early detection of prohibited substance use and identification of anomalous biological patterns, both of which require joint modeling of temporal dynamics and metabolic relationships. We propose STT-LLM, a structural-temporal tokenization framework that adapts LLMs to longitudinal clinical analysis without modifying their backbone architectures. STT-LLM constructs biologically grounded structural-temporal embeddings and transforms them into LLM-compatible tokens via specialized tokenizers that explicitly encode pathway structure and temporal evolution. We evaluate STT-LLM on real-world longitudinal datasets from athletes, showing consistent improvements over native LLM tokenization strategies in sequence prediction and anomaly detection. In addition, we present a case study where STT-LLM provides contextual reasoning that aligns more closely with expert assessments compared to baseline models. These results highlight tokenization as a key bottleneck and opportunity for adapting LLMs to clinical data.

Applications · Health / Medicine

Qi Chen, Shuhan Ding, Yu Gu, Nan Liu, Jiang Bian, Alan Yuille, Zongwei Zhou, Jingjing Fu

Variational autoencoders (VAEs) compress high resolution CT volumes into compact latents while preserving clinically relevant structure. However, training CT-specific VAEs from scratch or heavily fine-tuning them incurs substantial computational and engineering cost, and often degrades under heterogeneous scanners, protocols, and diseases. This paper makes a progressive stride toward training-free medical VAEs by leveraging a critical observation: a single Foundation VAE, pretrained at scale on natural images and videos, can serve as a unified interface for CT Reconstruction, Augmentation, and Generation. With both encoder and decoder frozen, the Foundation VAE reconstructs CT volumes with preserved anatomy while suppressing acquisition noise; training segmentation models on these reconstructions improves surface accuracy by 3.9\% NSD on average for pancreatic tumor and lung tumor. Within the same Foundation VAE latent space, a conditional latent diffusion model achieves 3.9\% lower average FVD with 36.2\% higher CT CLIP score, and improves multi-disease generation faithfulness across 18 types by 2.76\% AUC. These results demonstrate Foundation VAEs as a practical interface for scalable CT representation reuse and faithful CT generation.