ICLR 2026 Papers

Lightweight 3D medical image segmentation remains constrained by a fundamental "efficiency / robustness conflict", particularly when processing complex anatomical structures and heterogeneous modalities. In this paper, we study how to redesign the framework based on the characteristics of high-dimensional 3D images, and explore data synergy to overcome the fragile representation of lightweight methods. Our approach, VeloxSeg, begins with a deployable and extensible dual-stream CNN-Transformer architecture composed of Paired Window Attention (PWA) and Johnson-Lindenstrauss lemma-guided convolution (JLC). For each 3D image, we invoke a "glance-and-focus" principle, where PWA rapidly retrieves multi-scale information, and JLC ensures robust local feature extraction with minimal parameters, significantly enhancing the model's ability to operate with low computational budget. Followed by an extension of the dual-stream architecture that incorporates modal interaction into the multi-scale image-retrieval process, VeloxSeg efficiently models heterogeneous modalities. Finally, Spatially Decoupled Knowledge Transfer (SDKT) via Gram matrices injects the texture prior extracted by a self-supervised network into the segmentation network, yielding stronger representations than baselines at no extra inference cost. Experimental results on multimodal benchmarks show that VeloxSeg achieves a 26\% Dice improvement, alongside increasing GPU throughput by 11x, CPU by 48x, and reducing training peak GPU memory usage by 1/20, inference by 1/24.

Standard Convolutional Neural Networks are notoriously sensitive to photometric variations, a critical flaw that data augmentation only partially mitigates without offering formal guarantees. We introduce the *Scale-Equivariant Shift-Invariant* (*SEqSI*) model, a novel architecture that achieves intensity scale equivariance and intensity shift invariance by design, enabling full invariance to global intensity affine transformations with appropriate post-processing. By strategically prepending a single shift-invariant layer to a scale-equivariant backbone, *SEqSI* provides these formal guarantees while remaining fully compatible with common components like ReLU. We benchmark *SEqSI* against *Standard*, *Scale-Equivariant* (*SEq*), and *Affine-Equivariant* (*AffEq*) models on 2D and 3D image-classification and object-localization tasks. Our experiments demonstrate that *SEqSI* architectural properties provide certified robustness to affine intensity transformations and enhances generalization across non-affine corruptions and domain shifts in challenging real-world applications like biological image analysis. This work establishes *SEqSI* as a practical and principled approach for building photometrically robust models without major trade-offs.

Diffusion models have achieved remarkable success in content generation but suffer from prohibitive computational costs due to iterative sampling. While recent feature caching methods tend to accelerate inference through temporal extrapolation, these methods still suffer from severe quality loss due to the failure in modeling the complex dynamics of feature evolution. To solve this problem, this paper presents HiCache (Hermite Polynomial-based Feature Cache), a training-free acceleration framework that fundamentally improves feature prediction by aligning mathematical tools with empirical properties. Our key insight is that feature derivative approximations in Diffusion Transformers exhibit multivariate Gaussian characteristics, motivating the use of Hermite polynomials, the potentially theoretically optimal basis for Gaussian-correlated processes. Besides, we introduce a dual-scaling mechanism that ensures numerical stability while preserving predictive accuracy, which is also effective when applied standalone to TaylorSeer. Extensive experiments demonstrate HiCache's superiority: achieving \$5.55\times\$ speedup on FLUX.1-dev while exceeding baseline quality, maintaining strong performance across text-to-image, video generation, and super-resolution tasks. Moreover, HiCache can be naturally added to the previous caching methods to enhance their performance, e.g., improving ClusCa from \$0.9480\$ to \$0.9840\$ in terms of image rewards. Our code is included in the supplementary material, and will be released on GitHub.

State-of-the-art machine learning often follows a two-stage process: $(i)$ pre-training on large, general-purpose datasets; $(ii)$ fine-tuning on task-specific data. In fine-tuning, selecting training examples that closely reflect the target distribution is crucial. However, it is often the case that only a few samples are available from the target distribution. Existing data selection methods treat these target samples as a validation set and estimate the effect of adding or removing a single sample from the training pool by performing inference on the validation set. We propose a simpler and faster alternative that inverts the usual role of train and validation: we perform inference on the training pool before and after fine-tuning on the validation set. We then select samples whose predictions change the most. Our key insight is that the training samples most affected by fine-tuning on a small validation set tend to be the most beneficial for reducing test loss on the target distribution. Experiments on instruction tuning and named entity recognition tasks show that, in most cases, our method achieves lower test log-loss than state-of-the-art approaches. We support our findings with theoretical analysis.

Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they are not exposed to the reasoning processes and intents that guide authors in crafting these documents. We hypothesize that enhancing a model's intent awareness can significantly improve the quality of generated long-form reports. We develop and employ structured, tag-based schemes to better elicit underlying implicit intents to write or cite. We demonstrate that these extracted intents enhance both zero-shot generation capabilities in LLMs and enable the creation of high-quality synthetic data for fine-tuning smaller models. Our experiments reveal improved performance across various challenging scientific report generation tasks, with an average improvement of +2.9 and +12.3 absolute points for large and small models over baselines, respectively. Furthermore, our analysis illuminates how intent awareness enhances model citation usage and substantially improves report readability.

Natural language processing (NLP) models often replicate or amplify social bias from training data, raising concerns about fairness. At the same time, their black-box nature makes it difficult for users to recognize biased predictions and for developers to effectively mitigate them. While some studies suggest that input-based explanations can help detect and mitigate bias, others question their reliability in ensuring fairness. Existing research on explainability in fair NLP has been predominantly qualitative, with limited large-scale quantitative analysis. In this work, we conduct the first systematic study of the relationship between explainability and fairness in hate speech detection, focusing on both encoder- and decoder-only models. We examine three key dimensions: (1) identifying biased predictions, (2) selecting fair models, and (3) mitigating bias during model training. Our findings show that input-based explanations can effectively detect biased predictions and serve as useful supervision for reducing bias during training, but they are unreliable for selecting fair models among candidates. Our code is available at https://github.com/Ewanwong/fairness_x_explainability.

Recent strides in multimodal large language models (MLLMs) have demonstrated significant progress in many reasoning tasks, but they still fail in Abstract Visual Reasoning (AVR) tasks. Our experimental findings indicate that the core bottleneck lies not only in the reasoning capabilities of MLLMs but more critically in their absence of fine-grained perception. To address this issue, we present VisuRiddles, a dedicated resource for AVR research. It consists of (i) a benchmark, collected from real-world data, for the systematic evaluation of MLLMs' AVR capabilities, and (ii) a synthesizer, which automatically generates AVR instances enriched with perceptual descriptions and reasoning chains, enabling supervised training and deeper investigation. Building on VisuRiddles, we propose a two-stage training paradigm that progressively enhances perceptual ability and strengthens reasoning, producing the Perception-Augmented Visual Reasoner (PAVR). Experiments demonstrate that PAVR unifies perception and reasoning, substantially outperforming both open-source and commercial MLLMs, thereby underscoring fine-grained perception as the primary bottleneck in AVR.

Category-Agnostic Pose Estimation (CAPE) localizes keypoints across diverse object categories with a single model, using one or few annotated support images. Recent works have shown that using a pose-graph (i.e., treating keypoints as nodes in a graph rather than isolated points) helps handle occlusions and break symmetry. However, these methods assume a given pose-graph with equal-weight edges, leading to suboptimal results. We introduce EdgeCape, a novel framework that overcomes these limitations by predicting the graph's edge weights in order to optimize localization. To further leverage structural (i.e., graph) priors, we propose integrating Markov Attention Bias, which modulates the self-attention interaction between nodes based on the number of hops between them. We show that this improves the model’s ability to capture global spatial dependencies. Evaluated on the MP-100 benchmark, which includes 100 categories and over 20K images, EdgeCape achieves state-of-the-art results in the 1-shot and 5-shot settings, significantly improving keypoint localization accuracy.

Noncontact exfiltration of electronic screen content poses a security challenge, with side-channel incursions as the principal vector. We introduce an optical projection side-channel paradigm that confronts two core instabilities: (i) the near-singular Jacobian spectrum of projection mapping breaches Hadamard stability, rendering inversion hypersensitive to perturbations; (ii) irreversible compression in light transport obliterates global semantic cues, magnifying reconstruction ambiguity. Exploiting passive speckle patterns formed by diffuse reflection, our Irradiance Robust Radiometric Inversion Network (IR$^4$Net) fuses a Physically Regularized Irradiance Approximation (PRIrr‑Approximation), which embeds the radiative transfer equation in a learnable optimizer, with a contour-to-detail cross-scale reconstruction mechanism that arrests noise propagation. Moreover, an Irreversibility Constrained Semantic Reprojection (ICSR) module reinstates lost global structure through context-driven semantic mapping. Evaluated across four scene categories, IR$^4$Net achieves fidelity beyond competing neural approaches while retaining resilience to illumination perturbations.

Lane-level navigation is critical for geographic information systems and navigation-based tasks, offering finer-grained guidance than road-level navigation by standard definition (SD) maps. However, it currently relies on expansive global HD maps that cannot adapt to dynamic road conditions. Recently, online perception (OP) maps have become research hotspots, providing real-time geometry as an alternative, but lack the global topology needed for navigation. To address these issues, Online Navigation Refinement (ONR), a new mission is introduced that refines SD-map-based road-level routes into accurate lane-level navigation by associating SD maps with OP maps. The map-to-map association to handle many-to-one lane-to-road mappings under two key challenges: (1) no public dataset provides lane-to-road correspondences; (2) severe misalignment from spatial fluctuations, semantic disparities, and OP map noise invalidates traditional map matching. For these challenges, We contribute: (1) Online map association dataset (OMA), the first ONR benchmark with 30K scenarios and 2.6M annotated lane vectors; (2) MAT, a transformer with path-aware attention to aligns topology despite spatial fluctuations and semantic disparities and spatial attention for integrates noisy OP features via global context; and (3) NR P-R, a metric evaluating geometric and semantic alignment. Experiments show that MAT outperforms existing methods at 34 ms latency, enabling low-cost and up-to-date lane-level navigation.

3D Gaussian Splatting (3DGS) has recently emerged as a powerful approach for novel view synthesis by reconstructing scenes as sets of Gaussian ellipsoids. Despite its success in scenarios with dense input images, 3DGS faces critical challenges in sparse view settings, often resulting in geometric inaccuracies, inconsistencies across views, and degraded rendering quality. In this paper, we uncover and address two key implicit biases of 3DGS reconstruction algorithm in sparse-view: (1) the model has a stronger demand for supervision signal toward regions of high curvature, and (2) the model is sensitive to the smoothness of the trajectory of the input views. To tackle these issues, we propose a novel framework that optimizes camera trajectories to maximize curvature coverage while enforcing smooth motion, and we further enhance the informativeness of data through a synthetic view generation process. Extensive experiments on Mip-NeRF 360, DTU, Blender, Tanks & Temples, and LLFF datasets show that our method substantially outperforms state-of-the-art solutions in sparse-view scenarios, both in rendering quality and geometric fidelity. Beyond these empirical gains, our investigation uncovers the subtle ways in which data representation and trajectory planning interact to shape 3DGS performance, offering deeper theoretical insights into the algorithm’s inherent biases.

Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While existing methods have made great strides, most of them operate at global level but overlook region-wise and even pixel-wise semantic correspondence. To address this, we propose **CoCoDiff**, a novel *training-free* and *low-cost* style transfer framework that leverages pretrained latent diffusion models to achieve fine-grained, semantically consistent stylization. We identify that correspondence cues within generative diffusion models are under-explored and that content consistency across semantically matched regions is often neglected. CoCoDiff introduces a pixel-wise semantic correspondence module that mines intermediate diffusion features to construct a dense alignment map between content and style images. Furthermore, a cycle-consistency module then enforces structural and perceptual alignment across iterations, yielding object and region level stylization that preserves geometry and detail. Despite requiring no additional training or supervision, CoCoDiff delivers state-of-the-art visual quality and strong quantitative results, outperforming methods that rely on extra training or annotations.

Audio editing plays a central role in VR/AR immersion, virtual conferencing, sound design, and other interactive media. However, recent generative audio editing models depend on template-like instruction formats and are restricted to mono-channel audio. These models fail to deal with declarative audio editing, where the user declares what the desired outcome should be, while leaving the details of editing operations to the system. We introduce SmartDJ, a novel framework for stereo audio editing that combines the reasoning capability of audio language models with the generative power of latent diffusion. Given a high-level instruction, SmartDJ decomposes it into a sequence of atomic edit operations, such as adding, removing, or spatially relocating events. These operations are then executed by a diffusion model trained to manipulate stereo audio. To support this, we design a data synthesis pipeline that produces paired examples of high-level instructions, atomic edit operations, and audios before and after each edit operation. Experiments demonstrate that SmartDJ achieves superior perceptual quality, spatial realism, and semantic alignment compared to prior audio editing methods. Demos are provided in the supplementary file. Code and data will be released upon acceptance.

While generative Text-to-Speech (TTS) systems leverage vast "in-the-wild" data to achieve remarkable success, speech-to-speech processing tasks like enhancement face data limitations, which lead data-hungry generative approaches to distort speech content and speaker identity. To bridge this gap, we present SpeechOp, a multi-task latent diffusion model that transforms pre-trained TTS models into a universal speech processor capable of performing a wide range of speech tasks and composing them in novel ways at inference time. By adapting a pre-trained TTS model, SpeechOp inherits a rich understanding of natural speech, accelerating training and improving S2S task quality, while simultaneously enhancing core TTS performance. Finally, we introduce Implicit Task Composition (ITC), a novel pipeline where ASR-derived transcripts (e.g., from Whisper) guide SpeechOp's enhancement via our principled inference-time task composition. ITC achieves state-of-the-art content preservation by robustly combining web-scale speech understanding with SpeechOp's generative capabilities.

Video frame interpolation (VFI), which generates intermediate frames from given start and end frames, has become a fundamental function in video generation applications. However, existing generative VFI methods are constrained to synthesizing a fixed number of intermediate frames, lacking the flexibility to adjust generated frame rates or total sequence duration. In this work, we present ArbInterp, a novel generative VFI framework that enables efficient interpolation at any timestamp and of any length. Specifically, to support interpolation at any timestamp, we propose the Timestamp-aware Rotary Position Embedding (TaRoPE), which modulates positions in temporal RoPE to align generated frames with target normalized timestamps. This design enables fine-grained control over frame timestamps, addressing the inflexibility of fixed-position paradigms in prior work. For any-length interpolation, we decompose long-sequence generation into segment-wise frame synthesis. We further design a novel appearance-motion decoupled conditioning strategy: it leverages prior segment endpoints to enforce appearance consistency and temporal semantics to maintain motion coherence, ensuring seamless spatiotemporal transitions across segments. Experimentally, we develop comprehensive benchmarks for multi-scale frame interpolation (2× to 32×) to assess generalizability across arbitrary interpolation factors. Results show that ArbInterp outperforms prior methods across all scenarios with higher fidelity and more seamless spatiotemporal continuity.

State Space Models (SSMs) have emerged as powerful alternatives to attention-based Transformers, with Mamba demonstrating impressive efficiency and scalability. As these models grow increasingly larger, the need for Parameter-Efficient Fine-Tuning (PEFT) methods becomes critical to adapt pre-trained Mamba to downstream tasks without prohibitive computational costs. However, previous approaches simply apply traditional Transformer-tailored PEFT methods without addressing the unique temporal processing dynamics of SSMs. To address this limitation, we propose ***Memba***, a membrane-driven PEFT approach specifically designed for Mamba. ***Memba*** introduces Leaky Integrate Membrane (LIM) neurons as bio-inspired gating mechanisms that naturally accumulate membrane potentials over time, enhancing selective information retention. By strategically combining LIM neurons with Low-Rank Adaptations (LoRA) and cross-layer membrane transfer, our approach significantly improves Mamba's temporal modeling capabilities. Extensive experiments across language and vision tasks demonstrate that ***Memba*** achieves substantial improvements over existing PEFT methods.

3D Gaussian Splatting (3DGS) has emerged as a dominant novel-view synthesis technique, but its high memory consumption severely limits its applicability on edge devices. A growing number of 3DGS compression methods have been proposed to make 3DGS more efficient, yet most only focus on storage compression and fail to address the critical bottleneck of rendering memory. To address this problem, we introduce MEGS², a novel memory-efficient framework that tackles this challenge by jointly optimizing two key factors: the total primitive number and the parameters per primitive, achieving unprecedented memory compression. Specifically, we fully replace the memory-intensive Spherical Harmonics with lightweight, arbitrarily oriented and prunable Spherical Gaussian lobes as our color representations. More importantly, we propose a unified soft pruning framework that models primitive-number and lobe-number pruning as a single constrained optimization problem. Experiments show that MEGS² achieves a 50% static VRAM reduction and a 40% rendering VRAM reduction compared to existing methods, while maintaining comparable rendering quality.

Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nuanced emotional expressions due to the lack of fine-grained emotion control. To address this issue, we introduce a novel two-stage method (AUHead) to disentangle fine-grained emotion control, i.e. , Action Units (AUs), from audio and achieve controllable generation. In the first stage, we explore the AU generation abilities of large audio-language models (ALMs), by spatial-temporal AU tokenization and an "emotion-then-AU" chain-of-thought mechanism. It aims to disentangle AUs from raw speech, effectively capturing subtle emotional cues. In the second stage, we propose an AU-driven controllable diffusion model that synthesizes realistic talking-head videos conditioned on AU sequences. Specifically, we first map the AU sequences into the structured 2D facial representation to enhance spatial fidelity, and then model the AU-vision interaction within cross-attention modules. To achieve flexible AU-quality trade-off control, we introduce an AU disentanglement guidance strategy during inference, further refining the emotional expressiveness and identity consistency of the generated videos. Results on benchmark datasets demonstrate that our approach achieves competitive performance in emotional realism, accurate lip synchronization, and visual coherence, significantly surpassing existing techniques. Our implementation is available at https://github.com/laura990501/AUHead_ICLR

As a central task in product bundling, bundle construction aims to select a subset of items from huge item catalogs to complete a partial bundle. Existing methods often rely on the sequential construction paradigm that predicts items one at a time, nevertheless, this paradigm is fundamentally unsuitable for the essentially unordered bundles. In contrast, the non-sequential construction paradigm models bundle as a set, while it still faces two dimensionality curses: the combination complexity is exponential to the catalog size and bundle length. Accordingly, we identify two technical challenges: 1) how to effectively and efficiently model the higher-order intra-bundle relations with the growth of bundle length; and 2) how to learn item embeddings that are sufficiently discriminative while maintaining a relatively smaller search space other than the huge item set. To address these challenges, we propose DDBC, a Discrete Diffusion model for Bundle Construction. DDBC leverages a masked denoising diffusion process to build bundles non-sequentially, capturing joint dependencies among items without relying on certain pre-defined order. To mitigate the curse of large catalog size, we integrate residual vector quantization (RVQ), which compresses item embeddings into discrete codes drawn from a globally shared codebook, enabling more efficient search while retaining semantic granularity. We evaluate our method on real-world bundle construction datasets of music playlist continuation and fashion outfit completion, and the experimental results show that DDBC can achieve more than 100\% relative performance improvements compared with state-of-the-art baseline methods. Ablation and model analyses further confirm the effectiveness of both the diffusion backbone and RVQ tokenizer, where the performance gain is more significant for larger catalog size and longer bundle length. Our code is available at https://anonymous.4open.science/r/DDBC-44EE.