ICLR 2026 Papers

Recent advances in speech large language models (speech LLMs) have enabled seamless spoken interactions, but these systems still struggle with complex reasoning tasks. Previously, chain-of-thought (CoT) prompting or fine-tuning has been shown to significantly improve the reasoning abilities of text-based LLMs. In this work, we investigate the effect of CoT fine-tuning for multi-stream speech LLMs, demonstrating that reasoning in text space improves the accuracy of speech LLMs by 2.4x, on average, over a suite of spoken reasoning tasks. Beyond accuracy, the latency of the spoken response is a crucial factor for interacting with voice-based agents. Inspired by the human behavior of "thinking while listening," we propose methods to reduce the additional latency from reasoning by allowing the model to start reasoning before the user query has ended. To achieve this, we introduce an entropy-based metric, "question completeness," which acts as an indicator to guide the model on the optimal time to start reasoning. This method provides greater control over the accuracy-latency trade-off compared with heuristic-based approaches and, under equivalent latency conditions, yields a 4% accuracy gain on ARC-Easy. Finally, we use Direct Preference Optimization (DPO) on preference data created using rejection sampling to push the accuracy-latency pareto frontier further, resulting in a 70% reduction in latency without loss in accuracy.

Large Language Models (LLMs) can be adapted to extend their text capabilities to speech inputs. However, these speech-adapted LLMs consistently underperform their text-based counterparts—and even cascaded pipelines—on language understanding tasks. We term this shortfall the text–speech understanding gap: the performance drop observed when a speech-adapted LLM processes spoken inputs relative to when the original text-based LLM processes the equivalent text. Recent approaches to narrowing this gap either rely on large-scale speech synthesis of text corpora, which is costly and heavily dependent on synthetic data, or on large-scale proprietary speech datasets, which are not reproducible. As a result, there remains a need for more data-efficient alternatives for closing the text-speech understanding gap. In this work, we analyze the gap as driven by two factors: (i) forgetting of text capabilities during adaptation, and (ii) cross-modal misalignment between speech and text. Based on this analysis, we introduce SALAD—Sample-efficient Alignment with Learning through Active selection and cross-modal Distillation—which combines cross-modal distillation with targeted synthetic data to improve alignment while mitigating forgetting. Applied to 3B and 7B LLMs, SALAD achieves competitive performance with a strong open-weight model across broad-domain benchmarks in knowledge, language understanding, and reasoning, while training on over an order of magnitude less speech data from publicly available corpora.

The rapid development of Large Language Models (LLMs) has significantly enhanced the general capabilities of machine translation. However, as application scenarios become more complex, the limitations of LLMs in vertical domain translations are gradually becoming apparent. In this study, we focus on how to construct translation LLMs that meet the needs of domain customization. We take visual media subtitle translation as our topic and explore how to train expressive and vivid translation LLMs. We investigated the situations of subtitle translation and other domains of literal and liberal translation, verifying the reliability of LLM as reward model and evaluator for translation. Additionally, to train an expressive translation LLM, we constructed and released a multidirectional subtitle parallel corpus dataset and proposed the Adaptive Local Preference Optimization (ALPO) method to address fine-grained preference alignment. Experimental results demonstrate that ALPO achieves outstanding performance in multidimensional evaluation of translation quality.

Existing research indicates that the output of **Chain-of-Thought (CoT)** is significantly affected by input perturbations. Although many methods aim to mitigate such impact by optimizing prompts, a theoretical explanation of how these perturbations influence CoT outputs remains an open area of research. This gap limits our in-depth understanding of how input perturbations propagate during the reasoning process and hinders further improvements in prompt optimization methods. Therefore, in this paper, we theoretically analyze the effect of input perturbations on the fluctuation of CoT outputs. We first derive an upper bound for input perturbations under the condition that the output fluctuation is within an acceptable range, and we prove that: - *i)* This upper bound is **positively correlated** with the number of reasoning steps in the CoT; - *ii)* Even an infinitely long reasoning process **cannot eliminate** the impact of input perturbations. We then apply these conclusions to the **Linear Self-Attention (LSA)** model, which can be viewed as a simplified version of Transformer. For the LSA model, we prove that the upper bound for input perturbation is **negatively correlated** with the norms of the input embedding and hidden state vectors. To validate this theoretical analysis, we conduct experiments on **three mainstream datasets** and **four mainstream models**. The experimental results align with our theoretical analysis, empirically demonstrating the correctness of our findings.

Generating realistic and diverse human-human interactions from text is a crucial yet challenging task in computer vision, graphics, and robotics. Despite recent advances, existing methods have two key limitations. First, two-person interaction synthesis is highly complex, simultaneously requiring individual human motion quality and spatial-temporal sync between the interactants. However, due to their limited scale, the current datasets cannot effectively support learning such a complex task, restricting the model's generalizing capabilities. To address this, we propose a scalable data synthesis framework, InterCompose, which leverages the general knowledge encoded in large language models and the motion priors from strong single-person generators to synthesize high-quality two-person interactions novel to the original data distribution. Second, accurately describing the intricacies of two-person motions often requires text of comparable complexity, and modeling such texts with a single sentence-level vector inevitably causes information loss. For a finer modeling of interaction semantics, we further propose Text2Interact, which features an attention-based word-level conditioning module, improving fine-grained text-motion alignment. Meanwhile, we introduce an adaptive interaction supervision signal that dynamically weighs body parts based on the interaction context, enhancing interaction realism. We conduct extensive experiments to validate the effectiveness of our proposed data synthesis and word-level conditioning pipeline. Compared to state-of-the-art models, our approach significantly enhances motion diversity, text-motion alignment, and motion realism. The code and trained models will be released for reproducibility.

Automatic Speech Recognition (ASR) systems frequently produce transcription errors due to acoustic variability, which require post-processing correction methods. Recent approaches leverage Large Language Models (LLMs) for generative ASR error correction using N-best hypotheses but rely on fixed set sizes regardless of input complexity and do not provide performance guarantees. We propose an adaptive framework that dynamically determines the optimal number of hypotheses for each input using risk control. This mechanism leverages ASR confidence scores and applies Learn then test (LTT) to control the expected relative word error rate degradation compared to the best achievable performance for a given model and hypothesis set. Experimental results demonstrate that our approach provides theoretical guarantees with high-probability bounds while matching or exceeding fixed-size correction baselines and requiring fewer hypotheses on average, achieving substantial computational savings under diverse acoustic conditions.

Music learners can greatly benefit from tools that accurately detect errors in their practice. Existing approaches typically compare audio recordings to music scores using heuristics or learnable models. This paper introduces \textit{LadderSym}, a novel Transformer-based method for music error detection. \textit{LadderSym} is guided by two key observations about the state-of-the-art approaches: (1) late fusion limits inter-stream alignment and cross-modality comparison capability; and (2) reliance on score audio introduces ambiguity in the frequency spectrum, degrading performance in music with concurrent notes. To address these limitations, \textit{LadderSym} introduces (1) a two-stream encoder with inter-stream alignment modules to improve audio comparison capabilities and error detection F1 scores, and (2) a multimodal strategy that leverages both audio and symbolic scores by incorporating symbolic representations as decoder prompts, reducing ambiguity and improving F1 scores. We evaluate our method on the \textit{MAESTRO-E} and \textit{CocoChorales-E} datasets by measuring the F1 score for each note category. Compared to the previous state of the art, \textit{LadderSym} more than doubles F1 for missed notes on \textit{MAESTRO-E} (26.8\%~$\rightarrow$~56.3\%) and improves extra note detection by 14.4 points (72.0\%~$\rightarrow$~86.4\%). Similar gains are observed on \textit{CocoChorales-E}. Furthermore, we also evaluate our models on real data we curated. This work introduces insights about comparison models that could inform sequence evaluation tasks for reinforcement learning, human skill assessment, and model evaluation.

While previous AI Scientist systems can generate novel findings, they often lack the focus to produce scientifically valuable contributions that address pressing human-defined challenges. We introduce DeepScientist, a system designed to overcome this by conducting goal-oriented, fully autonomous scientific discovery over month-long timelines. It formalizes discovery as a Bayesian Optimization problem, using a cumulative Findings Memory to intelligently balance the exploitation of promising avenues with the exploration of novel hypotheses. Consuming over 20,000 GPU hours, the system generated about 5,000 unique ideas and experimentally validated approximately 1100, ultimately surpassing human-designed 2025 state-of-the-art (SOTA) methods on three frontier AI tasks by 183.7\%, 1.9\%, and 7.9\%. Crucially, this was achieved by autonomously redesigning core methodologies, not merely recombining existing techniques. In a striking demonstration, the system achieved progress on AI text detection in just two weeks that is comparable to three years of cumulative human research. This work provides the first large-scale evidence of an AI achieving discoveries that progressively surpass human SOTA on scientific tasks, producing valuable findings that genuinely push the frontier forward.

Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accuracy; yet existing methods suffer from objective entanglement that conflates competing goals in single loss functions and lack human preference alignment. We introduce **PrismAudio**, the first framework to integrate Reinforcement Learning into V2A generation with specialized Chain-of-Thought (CoT) planning. Our approach decomposes monolithic reasoning into four specialized CoT modules (Semantic, Temporal, Aesthetic, and Spatial CoT), each paired with targeted reward functions. This CoT-reward correspondence enables **multidimensional RL optimization** that guides the model to jointly generate better reasoning across all perspectives, solving the objective entanglement problem while preserving interpretability. To make this optimization computationally practical, we propose **Fast-GRPO**, which employs hybrid ODE-SDE sampling that dramatically reduces the training overhead compared to existing GRPO implementations. We also introduce **AudioCanvas**, a rigorous benchmark that is more distributionally balanced and covers more realistically diverse and challenging scenarios than existing datasets, with 300 single-event classes and 501 multi-event samples. Experimental results demonstrate that PrismAudio achieves state-of-the-art performance across all four perceptual dimensions on both the in-domain VGGSound test set and out-of-domain AudioCanvas benchmark. The project page is available at~\url{https://PrismAudio.github.io}.

Cross-modal matching tasks have achieved significant progress, yet remain limited by mini-batch subsampling and scarce labelled data. Existing objectives, such as contrastive losses, focus solely on instance-level alignment and implicitly assume that all feature dimensions contribute equally. Under small batches, this assumption amplifies noise, making alignment signals unstable and biased. We propose DART (Dual-level Alignment via Robust Transport), a framework that augments instance-level alignment with feature-level regularization based on the Unbalanced Wasserstein Distance (UWD). DART constructs reliability-weighted marginals that adaptively reweight channels according to their cross-modal consistency and variance statistics, highlighting stable and informative dimensions while down-weighting noisy or modality-specific ones. From a theoretical perspective, we establish concentration bounds showing that instance-level objectives scale with the maximum distance across presumed aligned pairs, while feature-level objectives are governed by the Frobenius norm of the transport plan. By suppressing unmatched mass and sparsifying the transport plan, DART reduces the effective transport diameter and tightens the bound, yielding greater robustness under small batches. Empirically, DART achieves state-of-the-art retrieval performance on three audio-text benchmarks, with particularly strong gains under scarce labels and small batch sizes.

Video scene segmentation aims to detect semantically coherent boundaries in long-form videos, bridging the gap between low-level visual signals and high-level narrative understanding. However, existing methods primarily rely on visual similarity between adjacent shots, which makes it difficult to accurately identify scene boundaries, especially when semantic transitions do not align with visual changes. In this paper, we propose a novel approach that incorporates production-level metadata, specifically genre conventions and shot duration patterns, into video scene segmentation. Our main contributions are three-fold: (1) we leverage textual genre definitions as semantic priors to guide shot-level representation learning during self-supervised pretraining, enabling better capture of narrative coherence; (2) we introduce a duration-aware anchor selection strategy that prioritizes shorter shots based on empirical duration statistics, improving pseudo-boundary generation quality; (3) we propose a test-time shot splitting strategy that subdivides long shots into segments for improved temporal modeling. Experimental results demonstrate state-of-the-art performance on MovieNet-SSeg and BBC datasets. We introduce MovieChat-SSeg, extending MovieChat-1K with manually annotated scene boundaries across 1,000 videos spanning movies, TV series, and documentaries.

Deep stereo disparity estimation has long been dominated by a \textbf{matching-centric paradigm}, built on constructing cost volumes and iteratively refining local correspondences. Despite its success, this paradigm exhibits an intrinsic vulnerability: visual ambiguities from occlusion or non-Lambertian surfaces invevitably induce errorneous matches that refinement cannot recover. This paper introduces \textbf{DispViT}, a new architecture that establishes a \textbf{regression-centric paradigm}. Instead of explicit matching, DispViT directly regresses disparity from tokenized binocular representations using a single-stream Vision Transformer. This is enabled by a set of lightweight yet critical designs, such as a probability-based disparity parameterization for stable training and an asymmetrically initialized stereo tokenizer for effective view distinction. To better align the two views during stereo tokenization, we introduce a novel shift-embedding mechanism that encodes different disparity shifts into channel groups, preserving geometric cues even under large view displacements. A lightweight refinement module then sharpens the regressed disparity map for fine-grained accuracy. By prioritizing holistic regression over explicit matching, DispViT streamlines the stereo pipeline while improving robustness and efficiency. Experiments on standard benchmarks show that our approach achieves state-of-the-art accuracy, with strong resilience to matching ambiguities and wide disparity ranges. Code will be released.

We present NOVA3R, an effective approach for non-pixel-aligned 3D reconstruction from a set of unposed images, in a feed-forward manner. Unlike pixel-aligned methods that tie geometry to per-ray predictions, our formulation learns a global, view-agnostic scene representation that decouples reconstruction from pixel alignment. This addresses two key limitations in pixel-aligned 3D: (1) it recovers both visible and invisible regions with a complete scene representation, and (2) it produces physically plausible geometry with fewer duplicated structures in overlapping regions. To achieve this, we introduce a scene-token mechanism that aggregates information across unposed images and a diffusion-based 3D decoder that reconstructs complete, non-pixel-aligned point clouds. Extensive experiments on both scene-level and object-level datasets demonstrate that NOVA3R outperforms state-of-the-art methods in terms of reconstruction accuracy and completeness.

High dynamic range (HDR) video can be reconstructed from low dynamic range (LDR) sequences with alternating exposures. However, most existing methods overlook the degradations (e.g., noise and blur) in LDR frames, focusing only on the brightness and position differences between them. To address this gap, we propose DeAltHDR, a novel framework for high-quality HDR video reconstruction from degraded sequences. Our framework addresses two key challenges. First, noisy and blurry contents complicate inter-frame alignment. To tackle this, we propose a flow-guided masked attention that leverages optical flow for a dynamic sparse cross-attention computation, achieving superior performance while maintaining efficiency. Notably, its controllable attention ratio allows for adaptive inference costs. Second, the lack of real-world paired data hinders practical deployment. We overcome this with a two-stage training paradigm: the model is first pre-trained on our newly introduced synthetic paired dataset and subsequently fine-tuned on unlabeled real-world videos via a proposed self-supervised method. Experiments show our method outperforms state-of-the-art ones. The datasets and code will be publicly available.

Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning its predictions should be both explainable and faithful to the visual content. Specifically, it should satisfy two key properties: 1) Verifiable, by producing interpretable reasoning that justifies its predictions and clearly links them to visual evidence; and 2) Trustworthy, by learning to abstain when no object in the image satisfies the given expression. However, most methods treat referring as a direct bounding box prediction task, offering limited interpretability and struggling to reject expressions with no matching object. In this work, we propose Rex-Thinker, a model that formulates object referring as an explicit CoT reasoning task. Given a referring expression, we first identify all candidate object instances corresponding to the referred object category. Rex-Thinker then performs step-by-step reasoning over each candidate to assess whether it matches the given expression, before making a final prediction. To support this paradigm, we construct a large-scale CoT-style referring dataset named HumanRef-CoT by prompting GPT-4o on the HumanRef dataset. Each reasoning trace follows a structured planning, action, and summarization format, enabling the model to learn decomposed, interpretable reasoning over object candidates. We then train Rex-Thinker in two stages: a cold-start supervised fine-tuning phase to teach the model how to perform structured reasoning, followed by GRPO-based RL learning to improve accuracy and generalization. Experiments show that our approach outperforms standard baselines in both precision and interpretability on in-domain evaluation, while also demonstrating improved ability to reject hallucinated outputs and strong generalization in out-of-domain settings.

Recent advances in multimodal learning have achieved remarkable success across diverse vision–language tasks. However, such progress heavily relies on large-scale image–text datasets, making training costly and inefficient. Prior efforts in dataset filtering and pruning attempt to mitigate this issue, but still require relatively large subsets to maintain performance and fail under very small subsets. Dataset distillation offers a promising alternative, yet existing multimodal dataset distillation methods require full-dataset training and joint optimization of image pixels and text features, making them architecture-dependent and limiting cross-architecture generalization. To overcome this, we propose a learning-free dataset distillation framework that eliminates the need for large-scale training and optimization while enhancing generalization across architectures. Our method uses CLIP to extract aligned image–text embeddings, obtains prototypes, and employs an unCLIP decoder to synthesize images, enabling efficient and scalable multimodal dataset distillation. Extensive experiments demonstrate that our approach consistently outperforms optimization-based dataset distillation and subset selection methods, achieving state-of-the-art cross-architecture generalization.

Historically, neuroscience has progressed by fragmenting into specialized domains, each focusing on isolated modalities, tasks, or brain regions. While fruitful, this approach hinders the development of a unified model of cognition. Here, we introduce TRIBE, the first deep neural network trained to predict brain responses to stimuli across multiple modalities, cortical areas and individuals. By combining the pretrained representations of text, audio and video foundational models and handling their time-evolving nature with a transformer, our model can precisely model the spatial and temporal fMRI responses to videos, achieving the first place in the Algonauts 2025 brain encoding competition with a significant margin over competitors. Ablations show that while unimodal models can reliably predict their corresponding cortical networks (e.g. visual or auditory networks), they are systematically outperformed by our multimodal model in high-level associative cortices. Currently applied to perception and comprehension, our approach paves the way towards building an integrative model of representations in the human brain. Our code is available at \url{https://anonymous.4open.science/r/algonauts-2025-C63E}.

Sound source localization (SSL) is a fundamental task in spatial audio understanding, yet most deep neural network-based methods are constrained by fixed array geometries and predefined directional grids, limiting generalizability and scalability. To address these issues, we propose _audio-geometry-grid representation learning_ (AGG-RL), a novel framework that jointly learns audio-geometry and grid representations in a shared latent space, enabling both geometry-invariant and grid-flexible SSL. Moreover, to enhance generalizability and interpretability, we introduce two physics-informed components: a _learnable non-uniform discrete Fourier transform_ (LNuDFT), which optimizes the dense allocation of frequency bins in a non-uniform manner to emphasize informative phase regions, and a _relative microphone positional encoding_ (rMPE), which encodes relative microphone coordinates in accordance with the nature of inter-channel time differences. Experiments on synthetic and real datasets demonstrate that AGG-RL achieves superior performance, particularly under unseen conditions. The results highlight the potential of representation learning with physics-informed design towards a universal solution for spatial acoustic scene understanding across diverse scenarios.

We introduce a novel formulation for continuous space-time video super-resolution. Instead of decoupling the representation of a video sequence into separate spatial and temporal components and relying on brittle, explicit frame warping for motion compensation, we encode video as a continuous, spatio-temporally coherent 3D Video Fourier Field (VFF). That representation offers three key advantages: (1) it enables cheap, flexible sampling at arbitrary locations in space and time; (2) it is able to simultaneously capture fine spatial detail and smooth temporal dynamics; and (3) it offers the possibility to include an analytical, Gaussian point spread function in the sampling to ensure aliasing-free reconstruction at arbitrary scale. The coefficients of the proposed, Fourier-like sinusoidal basis are predicted with a neural encoder with a large spatio-temporal receptive field, conditioned on the low-resolution input video. Through extensive experiments, we show that our joint modeling substantially improves both spatial and temporal super-resolution and sets a new state of the art for multiple benchmarks: across a wide range of upscaling factors, it delivers sharper and temporally more consistent reconstructions than existing baselines, while being computationally more efficient. Code will be published upon acceptance.