ICLR 2026 论文列表

Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy codecs with a limited bitrate. As a consequence, increasing audio quality requires generating more tokens, which imposes a trade-off between fidelity and computational cost. We address this issue by studying Continuous Audio Language Models (CALM). These models instantiate a large Transformer backbone that produces a contextual embedding at every timestep. This sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling. By avoiding lossy compression, CALM achieves higher quality at lower computational cost than their discrete counterpart. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. Samples are available at iclr-continuous-audio-language-models.github.io. Finally, we release Pocket TTS, an open-source 100M-parameter text-to-speech model that can run faster than real time on a laptop CPU: github.com/kyutai-labs/pocket-tts.

Audio-visual speech separation (AVSS) methods leverage visual cues to extract target speech and have demonstrated strong separation quality in noisy acoustic environments. However, these methods usually involve a large number of parameters and require high computational cost, which is unacceptable in many applications where speech separation serves as only a preprocessing step for further speech processing. To address this issue, we propose an efficient AVSS method, named **Dolphin**. For visual feature extraction, we develop **DP‑LipCoder**, a dual‑path lightweight video encoder that transforms lip‑motion into discrete audio‑aligned semantic tokens. For audio separation, we construct a lightweight encoder–decoder separator, in which each layer incorporates a global–local attention (GLA) block to efficiently capture multi-scale dependencies. Experiments on three benchmark datasets showed that Dolphin not only surpassed the current state-of-the-art (SOTA) model in separation quality but also achieved remarkable improvements in efficiency: over 50\% fewer parameters, more than 2.4$\times$ reduction in MACs, and over 6$\times$ faster GPU inference speed. These results indicate that Dolphin offers a practical and deployable solution for high-performance AVSS in real-world scenarios. Our code and demo page are publicly available at https://dolphin-avss.github.io/Dolphin.

Composed video retrieval presents a complex challenge: retrieving a target video based on a source video and a textual modification instruction. This task demands fine-grained reasoning over multimodal transformations. However, existing benchmarks predominantly focus on vision–text alignment, largely overlooking the rich semantic signals embedded in audio—such as speech, music, and environmental sounds—which are often decisive for comprehensive video understanding. To bridge this gap, we introduce **OmniCVR**, a large-scale benchmark for omni-composed video retrieval that establishes vision, audio, and text as first-class modalities. OmniCVR is constructed via a scalable, automated pipeline integrating content-aware segmentation, omni-modal annotation, and a rigorous dual-validation protocol involving both large language models and human experts. The benchmark comprises vision-centric, audio-centric, and integrated queries, with the latter forming the majority to accurately reflect real-world multimodal complexity. Furthermore, we propose **AudioVLM2Vec**, an audio-aware extension of VLM2Vec. By incorporating explicit audio semantics, AudioVLM2Vec achieves state-of-the-art performance, highlighting fundamental limitations in the audio reasoning capabilities of current multimodal retrieval systems.

Recent advances in multimodal large language models (MLLMs) have demonstrated substantial potential in video understanding. However, existing benchmarks fail to comprehensively evaluate synergistic reasoning capabilities across audio and visual modalities, often neglecting either one of the modalities or integrating them in a logically inconsistent manner. To bridge this gap, we introduce OmniVideoBench, a large-scale and rigorously designed benchmark dedicated to assessing synergistic audio–visual understanding, with a strong emphasis on modality complementarity and logical consistency. Specifically, OmniVideoBench comprises 1000 high-quality question–answer(QA) pairs, each annotated with step-by-step reasoning traces, derived from 628 diverse videos ranging from several seconds to 30 minutes, and manually verified to guarantee complete correctness and uniqueness. Moreover, OmniVideoBench encompasses 13 carefully designed question types, covering temporal reasoning, spatial localization, counting, causal inference, summarization, and beyond, thereby capturing the essential challenges of video understanding. Evaluation of multiple MLLMs on OmniVideoBench reveals a pronounced gap between model performance and human reasoning, with open-source models lagging significantly behind their closed-source counterparts, underscoring the inherent difficulty of genuine audio–visual reasoning. We will release OmniVideoBench to foster the development of MLLMs with stronger and more generalizable reasoning capabilities.

Multi-Agent System (MAS) powered by Visual Language Models (VLMs) enables challenging tasks but suffers from a novel failure term, multi-agent visual hallucination snowballing, where hallucinations are seeded in a single agent and amplified by following ones due to the over-reliance on textual flow to relay visual information. Through turn-, layer-, and token-wise attention analyses, we provide detailed insights into the essence of hallucination snowballing regarding the reduction of visual attention allocation. It leads us to identify a subset of vision tokens with a unimodal attention peak in middle layers that best preserve visual evidence but gradually diminish in deeper agent turns, resulting in the visual hallucination snowballing in MAS. Thus, we propose ViF, a lightweight, plug-and-play mitigation paradigm that relays inter-agent messages with Visual Flow powered by the selected visual relay tokens and applies attention reallocation to amplify this pattern. The experiment results demonstrate that our method markedly reduces hallucination snowballing, consistently improving the performance across eight benchmarks based on four common MAS structures and ten base models. The implementation source code will be made publicly available.

Mistake detection in procedural tasks is essential for building intelligent systems that support learning and task execution. Existing approaches primarily analyze how an action is performed, while overlooking what it produces, i.e., the \textbf{action effect}. Yet many errors manifest not in the execution itself but in the resulting outcome, such as an unintended object state or incorrect spatial arrangement. To address this gap, we propose Action Effect Modeling (AEM), a unified framework that jointly captures action execution and its outcomes through a probabilistic formulation. AEM first identifies the outcome of an action by selecting the most informative effect frame based on semantic relevance and visual quality. It then extracts complementary cues from visual grounding and symbolic scene graphs, aligning them in a shared latent space to form robust effect-aware representations. To detect mistakes, we further design a prompt-based detector that incorporates task-specific prompts and aligns each action segment with its intended execution semantics. Our approach achieves state-of-the-art performance on the EgoPER and CaptainCook4D benchmarks under the challenging one-class classification (OCC) setting. These results demonstrate that modeling both execution and outcome yields more reliable mistake detection, and highlight the potential of effect-aware representations to benefit a broader range of downstream applications.

Although Video Large Language Models (VLLMs) have shown remarkable capabilities in video understanding, they are required to process high volumes of visual tokens, causing significant computational inefficiency. Existing VLLMs acceleration frameworks usually compress spatial and temporal redundancy independently, which overlooks the spatiotemporal relationships, thereby leading to suboptimal spatiotemporal compression. The highly correlated visual features are likely to change in spatial position, scale, orientation, and other attributes over time due to the dynamic nature of video. Building on this insight, we introduce FlashVID, a training-free inference acceleration framework for VLLMs. Specifically, FlashVID utilizes Attention and Diversity-based Token Selection (ADTS) to select the most representative tokens for basic video representation, then applies Tree-based Spatiotemporal Token Merging (TSTM) for fine-grained spatiotemporal redundancy elimination. Extensive experiments conducted on three representative VLLMs across five video understanding benchmarks demonstrate the effectiveness and generalization of our method. Notably, by retaining only $\textbf{10}$% of visual tokens, FlashVID preserves $\textbf{99.1}$% of the performance of LLaVA-OneVision. Consequently, FlashVID can serve as a training-free and plug-and-play module for extending long video frames, which enables a $\textbf{10$\times$}$ increase in video frame input to Qwen2.5-VL, resulting in a relative improvement of $\textbf{8.6}$% within the same computational budget. Code is available at https://github.com/Fanziyang-v/FlashVID.

Subject-agnostic brain decoding, which aims to reconstruct continuous visual experiences from fMRI without subject-specific training, holds great potential for clinical applications. However, this direction remains underexplored due to challenges in cross-subject generalization and the complex nature of brain signals. In this work, we propose Visual Cortex Flow Architecture (VCFlow), a novel hierarchical decoding framework that explicitly models the ventral-dorsal architecture of the human visual system to learn multi-dimensional representations. By disentangling and leveraging features from early visual cortex, ventral, and dorsal streams, VCFlow captures diverse and complementary cognitive information essential for visual reconstruction. Furthermore, we introduce a feature-level contrastive learning strategy to enhance the extraction of subject-invariant semantic representations, thereby enhancing subject-agnostic applicability to previously unseen subjects. Unlike conventional pipelines that need more than 12 hours of per-subject data and heavy computation, VCFlow sacrifices only 7\% accuracy on average yet generates each reconstructed video in 10 seconds without any retraining, offering a fast and clinically scalable solution.

Multimodal Large Language Models (MLLMs), which couple pre-trained vision encoders and language models, have shown remarkable capabilities. However, their reliance on the ubiquitous Pre-Norm architecture introduces a subtle yet critical flaw: a severe norm disparity between the high-norm visual tokens and the low-norm text tokens. In this work, we present a formal theoretical analysis demonstrating that this imbalance is not a static issue. Instead, it induces an ''asymmetric update dynamic,'' where high-norm visual tokens exhibit a ``representational inertia,'' causing them to transform semantically much slower than their textual counterparts. This fundamentally impairs effective cross-modal feature fusion. Our empirical validation across a range of mainstream MLLMs confirms that this theoretical dynamic---the persistence of norm disparity and the resulting asymmetric update rates---is a prevalent phenomenon. Based on this insight, we propose a remarkably simple yet effective solution: inserting a single, carefully initialized LayerNorm layer after the visual projector to enforce norm alignment. Experiments conducted on the LLaVA-1.5 architecture show that this intervention yields significant performance gains not only on a wide suite of multimodal benchmarks but also, notably, on text-only evaluations such as MMLU, suggesting that resolving the architectural imbalance leads to a more holistically capable model.

Autoregressive (AR) models have emerged as powerful tools for image generation by modeling images as sequences of discrete tokens. While Classifier-Free Guidance (CFG) has been adopted to improve conditional generation, its application in AR models faces two key issues: guidance diminishing, where the conditional–unconditional gap quickly vanishes as decoding progresses, and over-guidance, where strong conditions distort visual coherence. To address these challenges, we propose SoftCFG, an uncertainty-guided inference method that distributes adaptive perturbations across all tokens in the sequence. The key idea behind SoftCFG is to let each generated token contribute certainty-weighted guidance, ensuring that the signal persists across steps while resolving conflicts between text guidance and visual context. To further stabilize long-sequence generation, we introduce Step Normalization, which bounds cumulative perturbations of SoftCFG. Our method is training-free, model-agnostic, and seamlessly integrates with existing AR pipelines. Experiments show that SoftCFG significantly improves image quality over standard CFG and achieves state-of-the-art FID on ImageNet 256 × 256 among autoregressive models.

Video Query Sound Separation (VQSS) aims to isolate target sounds conditioned on visual queries while suppressing off-screen interference—a task central to audiovisual understanding. However, existing methods often fail under conditions of homogeneous interference and overlapping soundtracks, due to limited temporal modeling and weak audiovisual alignment. We propose \textbf{AlignSep}, the first generative VQSS model based on flow matching, designed to address common issues such as spectral holes and incomplete separation. To better capture cross-modal correspondence, we introduce a series of temporal consistency mechanisms that guide the vector field estimator toward learning robust audiovisual alignment, enabling accurate and resilient separation in complex scenes. As a \textit{multi-conditioned generation} task, VQSS presents unique challenges that differ fundamentally from traditional flow matching setups. We provide an in-depth analysis of these differences and their implications for generative modeling. To systematically evaluate performance under realistic and difficult conditions, we further construct \textbf{VGGSound-Hard}, a challenging benchmark composed entirely of separation cases with homogeneous interference and strong reliance on temporal visual cues. Extensive experiments across multiple benchmarks demonstrate that AlignSep achieves state-of-the-art performance both quantitatively and perceptually, validating its practical value for real-world applications. More results and audio examples are available at: \url{https://AlignSep.github.io}.

We introduce $\pi^3$, a feed-forward neural network that offers a novel approach to visual geometry reconstruction, breaking the reliance on a conventional fixed reference view. Previous methods often anchor their reconstructions to a designated viewpoint, an inductive bias that can lead to instability and failures if the reference is suboptimal. In contrast, $\pi^3$ employs a fully permutation-equivariant architecture to predict affine-invariant camera poses and scale-invariant local point maps without any reference frames. This design not only makes our model inherently robust to input ordering, but also leads to higher accuracy and performance. These advantages enable our simple and bias-free approach to achieve state-of-the-art performance on a wide range of tasks, including camera pose estimation, monocular/video depth estimation, and dense point map reconstruction. Code and models will be publicly available.

Visual autoregressive (AR) generation offers a promising path toward unifying vision and language models, yet its performance remains suboptimal against diffusion models. Prior work often attributes this gap to tokenizer limitations and rasterization ordering. In this work, we identify a core bottleneck from the perspective of generator-tokenizer inconsistency, i.e., the AR-generated tokens may not be well-decoded by the tokenizer. To address this, we propose reAR, a simple training strategy introducing a token-wise regularization objective: when predicting the next token, the causal transformer is also trained to recover the visual embedding of the current token and predict the embedding of the target token under a noisy context. It requires no changes to the tokenizer, generation order, inference pipeline, or external models. Despite its simplicity, reAR substantially improves performance. On ImageNet, it reduces gFID from 3.02 to 1.86 and improves IS to 316.9 using a standard rasterization-based tokenizer. When applied to advanced tokenizers, it achieves a gFID of 1.42 with only 177M parameters, matching the performance with larger state-of-the-art diffusion models (675M).

Despite the importance of global contextual modeling in visual tasks, a rigorous mathematical definition remains absent, and the concept is still largely described in heuristic or empirical terms. Existing methods either rely on computationally expensive attention mechanisms or are constrained by the recursive modeling nature of State Space Models (SSMs), making it challenging to achieve both efficiency and true global perception. To address this, we first propose a mathematical definition of global modeling for visual images, providing a theoretical foundation for designing globally-aware and interpretable models. Based on in-depth analysis of SSMs and frequency-domain modeling principles, we construct a complete theoretical framework that overcomes the limitations imposed by SSMs' recursive modeling mechanism from a frequency perspective, thereby adapting SSMs for global perception in image modeling. Guided by this framework, we design the Global-aware SSM (GSSM) module and formally prove that it satisfies definitional requirements of global image modeling. GSSM leverages a Discrete Fourier Transform (DFT)-based modulation mechanism, providing precise front-end control over the SSM's modeling behavior, and enabling efficient global image modeling with linear-logarithmic complexity. Building upon GSSM, we develop GMamba, a plug-and-play module that can be seamlessly integrated at any stage of Convolutional Neural Networks (CNNs). Extensive experiments across multiple tasks, including object detection, semantic segmentation, and instance segmentation, across diverse model architectures, demonstrate that GMamba consistently outperforms existing global modeling modules, validating both the effectiveness of our theoretical framework and the rigor of proposed definition. Code is available at \url{https://github.com/Xinmu-Tantai/GMamba-GSSM}

Audio–Visual Question Answering (AVQA) is a challenging multimodal task that requires jointly reasoning over audio, visual, and textual information in a given video to answer natural language questions. Inspired by recent advances in Video QA, many existing AVQA approaches primarily focus on visual information processing, leveraging pre-trained models to extract object-level and motion-level representations. However, in those methods, the audio input is primarily treated as complementary to video analysis, and the textual question information contributes minimally to audio–visual understanding, as it is typically integrated only in the final stages of reasoning. To address these limitations, we propose a novel Query-guided Spatial–Temporal–Frequency (QSTar) interaction method, which effectively incorporates question-guided clues and exploits the distinctive frequency-domain characteristics of audio signals, alongside spatial and temporal perception, to enhance audio–visual understanding. Furthermore, we introduce a Query Context Reasoning (QCR) block inspired by prompting, which guides the model to focus more precisely on semantically relevant audio and visual features. Extensive experiments conducted on two AVQA benchmarks demonstrate the effectiveness of our proposed method, achieving significant performance improvements over existing Audio QA, Visual QA, Video QA, and AVQA approaches. The code is released under https://github.com/lik1996/QSTar.

Understanding how the brain encodes visual information is a central challenge in neuroscience and machine learning. A promising approach is to reconstruct visual stimuli—essentially images—from functional Magnetic Resonance Imaging (fMRI) signals. This involves two stages: transforming fMRI signals into a latent space and then using a pre-trained generative model to reconstruct images. The reconstruction quality depends on how similar the latent space is to the structure of neural activity and how well the generative model produces images from that space. Yet, it remains unclear which type of latent space best supports this transformation and how it should be organized to represent visual stimuli effectively. We present two key findings. First, fMRI signals are more similar to the text space of a language model than to either a vision-based space or a joint text–image space. Second, text representations and the generative model should be adapted to capture the compositional nature of visual stimuli, including objects, their detailed attributes, and relationships. Building on these insights, we propose PRISM, a model that Projects fMRI sIgnals into a Structured text space as an interMediate representation for visual stimuli reconstruction. It includes an object-centric diffusion module that generates images by composing individual objects to reduce object detection errors, and an attribute–relationship search module that automatically identifies key attributes and relationships that best align with the neural activity. Extensive experiments on real-world datasets demonstrate that our framework outperforms existing methods, achieving up to an 8% reduction in perceptual loss. These results highlight the importance of using structured text as the intermediate space to bridge fMRI signals and image reconstruction.

Visual Prompt Tuning (VPT) enables effective adaptation of a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable prompt tokens into the token sequence at each layer. However, we observe that existing VPT variants often suffer from unstable training dynamics, characterized by gradient oscillations. A closer layer-wise analysis reveals that shallow-layer prompts tend to stagnate early, while deeper-layer prompts exhibit high-variance oscillations, leading to a cross-layer mismatch. These issues contribute to slower convergence and degraded final performance. To address these challenges, we propose the Prompt-Agnostic Evolution ($\mathtt{PAE}$) method, which can strengthen vision prompt tuning by explicitly modeling the dynamics of learnable prompts. From a frequency-domain perspective, we initialize prompts in a task-aware direction by uncovering and propagating frequency shortcut patterns that the backbone inherently exploits for recognition. To ensure coherent evolution across layers, we further employ a shared Koopman operator, which imposes a global linear transformation rather than uncoordinated, layer-specific updates. Finally, inspired by Lyapunov stability theory, we introduce a regularizer that constrains error amplification during evolution. Extensive experiments demonstrate that using $\mathtt{PAE}$ with VPT variants not only accelerates convergence with an average 1.41$\times$ speedup but also yields 1–3% gains on 25 datasets with multi downstream tasks. Beyond performance, $\mathtt{PAE}$ remains prompt-agnostic and lightweight, and it integrates seamlessly with diverse VPT variants without backbone modification or inference-time changes, providing a practical and scalable solution for advancing prompt tuning.

Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision–language alignment, yet they remain limited in visual–spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual tokens are overshadowed by language tokens, preventing the model from consistently recognizing the same visual cues across frames. To address this challenge, we draw a novel connection between the self-expressiveness property in sparse subspace clustering and the attention mechanism in Transformers. Building on this insight, we propose VideoAnchor, a plug-and-play module that leverages subspace affinities to reinforce visual cues across frames without retraining, effectively anchoring attention to shared visual structures. Extensive experiments across benchmarks and backbone models show consistent performance gains — e.g., 3.2% and 4.6% improvements on VSI-Bench and Video-MME (spatial-related tasks) with InternVL2-8B and Qwen2.5VL-72B—while qualitative analyses demonstrate more coherent subspace partitions and stronger visual grounding.