ICLR 2026 Papers

Despite achieving significant progress in 2D image understanding, large multimodal models (LMMs) struggle in the physical world due to the lack of spatial representation. Typically, existing 3D LMMs mainly embed 3D positions as fixed spatial prompts within visual features to represent the scene. However, these methods are limited to understanding the static background and fail to capture temporally varying dynamic objects. In this paper, we propose LLaVA-4D, a general LMM framework with a novel spatiotemporal prompt for visual representation in 4D scene understanding. The spatiotemporal prompt is generated by encoding 3D position and 1D time into a dynamic-aware 4D coordinate embedding. Moreover, we demonstrate that spatial and temporal components disentangled from visual features are more effective in distinguishing the background from objects. This motivates embedding the 4D spatiotemporal prompt into these features to enhance the dynamic scene representation. By aligning visual spatiotemporal embeddings with language embeddings, LMMs gain the ability to understand both spatial and temporal characteristics of static background and dynamic objects in the physical world. Additionally, we construct a 4D vision-language dataset with spatiotemporal coordinate annotations for instruction fine-tuning LMMs. Extensive experiments have been conducted to demonstrate the superiority of our method on various tasks of 4D scene understanding. Our code will be open-sourced on paper acceptance.

Computer-Aided Design (CAD) is a foundational component of industrial prototyping. where models are defined not by raw coordinates but by construction sequences such as sketches and extrusions. This sequential structure enables both efficient prototype initialization and subsequent editing. Text-guided CAD prototyping, which unifies Text-to-CAD generation and CAD editing, has the potential to streamline the entire design pipeline. However, prior work has not explored this setting, largely because standard large language model (LLM) tokenizers decompose CAD sequences into natural-language word pieces, failing to capture primitive-level CAD semantics and hindering attention modules from modeling geometric structure. We conjecture that a multimodal tokenization strategy, aligned with CAD’s primitive and structural nature, can provide more effective representations. To this end, we propose CAD-Tokenizer, a framework that represents CAD data with modality-specific tokens using a sequence-based VQ-VAE with primitive-level pooling and constrained decoding. This design produces compact, primitive-aware representations that align with CAD’s structural nature. Applied to unified text-guided CAD prototyping, CAD-Tokenizer significantly improves instruction following and generation quality, achieving better quantitative and qualitative performance over both general-purpose LLMs and task-specific baselines.

While many diffusion models have achieved impressive results in real-world video super-resolution (Real-VSR) by generating rich and realistic details, their reliance on multi-step sampling leads to slow inference. One-step networks like SeedVR2, DOVE, and DLoRAL alleviate this through condensing generation into one single step, yet they remain heavy, with billions of parameters and multi-second latency. Recent adversarial diffusion compression (ADC) offers a promising path via pruning and distilling these models into a compact AdcSR network, but directly applying it to Real-VSR fails to balance spatial details and temporal consistency due to its lack of temporal awareness and the limitations of standard adversarial learning. To address these challenges, we propose an improved **ADC** method for Real-**VSR**. Our approach distills a large diffusion Transformer (DiT) teacher DOVE equipped with 3D spatio-temporal attentions, into a pruned 2D Stable Diffusion (SD)-based AdcSR backbone, augmented with lightweight 1D temporal convolutions, achieving significantly higher efficiency. In addition, we introduce a dual-head adversarial distillation scheme, in which discriminators in both pixel and feature domains explicitly disentangle the discrimination of details and consistency into two heads, enabling both objectives to be effectively optimized without sacrificing one for the other. Experiments demonstrate that the resulting compressed **AdcVSR** model reduces complexity by **95%** in parameters and achieves an **8$\times$** acceleration over its DiT teacher DOVE, while maintaining competitive video quality and efficiency.

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned Sparse Retrieval (LSR), whose objective is to encode queries and documents into high-dimensional sparse representations optimized for efficient retrieval. In contrast to existing LSR approaches that project input sequences into the vocabulary space, SAE-based representations offer the potential to produce more semantically structured, expressive, and language-agnostic features. By leveraging recently released open-source SAEs, we show that their latent features can serve as effective indexing units for representing documents and queries for sparse retrieval. Our experiments demonstrate that SAE-based LSR models consistently outperform their vocabulary-based counterparts in multilingual and out-of-domain settings. Finally, we introduce SPLARE, a 7B-parameter multilingual retrieval model capable of producing generalizable sparse latent embeddings for a wide range of languages and domains, achieving top results on MMTEB’s multilingual and English retrieval tasks. We also release a more efficient 2B-parameter variant, offering strong performance with a significantly lighter footprint.

Recent advances in the audio language modeling (ALM) domain tackle audio understanding and text-to-audio generation as separate tasks. Very few studies attempt to unify these tasks -- an essential step toward advanced multimodal reasoning. This paper introduces Unified Audio Language Model (UALM), which aims to unify audio understanding, text-to-audio generation, and multimodal reasoning in a single model. To achieve this goal, we first present UALM-Gen, a text-to-audio language model that directly predicts audio tokens and is comparable to state-of-the-art diffusion-based models. We then demonstrate, using proper data blending, training recipes, and inference techniques, that our single UALM model matches the quality of state-of-the-art specialized models in audio understanding, text-to-audio generation, and text reasoning. Furthermore, we present UALM-R1, a multimodal reasoning model that utilizes both text and audio in the intermediate thinking steps to facilitate complex generation tasks. To our knowledge, this is the first demonstration in audio research of cross-modal generative reasoning, with its effectiveness confirmed by subjective evaluations.

Despite rapid progress in Multi-modal Large Language Models and Large Audio-Language Models, existing audio benchmarks largely test semantics that can be recovered from text captions, masking deficits in fine-grained perceptual reasoning. We formalize audio 4D intelligence that is defined as reasoning over sound dynamics in time and 3D space, and introduce STAR-Bench to measure it. STAR-Bench combines a Foundational Acoustic Perception setting (six attributes under absolute and relative regimes) with a Holistic Spatio-Temporal Reasoning setting that includes segment reordering for continuous and discrete processes and spatial tasks spanning static localization, multi-source relations, and dynamic trajectories. Our data curation pipeline uses two methods to ensure high-quality samples. For foundational tasks, we use procedurally synthesized and physics-simulated audio. For holistic data, we follow a four-stage process that includes human annotation and final selection based on human performance. Unlike prior benchmarks where caption-only answering reduces accuracy slightly, STAR-Bench induces far larger drops (-31.5\% temporal, -35.2\% spatial), evidencing its focus on linguistically hard-to-describe cues. Evaluating 19 models reveals substantial gaps compared with humans and a capability hierarchy: closed-source models are bottlenecked by fine-grained perception, while open-source models lag across perception, knowledge, and reasoning. Our STAR-Bench provides critical insights and a clear path forward for developing future models with a more robust understanding of the physical world.

Real-time voice conversion and speaker anonymization require causal, low-latency synthesis without sacrificing intelligibility or naturalness. Current systems have a core representational mismatch: content is time-varying, while speaker identity is injected as a static global embedding. We introduce a streamable speech synthesizer that aligns the temporal granularity of identity and content via a content-synchronous, time-varying timbre (TVT) representation. A Global Timbre Memory expands a global timbre instance into multiple compact facets; frame-level content attends to this memory, a gate regulates variation, and spherical interpolation preserves identity geometry while enabling smooth local changes. In addition, a factorized vector-quantized bottleneck regularizes content to reduce residual speaker leakage. The resulting system is streamable end-to-end, with <80 ms GPU latency. Experiments show improvements in naturalness, speaker transfer, and anonymization compared to SOTA streaming baselines, establishing TVT as a scalable approach for privacy-preserving and expressive speech synthesis under strict latency budgets.

Knowledge-Based Visual Question Answering (KB-VQA) requires models to answer questions about an image by integrating external knowledge, posing significant challenges due to noisy retrieval and the structured, encyclopedic nature of the knowledge base. These characteristics create a distributional gap from pretrained multimodal large language models (MLLMs), making effective reasoning and domain adaptation difficult in the post-training stage. In this work, we propose \textit{Wiki-R1}, a data-generation-based curriculum reinforcement learning framework that systematically incentivizes reasoning in MLLMs for KB-VQA. Wiki-R1 constructs a sequence of training distributions aligned with the model’s evolving capability, bridging the gap from pretraining to the KB-VQA target distribution. We introduce \textit{controllable curriculum data generation}, which manipulates the retriever to produce samples at desired difficulty levels, and a \textit{curriculum sampling strategy} that selects informative samples likely to yield non-zero advantages during RL updates. Sample difficulty is estimated using observed rewards and propagated to unobserved samples to guide learning. Experiments on two KB-VQA benchmarks, Encyclopedic VQA and InfoSeek, demonstrate that Wiki-R1 achieves new state-of-the-art results, improving accuracy from 35.5\% to 37.1\% on Encyclopedic VQA and from 40.1\% to 44.1\% on InfoSeek.

Diffusion models have recently demonstrated significant robustness in medical image segmentation, effectively accommodating variations across different imaging styles. However, their applications remain limited due to: (i) current successes being primarily confined to 2D segmentation tasks—we observe that diffusion models tend to collapse at the early stage when applied to 3D medical tasks; and (ii) the inherently isolated iteration along timesteps during training and inference. To tackle these limitations, we propose a novel framework named Cross-Timestep, which incorporates two key innovations: an Adaptive Priori Decoding Strategy (APDS) and a trans-temporal memory LSTM (tLSTM) mechanism. (i) The APDS provides prior guidance during the diffusion process by employing a Priori Decoder(PD) that focuses solely on the conditional branch, successfully stabilizing the reverse diffusion process. (ii) The tLSTM integrates convolution and linear layers into the LSTM gating structure, and enhances the memory cell mechanism to retain temporal state, explicitly preserving and propagating continuous temporal states across timesteps. Experimental results demonstrate that Cross-Timestep performs favorably on heterogeneous 3D medical datasets. Three experiments further analyze the collapse phenomenon in 3D medical diffusion models and validate that APDS effectively prevents initial-stage collapse without excessively constraining the model, while tLSTM facilitates the performance and scalability of diffusion models.

Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We present Adaptive Patch Transformers (APT), which addresses this by using multiple different patch sizes within the same image. APT reduces the total number of input tokens by allocating larger patch sizes in more homogeneous areas and smaller patches in more complex ones. APT achieves a drastic speedup in ViT inference and training, increasing throughput by 40\% on ViT-L and 50\% on ViT-H while maintaining downstream performance. It can be applied to a previously fine-tuned ViT and converges in as little as 1 epoch. It also significantly reduces training and inference time without loss of performance in high-resolution dense visual tasks, achieving up to 30\% faster training and inference in visual QA, object detection, and semantic segmentation. We will release all code and trained models.

Training critiquing language models to assess and provide feedback on model outputs is a promising way to improve LLMs for complex reasoning tasks. However, existing approaches typically rely on stronger supervisors for annotating critique data. To address this, we propose Critique-RL, an online RL approach for developing critiquing language models without stronger supervision. Our approach operates on a two-player paradigm: the actor generates a response, the critic provides feedback, and the actor refines the response accordingly. We first reveal that relying solely on indirect reward signals from the actor’s outputs for RL optimization often leads to unsatisfactory critics: while their helpfulness (i.e., providing constructive feedback) improves, the discriminability (i.e., determining whether a response is high-quality or not) remains poor, resulting in marginal performance gains. To overcome this, Critique-RL adopts a two-stage optimization strategy. In stage I, it reinforces the discriminability of the critic with direct rule-based reward signals; in stage II, it introduces indirect rewards based on actor refinement to improve the critic's helpfulness, while maintaining its discriminability via appropriate regularization. Extensive experiments across various tasks and models show that Critique-RL delivers substantial performance improvements. For example, it achieves a $9.02\%$ gain on in-domain tasks and a $5.70\%$ gain on out-of-domain tasks for Qwen2.5-7B, highlighting its potential.

Evaluating modern machine learning models has become prohibitively expensive. Benchmarks such as LMMs-Eval and HELM demand thousands of GPU hours per model. Costly evaluation reduces inclusivity, slows the cycle of innovation, and worsens environmental impact. To address the growing cost of standard evaluation, new methods focused on efficient evaluation have started to appear. The typical approach follows two steps. The typical approach follows two steps. First, select an anchor subset of data. Second, train a mapping from the accuracy on this subset to the final test result. The drawback is that anchor selection depends on clustering, which can be complex and sensitive to design choices. We argue that promoting diversity among samples is not essential; what matters is to select samples that *maximise diversity in model responses*. Our method, **Diversifying Sample Condensation** **(DISCO)**, selects the top-k samples with the greatest model disagreements. This uses greedy, sample-wise statistics rather than global clustering. The approach is conceptually simpler. From a theoretical view, inter-model disagreement provides an information-theoretically optimal rule for such greedy selection. **DISCO** shows empirical gains over prior methods, achieving state-of-the-art results in performance prediction across MMLU, Hellaswag, Winogrande, and ARC.

Automatic polyp segmentation from colonoscopy videos is a crucial technique that assists clinicians in improving the accuracy and efficiency of diagnosis, preventing polyps from developing into cancer. However, video polyp segmentation (VPS) is a challenging task due to (1) the significant inter-frame divergence in videos, (2) the high camouflage of polyps in normal colon structures and (3) the clinical requirement of real-time performance. In this paper, we propose a novel segmentation network, WavePolyp, which consists of two innovative components: a hierarchical wavelet-based feature aggregation (HWFA) module and inter-frame divergence perception (IDP) blocks. Specifically, HWFA excavates and amplifies discriminative information from high-frequency and low-frequency features decomposed by wavelet transform, hierarchically aggregating them into refined spatial representations within each frame. This module enhances the representation capability of intra-frame spatial features, effectively addressing the high camouflage of polyps in normal colon structures. Furthermore, IDP perceives and captures inter-frame polyp divergence through a temporal divergence perception mechanism, enabling accurate polyp tracking while mitigating temporal inconsistencies caused by the significant inter-frame variations across frames. Extensive experiments conducted on the SUN-SEG and CVC-612 datasets demonstrate that our method outperforms other state-of-the-art methods. Codes will be released upon publication.

Developing a mobile system capable of generating responses based on stored user data is a crucial challenge. Since user data is stored in the form of Knowledge Graphs, the field of knowledge graph question answering (KGQA) presents a promising avenue towards addressing this problem. However, existing KGQA systems face two critical limitations that preclude their on-device deployment: resource constraints and the inability to handle data accumulation. Therefore, we propose MobileKGQA, the first on-device KGQA system capable of adapting to evolving databases with minimal resource demands. MobileKGQA significantly reduces computational overhead through embedding hashing. Moreover, it successfully adapts to evolving databases under resource constraints through a novel annotation generation method. Its mobile applicability is validated on the NVIDIA Jetson Orin Nano edge-device platform, achieving 20.3% higher performance while using only 30.4% of the energy consumed by the SOTA (state of the art). On standard KGQA benchmarks, using just 7.2% of the computation and 9% of the parameters, MobileKGQA demonstrates performance that is empirically indistinguishable from the SOTA and outperforms baselines under distribution shift scenarios.

This work analyzes the training dynamics of Image Restoration (IR) Transformers and uncovers a critical yet overlooked issue: conventional LayerNorm (LN) drives feature magnitudes to diverge to a million scale and collapses channel-wise entropy. We analyze this in the perspective of networks attempting to bypass LayerNorm’s constraints, which conflict with IR tasks. Accordingly, we address two misalignments: 1) per-token normalization that disrupts spatial correlations, and 2) input-independent scaling that discards input-specific statistics. To address this, we propose Image Restoration Transformer Tailored Layer Normalization (i-LN), a simple drop-in replacement that normalizes features holistically and adaptively rescales them per input. We provide theoretical insights and empirical evidence that this design effectively captures important spatial correlations and better preserves input-specific statistics throughout the network. Experimental results verify that the proposed i-LN consistently outperforms vanilla LN on various IR tasks.

Real-time reconstruction of dynamic 3D scenes from uncalibrated video streams demands robust online methods that recover scene dynamics from sparse observations under strict latency and memory constraints. Yet most dynamic reconstruction methods rely on hours of per-scene optimization under full-sequence access, limiting practical deployment. In this work, we introduce **StreamSplat**, a fully feed-forward framework that instantly transforms uncalibrated video streams of arbitrary length into dynamic 3D Gaussian Splatting (3DGS) representations in an online manner. It is achieved via three key technical innovations: 1) a probabilistic sampling mechanism that robustly predicts 3D Gaussians from uncalibrated inputs; 2) a bidirectional deformation field that yields reliable associations across frames and mitigates long-term error accumulation; 3) an adaptive Gaussian fusion operation that propagates persistent Gaussians while handling emerging and vanishing ones. Extensive experiments on standard dynamic and static benchmarks demonstrate that StreamSplat achieves state-of-the-art reconstruction quality and dynamic scene modeling. Uniquely, our method supports the online reconstruction of arbitrarily long video streams with a $1200\times$ speedup over optimization-based methods. Our code and models will be made publicly available.

Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (\textit{e.g.}, $\times$ 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling coordinate-to-pixel mappings. However, the efficiency of these methods may suffer from repeated upsampling and decoding, while their reconstruction fidelity and quality are constrained by the intrinsic representational limitations of coordinate-based functions. To address these challenges, we propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting. This approach eliminates the need for time-consuming upsampling and decoding, enabling extremely fast ASSR. Once the Gaussian field is built in a single pass, ContinuousSR can perform arbitrary-scale rendering in just 1ms per scale. Our method introduces several key innovations. Through statistical analysis, we uncover the Deep Gaussian Prior (DGP) and propose DGP-Driven Covariance Weighting, which dynamically optimizes covariance via adaptive weighting. Additionally, we present Adaptive Position Drifting, which refines the positional distribution of the Gaussian space based on image content, further enhancing reconstruction quality. Extensive experiments on seven benchmarks demonstrate that our ContinuousSR delivers significant improvements in SR quality across all scales, with an impressive 19.5× speedup when continuously upsampling an image across forty scales.

Effectively applying Vision-Language Models (VLMs) to Video Question Answering (VideoQA) hinges on selecting a concise yet comprehensive set of frames, as processing entire videos is computationally infeasible. However, current frame selection methods face a critical trade-off: approaches relying on lightweight similarity models, such as CLIP, often fail to capture the nuances of complex queries, resulting in inaccurate similarity scores that cannot reflect the authentic query-frame relevance, which further undermines frame selection. Meanwhile, methods that leverage a VLM for deeper analysis achieve higher accuracy but incur prohibitive computational costs. To address these limitations, we propose A.I.R., a training-free approach for Adaptive, Iterative, and Reasoning-based frame selection. We leverage a powerful VLM to perform deep, semantic analysis on complex queries, and this analysis is deployed within a cost-effective iterative loop that processes only a small batch of the most high-potential frames at a time. Extensive experiments on various VideoQA benchmarks demonstrate that our approach outperforms existing frame selection methods, significantly boosts the performance of the foundation VLM, and achieves substantial gains in computational efficiency over other VLM-based techniques.

Multimodal large language models (MLLMs) often miss small details and spatial relations in cluttered scenes, leading to errors in fine-grained perceptual grounding. We introduce AttWarp, a lightweight method that allocates more resolution to query-relevant content while compressing less informative areas, all while preserving global context. At test time, the approach uses an MLLM's cross-modal attention to perform rectilinear warping of the input image, reallocating spatial resolution toward regions the model deems important, without changing model weights or architecture. This attention-guided warping preserves all original image information but redistributes it non-uniformly, so small objects and subtle relationships become easier for the same model to read while the global layout remains intact. Across ten benchmarks (TextVQA, GQA, DocVQA, POPE, MMMU, MIA-Bench, MMVP, VQAv2, RealWorldQA, BLINK) and four MLLMs (LLaVA, Qwen-VL, InternVL, and InstructBLIP), AttWarp consistently improves accuracy, strengthens compositional reasoning, and reduces hallucinations, outperforming four competitive baselines that manipulate raw images at test time. Together, these results show that attention-guided warping prioritizes information relevant to the query while preserving context, and that the same MLLMs perform better when given such warped inputs.