ICLR 2026 论文列表

Temporally localizing user-queried events through natural language is a crucial capability for video models. Recent methods predominantly adapt video LLMs to generate event boundary timestamps for temporal localization tasks, which struggle to leverage LLMs' pre-trained semantic understanding capabilities due to the uninformative nature of timestamp outputs. In this work, we explore a timestamp-free, semantic-oriented framework that fine-tunes video LLMs using two generative learning tasks and one discriminative learning task. We first introduce a structural token generation task that enables the video LLM to recognize the temporal structure of input videos based on the input query. Through this task, the video LLM generates a sequence of special tokens, called structural tokens, which partition the video into consecutive segments and categorize them as either target events or background transitions. To enhance precise recognition of event segments, we further propose a query-focused captioning task that enables the video LLM to extract fine-grained event semantics that can be effectively utilized by the structural tokens. Finally, we introduce a structural token grounding module driven by contrastive learning to associate each structural token with its corresponding video segment, achieving holistic temporal segmentation of the input video and readily yielding the target event segments for localization. Extensive experiments across diverse temporal localization tasks demonstrate that our proposed framework, MeCo, consistently outperforms methods relying on boundary timestamp generation, highlighting the potential of a semantic-driven approach for temporal localization with video LLMs.

Visual geolocalization, the task of predicting where an image was taken, remains challenging due to global scale, visual ambiguity, and the inherently hierarchical structure of geography. Existing paradigms rely on either large-scale retrieval, which requires storing a large number of image embeddings, grid-based classifiers that ignore geographic continuity, or generative models that diffuse over space but struggle with fine detail. We introduce an entity-centric formulation of geolocation that replaces image-to-image retrieval with a compact hierarchy of geographic entities embedded in Hyperbolic space. Images are aligned directly to country, region, subregion, and city entities through Geo-Weighted Hyperbolic contrastive learning by directly incorporating haversine distance into the contrastive objective. This hierarchical design enables interpretable predictions and efficient inference with 240k entity embeddings instead of over 5 million image embeddings on the OSV5M benchmark, on which our method establishes a new state-of-the-art performance. Compared to the current methods in the literature, it reduces mean geodesic error by 19.5\%, while improving the fine-grained subregion accuracy by 43\%. These results demonstrate that geometry-aware hierarchical embeddings provide a scalable and conceptually new alternative for global image geolocation.

While existing approaches address unpaired image-text matching by constructing cross-modal aligned knowledge, they often fail to identify semantically corresponding visual representations for Out-of-Distribution (OOD) words. Moreover, the distributional variance of visual representations associated with different words varies significantly, which negatively impacts matching accuracy. To address these issues, we propose a novel method namely Multimodal Aligned Semantic Knowledge (MASK), which leverages word embeddings as bridges to associate words with their corresponding prototypes, thereby enabling semantic knowledge alignment between the image and text modalities. For OOD words, the representative prototypes are constructed by leveraging the semantic relationships encoded in word embeddings. Beyond that, we introduce a prototype consistency contrastive loss to structurally regularize the feature space, effectively mitigating the adverse effects of variance. Experimental results on the Flickr30K and MSCOCO datasets demonstrate that MASK achieves superior performance in unpaired matching.

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.

Learning to control high-speed objects in dynamic environments represents a fundamental challenge in robotics. Table tennis serves as an ideal testbed for advancing robotic capabilities in dynamic environments. This task presents two fundamental challenges: it requires a high-precision vision system capable of accurately predicting ball trajectories under complex dynamics, and it necessitates intelligent control strategies to ensure precise ball striking to target regions. High-speed object manipulation typically demands advanced visual perception hardware capable of capturing rapid motion with exceptional temporal resolution. Drawing inspiration from Kahneman's dual-system theory, where fast intuitive processing complements slower deliberate reasoning, there exists an opportunity to develop more robust perception architectures that can handle high-speed dynamics while maintaining accuracy. To this end, we present \textit{\textbf{SpikePingpong}}, a novel system that integrates spike-based vision with imitation learning for high-precision robotic table tennis. We develop a cognitive-inspired Fast-Slow system architecture where System 1 provides rapid ball detection and preliminary trajectory prediction with millisecond-level responses, while System 2 employs spike-oriented neural calibration for precise hittable position corrections. For strategic ball striking, we introduce Imitation-based Motion Planning And Control Technology, which learns optimal robotic arm striking policies through demonstration-based learning. Experimental results demonstrate that \textit{\textbf{SpikePingpong}} achieves a remarkable 92\% success rate for 30 cm accuracy zones and 70\% in the more challenging 20 cm precision targeting. This work demonstrates the potential of cognitive-inspired architectures for advancing robotic capabilities in time-critical manipulation tasks.

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.

Stochastic differential equation (SDE)-based generative models have achieved substantial progress in conditional generation via training-free differentiable loss-guided approaches. However, existing methodologies utilizing posterior sam- pling typically confront a substantial estimation error, which results in inaccurate gradients for guidance and leading to inconsistent generation results. To mitigate this issue, we propose that performing an additional backward denoising step and Monte-Carlo sampling (ABMS) can achieve better guided diffusion, which is a plug-and-play adjustment strategy. To verify the effectiveness of our method, we provide theoretical analysis and propose the adoption of a dual-evaluation frame- work, which further serves to highlight the critical problem of cross-condition interference prevalent in existing approaches. We conduct experiments across var- ious task settings and data types, mainly including conditional online handwritten trajectory generation, image inverse problems (inpainting, super resolution and gaussian deblurring), and molecular inverse design. Experimental results demon- strate that our approach consistently improves the quality of generation samples across all the different scenarios.

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.

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception capabilities, garnering significant attention. While numerous evaluation studies have emerged, assessing LVLMs both holistically and on specialized tasks, fine-grained image tasks—fundamental to computer vision—remain largely unexplored. To fill this gap, we introduce a comprehensive fine-grained evaluation benchmark, i.e., FG-BMK, comprising 1.01 million questions and 0.28 million images. Our evaluation systematically examines LVLMs from both human-oriented and machine-oriented perspectives, focusing on their semantic recognition and fine-grained feature representation capabilities. Through extensive experiments on twelve representative LVLMs/VLMs, we uncover key findings regarding the influence of training paradigms, modality alignment, perturbation susceptibility, and fine-grained category reasoning on task performance. This work provides critical insights into the limitations of current LVLMs and offers guidance for future data construction and model design in the development of more advanced LVLMs. Our code is open-source and available at https://anonymous.4open.science/r/FG-BMK-7B51.

Planning physically feasible dexterous hand manipulation is a central challenge in robotic manipulation and Embodied AI. Prior work typically relies on object-centric cues or precise hand-object interaction sequences, foregoing the rich, compositional guidance of open-vocabulary instruction. We introduce UniHM, the first framework for unified dexterous hand manipulation guided by free-form language commands. We propose a Unified Hand-Dexterous Tokenizer that maps heterogeneous dexterous-hand morphologies into a single shared codebook, improving cross-dexterous hand generalization and scalability to new morphologies. Our vision language action model is trained solely on human-object interaction data, eliminating the need for massive real-world teleoperation datasets, and demonstrates strong generalizability in producing human-like manipulation sequences from open-ended language instructions. To ensure physical realism, we introduce a physics-guided dynamic refinement module that performs segment-wise joint optimization under generative and temporal priors, yielding smooth and physically feasible manipulation sequences. Across multiple datasets and real-world evaluations, UniHM attains state-of-the-art results on both seen and unseen objects and trajectories, demonstrating strong generalization and high physical feasibility.

With the rapid advancement of data science, charts have evolved from simple numerical presentation tools to essential instruments for insight discovery and decision-making support. However, current chart data intelligence exhibits significant limitations in deep research capabilities, with existing methods predominantly addressing shallow tasks such as visual recognition or factual question-answering, rather than the complex reasoning and high-level data analysis that deep research requires. This limitation stems from two primary technical bottlenecks: at the training level, existing post-training techniques exhibit deficiencies in handling multi-dimensional reward signal interference and heterogeneous data gradient conflicts, preventing models from achieving balanced development across multiple capability dimensions; at the evaluation level, current methods remain limited to factual retrieval and basic computation, failing to assess end-to-end analytic reasoning and other deep research capabilities. To address the training challenge, we propose PRPO, which performs parallel optimization across reward dimensions and capability partitioning across data types, effectively disentangling conflicts between heterogeneous data and multi-dimensional reward signals while ensuring optimization stability. For the evaluation challenge, we construct MCDR-Bench based on the "error uniqueness principle," transforming subjective generation assessment into objective error identification through controllable error injection, enabling quantifiable evaluation of deep research capabilities. Experimental validation confirms that the proposed PRPO and MCDR-Bench jointly establish a unified framework that systematically advances chart deep research through enhanced collaborative training and objective evaluation.

Scaling up high-quality trajectory data has long been a critical bottleneck for developing human-like computer use agents. We introduce PC Agent-E, an efficient agent training framework that significantly reduces reliance on large-scale human demonstrations. Starting with just 312 human-annotated computer use trajectories, we further augment them by synthesizing diverse alternative action decisions with Claude 3.7 Sonnet. Trained on these enriched trajectories, our PC Agent-E model achieved a remarkable 141% relative improvement, and even surpassed the Claude 3.7 Sonnet by 10% on WindowsAgentArena-V2, an improved benchmark we also released. By integrating robust human computer use skills with automated AI data synthesis capabilities, our method not only brought substantial improvements over training on human trajectories alone, but also significantly surpassed direct distillation from Claude 3.7 Sonnet.

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.

We introduce SCUBA, a benchmark designed to evaluate computer-use agents on customer relationship management (CRM) workflows within the Salesforce platform. SCUBA contains 300 task instances derived from real user interviews, spanning three primary personas—platform administrators, sales representatives, and service agents. The tasks test a range of enterprise-critical abilities, including Enterprise Software UI navigation, data manipulation, workflow automation, information retrieval, and troubleshooting. To ensure realism, SCUBA operates in Salesforce sandbox environments with support for parallel execution and fine-grained evaluation metrics to capture milestone progress. We benchmark a diverse set of agents under both zero-shot and demonstration-augmented settings. We observed huge performance gaps in different agent design paradigm and gaps between the open-source model and the closed-source model. In the zero-shot setting, open-source model powered computer-use agents that have strong performance on related benchmarks like OSWorld only have less than 5\% success rate on SCUBA, while methods built on closed-source models can still have up to 39\% percent task success rate. In the demonstration-augmented settings, task success rates can be improved to 50\% while simultaneously reducing time and costs by 13\% and 16\%, respectively. These findings highlight both the challenges of enterprise tasks automation and the promise of agentic solutions. By offering a realistic benchmark with interpretable evaluation, SCUBA aims to accelerate progress in building reliable computer-use agents for complex business software ecosystems.

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.