ICML 2026 论文列表

Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine object category. In this work, we formalize *text-driven amodal 3D generation*, where text prompts steer the completion of unseen regions while strictly preserving input observation. Crucially, we identify that these objectives demand distinct control granularities: rigid control for the observation versus relaxed structural control for the prompt. To this end, we propose **RelaxFlow**, a training-free dual-branch framework that decouples control granularity via a Multi-Prior Consensus Module and a Relaxation Mechanism. Theoretically, we prove that our relaxation is equivalent to applying a low-pass filter on the generative vector field, which suppresses high-frequency instance details to isolate geometric structure that accommodates the observation. To facilitate evaluation, we introduce two diagnostic benchmarks, **ExtremeOcc-3D** and **AmbiSem-3D**. Extensive experiments demonstrate that RelaxFlow successfully steers the generation of unseen regions to match the prompt intent without compromising visual fidelity. Code and datasets will be released.

Most deep video codecs emphasize low-level motion modeling and remain largely semantics-agnostic, which can degrade perceptual quality in complex scenes. We propose **MoVie**, a **M**ultim**o**dal **Vi**d**e**o compression framework built on a Text-guided Video Transformer–CNN Mixed block (*Text-VideoTCM*). MoVie adopts a video-centric architecture that jointly models local spatial structures and temporal dynamics via window-based processing, delivering a favorable computation--perception trade-off. To incorporate semantics, we introduce dual-stage text fusion with *Extractor* and *Injector* modules. We further present history-conditioned coding that leverages both previous and aggregated historical frames, and a spatial--channel factorized entropy model that estimates probabilities over spatial neighborhoods and channel groups for adaptive bit allocation. Together, these designs reduce redundancy and improve rate control and temporal coherence, yielding reconstructions at low bitrates. On UVG and MCL-JCV, MoVie achieves **$-$50.23\%** BD-rate for FID and **$-$14.64\%** for LPIPS (VGGNet) relative to HM, while requiring only **55.76\%** of DCVC-FM's per-pixel kMACs. A human perceptual study further confirms consistent subjective preference over strong baselines.

Does natural language text have an intrinsic curvature? Language is increasingly modeled in curved geometries—hyperbolic spaces for hierarchy, mixed-curvature manifolds for compositional structure—yet a basic scientific question remains unresolved: what does curvature mean for text itself, in a way that is native to language rather than an artifact of the embedding space we choose? We argue that text does indeed have curvature, and show how to detect it, define it, and use it. To this end, we propose Texture, a text-native, word-level discrete curvature signal, and make three contributions. (a) Existence: We provide empirical and theoretical certificates that semantic inference in natural corpora is non-flat. (b) Definition: We define Texture as a signed two-axis curvature of the word-in-context belief field—the differential of reconciliation between prefix and suffix—measuring, via a debiased Schrödinger transport divergence, whether adding context from one side contracts the semantic effect of context from the other side (focus, positive) or expands it into competing continuations (fan-out, negative). (c) Utility: Texture is actionable: it serves as a general-purpose measurement and control primitive enabling geometry without geometric training; we instantiate it on two representative tasks, improving long-context inference through curvature-guided compression and retrieval-augmented generation through curvature-guided routing. Together, our results establish a text native curvature paradigm, making Texture practically useful.

Recent text-to-video diffusion models can synthesize visually compelling clips from natural language prompts. However, practical applications increasingly demand long-form videos with evolving narratives and persistent identity. A common solution is autoregressive generation, where the video is produced clip by clip over long horizons, yet coherence often degrades as errors compound. In this work, we study long-video generation under an autoregressive setting, where videos are synthesized clip by clip over long horizons. Despite strong short-clip quality, existing approaches often suffer from semantic drift, motion decay, and appearance instability as the sequence grows. We present DynaMem, a unified framework that improves long-horizon coherence via three components: Semantic-Adaptive Hierarchical Memory for long-range semantic preservation, Motion-Prioritized Optimization for motion-coherent learning, and Reference-Anchored Perceptual Alignment for stabilizing appearance. Extensive experiments show that DynaMem produces more consistent semantics, stronger temporal dynamics, and more stable appearance on long videos compared to competitive baselines.

Text-to-motion (T2M) generation has become a fundamental task, yet existing evaluation metrics often fail to capture whether a generated motion semantically matches its text description. We propose VeMo, a zero-shot evaluation framework that renders generated human motions into videos and uses pretrained video-language models (VLMs) to assess text-motion alignment. Instead of training an evaluator on scarce motion-specific labels, VeMo transfers the semantic reasoning ability of VLMs to T2M evaluation through normalized likelihood-based scoring. To reduce the effect of 3D-to-2D projection ambiguity, we introduce an entropy-driven uncertainty analysis for identifying reliable rendered views. To address the lack of rigorous standards in the field, we further contribute a test-only and human-annotated meta-evaluation benchmark, covering motions generated by multiple representative T2M models. Extensive experiments show that VeMo correlates better with human judgments than existing reference-based and reference-free metrics. Additional analyses on view selection, rendering protocols, textual prompt robustness, and computational trade-offs characterize both the promise and limitations of VLM-based T2M evaluation.

Expanding multimodal representations to novel modalities is constrained by reliance on largescale paired datasets (e.g., text–image, text–audio, text–3D, text–molecule), which are costly and often infeasible in domains requiring expert annotation such as medical imaging and molecular analysis. We introduce TextME, to the best of our knowledge the first modality expansion framework based on text-only training, projecting diverse modalities into LLM embedding space as a unified anchor. Our approach exploits the geometric structure of pretrained contrastive encoders to enable zero-shot cross-modal transfer using only text descriptions, without paired supervision. We empirically validate that such consistent modality gaps exist across image, video, audio, 3D, X-ray, and molecular domains, demonstrating that text-only training can preserve substantial performance of pretrained encoders. We further show that our framework enables emergent cross-modal retrieval between modality pairs not explicitly aligned during training (e.g., audioto-image, 3D-to-image). These results establish text-only projection training as a practical alternative to paired supervision for modality expansion. The code is available at https://soyeonhh.github.io/TextME/.

Recent advancements in large multimodal models (LMMs) have driven substantial progress in both text-to-video (T2V) generation and video-to-text (V2T) interpretation tasks. However, current AI-generated videos (AIGVs) still exhibit limitations in terms of perceptual quality and text-video alignment. To this end, we present **AIGVE-60K**, a comprehensive dataset and benchmark for AI-Generated Video Evaluation, which features **(i)** comprehensive tasks, encompassing 3,050 extensive prompts across 20 fine-grained task dimensions, **(ii)** the largest human annotations, including 120K mean-opinion scores (MOSs) and 60K question-answering (QA) pairs annotated on 58,500 videos generated from 30 T2V models, and **(iii)** bidirectional benchmarking and evaluating for both T2V generation and V2T interpretation capabilities. Based on AIGVE-60K, we propose **LOVE**, a LMM-based metric for AIGV Evaluation from multiple dimensions including perceptual preference, text-video correspondence, and task-specific accuracy. Building upon LOVE, we further introduce **LOVE-Reward** to optimize T2V models through reinforcement learning, effectively enhancing both the perceptual quality and text-video correspondence of generated videos. Comprehensive experiments demonstrate that LOVE achieves state-of-the-art performance and generalizes effectively to various AIGV benchmarks. LOVE-Reward significantly improves video generation quality. These findings highlight the effectiveness of the AIGVE-60K dataset and our proposed methods. The database and codes are available at https://github.com/IntMeGroup/LOVE.

To deploy large language models (LLMs) in high-stakes application domains that require substantively accurate responses to open-ended prompts, we need reliable, computationally inexpensive methods that assess the trustworthiness of long-form responses generated by LLMs. However, existing approaches often rely on claim-by-claim fact-checking, which is computationally expensive and brittle in long-form responses to open-ended prompts. In this work, we introduce semantic isotropy---the degree of uniformity across normalized text embeddings on the unit sphere---and use it to assess the trustworthiness of long-form responses generated by LLMs. To do so, we generate several long-form responses, embed them, and estimate the level of semantic isotropy of these responses as the angular dispersion of the embeddings on the unit sphere. We find that higher semantic isotropy---that is, greater embedding dispersion---reliably signals lower factual consistency across samples. Our approach requires no labeled data, no fine-tuning, and no hyperparameter selection, and can be used with open- or closed-weight embedding models. Across multiple domains, our method consistently outperforms existing aggregate trust signals in predicting nonfactuality using only a handful of samples, offering a practical, low-cost first-pass signal that complements claim-level verification in real-world LLM workflows.

Long-video temporal reasoning remains a bottleneck for Large Video Language Models (LVLMs). Existing reinforcement-learning approaches reward only final-answer correctness, so they cannot distinguish answers reached through grounded reasoning from those reached through fabricated chronology; the intermediate temporal claims that constitute the reasoning are never verified. We trace this gap to a structural correspondence between two kinds of traces: a video has its own temporal trace, an ordered sequence of how events unfold, while a model's answer is built up through a reasoning trace, an ordered sequence of intermediate temporal claims. Correct reasoning requires the latter to mirror the former, claim by claim. We act on this correspondence with two contributions. We introduce Temporal Reasoning Traces (TRT), a structured index of a video's ordered event chains that exposes a small set of deterministic verification primitives, materializing the temporal trace as a programmatically queryable object. We then propose temporal-enhanced GRPO, a reinforcement-learning procedure whose reward decomposes into per-block components, each computed by a TRT primitive on a typed think block of the reasoning trace. Because the reward is fully symbolic, fabricated temporal claims are caught at the per-claim level rather than masked by a correct final answer. Across long-video reasoning benchmarks, our model achieves state-of-the-art performance, with the largest gains on out-of-domain reasoning tasks such as Video-Holmes, CG-Bench-Reasoning, and VRBench.

Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and how it is organized. A _de facto_ standard approach to video tokenization is to represent a video as a spatiotemporal 3D grid of tokens, each capturing local information from the original signal. This requires the downstream model, e.g., a text-to-video model, to learn to predict all low-level details "pixel-by-pixel" irrespective of the video's inherent complexity, leading to high learning complexity. __We present _VideoFlexTok_, which represents videos with a variable-length sequence of tokens structured in a coarse-to-fine manner__, where the first tokens (emergently) capture information such as semantics and motion, and later tokens add fine-grained details. The generative flow decoder enables realistic video reconstructions from any token count. This representation structure allows adapting the token count to downstream needs and encoding videos longer than the baselines within the same budget. We evaluate VideoFlexTok on class- and text-to-video generative tasks and show that it yields more efficient training than 3D grid tokens, _achieving comparable generation quality (gFVD and ViCLIP Score) with a 5x smaller model (1.1B vs 5.2B)._ Finally, we show how _VideoFlexTok can enable long video generation without prohibitive computational cost_ by training a text-to-video model on 10-second 81-frame videos with only 672 tokens, 8x fewer than a comparable 3D grid tokenizer.

Verbal logic and visual mental simulation are two essential components of human intelligence. Modern Large Language Models (LLMs) have demonstrated strong verbal reasoning capabilities through textual Chain-of-Thought (CoT) reasoning. In contrast, current Video Generation Models (VGMs) struggle with visual reasoning tasks such as spatial planning. We attribute this limitation to two fundamental gaps: (i) VGMs are predominantly trained on general-purpose video corpora emphasizing perceptual fidelity over visual reasoning, leaving reasoning abilities underdeveloped; (ii) most VGMs generate videos in a single pass without mechanisms to explore alternative reasoning trajectories and to revise intermediate errors. Motivated by these limitations, we introduce **ReaForest**, a framework that fosters the reasoning capacity of VGMs in spatial planning through both training-time activation and inference-time scaling. ReaForest comprises three key components: **(1)** ReaGen-27k, a dataset covering diverse spatial planning tasks that require multi-step reasoning, which activates basic reasoning capabilities of VGMs for spatial planning; **(2)** Reflective Entropy-Aware Test-Time Scaling (ReaTTS), an inference framework that evolves multiple reasoning branches while enabling failure recovery; **(3)** Hierarchical constraint verification, which provides actionable feedback for ReaTTS based on decomposed constraints. Extensive experiments demonstrate that ReaForest substantially surpasses advanced textual reasoning models (e.g., Gemini-2.5-Pro) and video generation models (e.g., Sora-2). ReaForest exhibits emergent properties including self-correction, parallel thinking, and scalable reasoning, advancing VGMs toward human-like visual mental simulation.

Large-scale, high-quality dynamic 3D (4D) assets are essential for learning physically grounded representations, but remain costly to capture and annotate at scale. This limits the viability of supervised 4D learning and motivates zero-shot text-to-4D generation leveraging pretrained diffusion priors. To model complex dynamics, prior methods typically adopt implicit 3D representations (e.g., NeRFs or 3DGS) for their deformation capacity. However, their implicit nature provides limited control over surface topology, which hinders high-fidelity geometry and makes temporally coherent surface reconstruction challenging. To address these limitations, we explore zero-shot text-to-4D mesh generation. However, a structural mismatch arises when combining diffusion-based guidance with topology-constrained meshes: the guidance is noisy and spatially inconsistent, while meshes impose severe topological constraints, making direct vertex-level deformation unstable. In this paper, we introduce TextMesh4D, the first zero-shot framework for text-to-4D that directly generates dynamic meshes by addressing the above challenge at two complementary levels. Geometrically, we shift deformation modeling from vertices to faces via a Jacobian Deformation Field (JDF), enabling topology-aware surface reconstruction through an integrability-enforcing integration formulation. Semantically, we propose a Local-Global Semantic Regularizer (LGSR) that preserves identity over time by jointly constraining local deformation plausibility and global shape consistency. Extensive experiments demonstrate state-of-the-art temporal consistency, structural fidelity, and visual quality, while remaining efficient on a single 24GB GPU.

Diffusion models have achieved state-of-the-art performance in generating images, audio, and video, but their adaptation to text remains challenging due to its discrete nature. Prior approaches either apply Gaussian diffusion in continuous latent spaces, which inherits semantic structure but struggles with token decoding, or operate in categorical simplex space, which respect discreteness but disregard semantic relation between tokens. In this paper, we propose Smoothing Diffusion on Token Embeddings (Smoothie), a novel diffusion method that combines the strengths of both approaches by progressively smoothing token embeddings based on semantic similarity. This technique enables gradual information removal while maintaining a natural decoding process. Experimental results on several sequence-to-sequence and unconditional generation tasks demonstrate that Smoothie outperforms existing diffusion-based models in generation quality. Furthermore, ablation studies show that our proposed diffusion space yields better performance than both the standard embedding space and the categorical simplex.

Video subtitle removal is essential for content localization and media re-editing, yet existing mask-guided diffusion methods face critical limitations: training inefficiency requiring extensive annotations and full model fine-tuning, inference complexity demanding explicit mask sequences, and static prior utilization unable to adapt to quality variations. We present CLEAR (Context-aware Learning for End-to-end Adaptive subtitle Removal), a lightweight adapter-based framework addressing these challenges through three technical innovations. First, self-supervised prior learning (Stage I) extracts occlusion guidance from video pairs using pixel differences as weak supervision, eliminating annotation dependency while learning generalizable subtitle features across languages. Second, LoRA-based adaptive refinement (Stage II) enables parameter-efficient training that preserves pre-trained visual priors while achieving true mask-free end-to-end inference without external detection modules. Third, adaptive focal weighting dynamically adjusts prior influence based on local quality assessment, effectively handling diverse subtitle styles and noisy guidance signals. Extensive experiments demonstrate CLEAR's superior performance in multilingual subtitle removal while requiring only 0.77% trainable parameters, establishing a new paradigm for efficient video text removal without inference-time mask dependencies.

Diffusion transformers have achieved remarkable success in high-quality video generation, yet their reliance on spatiotemporal 3D full attention incurs prohibitive computational cost due to the quadratic complexity of attention. Block sparse attention is a common approach to mitigate this by focusing computation on important regions. However, attention maps in DiTs exhibit inherently dynamic and fine-grained sparsity, which causes existing block sparse attention methods to degrade significantly in quality, especially at high sparsity ratios. In this paper, we revisit block sparse attention and derive a theoretical lower bound on attention recall to characterize the key factors governing its effectiveness. Guided by these insights, we propose DFSAttn, a training-free sparse attention framework that enables dynamic, fine-grained sparsification efficiently. DFSAttn incorporates three core designs: Hilbert curve-based token reordering to achieve fine-grained sparsity while preserving efficient GPU execution, hierarchical block scoring for accurate block importance estimation, and sparse mask caching with adaptive ratios to balance accuracy and efficiency. Experimental results demonstrate that DFSAttn consistently outperforms prior methods under high sparsity, achieving up to 2.1$\times$ end-to-end speedup while maintaining high generation quality. Our code is open-sourced and available at https://github.com/jessica-hujie/DFSAttn.

While Large Language Models (LLMs) have achieved remarkable success across diverse tasks, they remain vulnerable to jailbreak attacks, which pose significant risks to their secure deployment. Driven by their inherent token-by-token autoregressive inference, LLMs exhibit semantic representations that lack robustness against spatially structured perturbations, thereby rendering current output-guardrail safety mechanisms penetrable. Exploiting the Transformer's spatial weakness, we propose SpatialJB to disrupt the model’s output generation process, allowing harmful content to bypass guardrails without detection. Comprehensive experiments on leading LLMs demonstrate that SpatialJB achieves a nearly 100\% ASR and consistently maintains a success rate exceeding 75\% even against advanced output guardrails like the OpenAI Moderation API, outperforming current jailbreak techniques by a significant margin. While **SpatialJB** advances LLM safety research by exposing guardrail weaknesses and highlighting spatial semantics, we also propose and evaluate baseline defense strategies to prevent its potential misuse. You can click [Video Link](https://1drv.ms/v/s!ApaP6YaJA87pgk-Rk7ZCvPeYcIZa?e=J8kbg0) and [Code Link](https://github.com/DongFangShenWa/SpatialJailbreak.git) to see our demo presentation and code.

Recent advances in video diffusion models have significantly improved visual quality, yet ultra-high-resolution (UHR) video generation remains a formidable challenge due to the compounded difficulties of motion modeling, semantic planning, and detail synthesis. To address these limitations, we propose \textbf{LUVE}, a \textbf{L}atent-cascaded \textbf{U}HR \textbf{V}ideo generation framework built upon dual frequency \textbf{E}xperts. LUVE employs a three-stage architecture comprising low-resolution motion generation for motion-consistent latent synthesis, video latent upsampling that performs resolution upsampling directly in the latent space to mitigate memory and computational overhead, and high-resolution content refinement that integrates low-frequency and high-frequency experts to jointly enhance semantic coherence and fine-grained detail generation. Extensive experiments demonstrate that our LUVE achieves superior photorealism and content fidelity in UHR video generation, and comprehensive ablation studies further validate the effectiveness of each component.

Modern visual object trackers show impressive results on general targets, yet their performance drops substantially when dealing with scene text. Although currently underexplored, tracking text in videos is essential for dynamic text manipulations such as segmentation, removal, and editing. To fill this gap, this paper formalizes this specific task as Scene Text Tracking and presents the first systematic work for it. We identify three primary challenges in this task: 1) severe geometric distortions from perspective shifts, 2) high visual ambiguity across different instances, and 3) high sensitivity to fine-grained structural details. To address these issues, we propose SymTrack, a unified detection-free framework with synergistic dual-branch design. It integrates a Cross-Expert Calibration mechanism to reduce semantic bias, along with a Predictive Token Rectification mechanism to correct structural imbalances, complemented by an Adaptive Inference Engine that stabilizes predictions under motion constraints. Considering the lack of dedicated benchmarks for this task, we utilize three datasets from video text spotting to construct a benchmark with high-quality annotations. Extensive experiments demonstrate that SymTrack sets the new state-of-the-art on all three benchmarks, outperforming previous best trackers by up to 11.97\% AUC on $ \text{BOVText}_{\text{SOT}} $. Overall, our work promotes efficient and thorough text tracking, paving the way toward more generalized video text manipulation.

Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant strides in maintaining temporal consistency, they are predominantly confined to non-interactive scenarios where models merely showcase garments. This limitation overlooks a crucial aspect of real-world apparel presentation: active human-garment interaction. To bridge this gap, we introduce and formalize a new challenging task: Interactive Video Virtual Try-On (Interactive VVT), where subjects in the video actively engage with their clothing (e.g., pulling a hem or unzipping a jacket). This task introduces unique challenges beyond simple texture preservation, including: (1) resolving the semantic ambiguity of interactions from standard pose information, and (2) learning complex garment deformations from video where interactive moments are sparse and brief. To address these challenges, we propose **iTryOn**, a novel framework built upon a large-scale video diffusion Transformer. iTryOn pioneers a multi-level interaction injection mechanism to guide the generation of complex dynamics. At the spatial level, we introduce a garment-agnostic 3D hand prior to provide fine-grained guidance for precise hand-garment contact, effectively resolving spatial ambiguity. At the semantic level, iTryOn leverages global captions for overall context and time-stamped action captions for localized interactions, synchronized via our novel Action-aware Rotational Position Embedding (A-RoPE). Furthermore, we design an action-aware constraint loss to stabilize training and focus the learning process on these critical interactive frames. To facilitate research and evaluation, we construct VVT-Interact, the first large-scale dataset for this task, and propose a novel interaction-aware evaluation metric to quantify the semantic fidelity of interactions. Extensive experiments demonstrate that iTryOn not only achieves state-of-the-art performance on traditional VVT benchmarks but also establishes a commanding lead in the new interactive setting, marking a significant step towards more dynamic and controllable virtual try-on experiences.