Search arXiv⌕ Search

SEARCH · Search arXiv

Search Search arXiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

44 recordsLinked to original sources
arXiv2026

Adversarial Stress Testing of Outlier Detection in Subjective Image Quality Assessment

In subjective image and video quality assessment, observers rate or compare selected stimuli. Before calculating mean opinion scores (MOSs), unreliable ratings should be identified and handled as outliers. Several outlier-detection methods are available, including standardized procedures, but their comparative performance is often evaluated using only specific types of synthetic outliers such as random clickers. Such tests do not necessarily reveal the worst-case behavior of these methods. To address this gap, we introduce and demonstrate a general empirical worst-case framework for outlier-detection methods, with proof-of-concept adversarial attack generators for both discrete absolute category and continuous visual analog scale ratings. The attacks use optimization algorithms to identify ratings that maximize the discrepancy between the resulting MOS estimates and the ground truth. We apply the proposed framework to several hard and soft outlier-detection methods and demonstrate substantial differences in their worst-case reconstruction performance under adversarial stress. We also propose several low-complexity outlier-detection methods that achieve excellent empirical worst-case performance.

eess.IV↗
arXiv2026

Bernini: Latent Semantic Planning for Video Diffusion

Multimodal large language models (MLLMs) and diffusion models have each reached remarkable maturity: MLLMs excel at reasoning over heterogeneous multimodal inputs with strong semantic grounding, while diffusion models synthesize images and videos with photorealistic fidelity. We argue that these two families can be unified through a simple division of labor: MLLMs perform semantic planning, while diffusion models render pixels from high-level semantic guidance and low-level visual features. Building on this idea, we propose Bernini, a unified framework for video generation and editing. An MLLM-based planner predicts the target semantic representation directly in the ViT embedding space, and a DiT-based renderer synthesizes pixels conditioned on this plan, augmented by text features and, for editing, source VAE features for detail preservation. Because semantics serve as the interface, the planner and renderer can be trained separately and only lightly co-trained, preserving the pretrained strengths of both components while keeping training efficient. To better handle multiple visual inputs, we introduce Segment-Aware 3D Rotary Positional Embedding (SA-3D RoPE), and further incorporate chain-of-thought reasoning in the planner to better transfer understanding into generation. Bernini achieves state-of-the-art performance across a wide range of video generation and editing benchmarks, with the MLLM's pretrained understanding translating into strong generalization on challenging editing tasks.

cs.CV↗
arXiv2026

Beyond Appearance: Can Multimodal Large Language Models Exploit Vertical Structure for Remote Sensing Natural Scene Understanding?

Multimodal large language models (MLLMs) have advanced rapidly in remote-sensing analysis, yet existing evaluations remain predominantly 2D-centric. Because spectrally confused regions can appear nearly identical yet differ substantially in vertical structure, appearance alone is often insufficient for reliable semantic interpretation in natural scenes. Vertical structure therefore provides decision-critical physical evidence, yet whether current MLLMs can effectively perceive, ground, and utilize such geometric evidence remains underexplored. To bridge this gap, we introduce VertiCue-Bench, the first diagnostic benchmark that uses controlled interventions to probe whether vertical height evidence is actually perceived, grounded, and utilized, and we establish a three-stage evidence-utilization framework of Perception--Grounding--Utilization. By constructing a Representation Intervention Spectrum spanning multiple presentation and interaction modalities, including Raw Visual, Tool-assisted, and Oracle Text conditions, together with controlled counterfactual tests, we conduct an in-depth disentangled diagnosis across 10 state-of-the-art models. Our experiments reveal and formally characterize the Vertical Structure Utilization Gap. Although current models exhibit emerging geometric perception capabilities, they still struggle to accurately ground vertical evidence to relevant spatial entities and integrate it into high-level semantic decisions. This finding identifies a critical bottleneck in developing physically grounded and geometry-aware remote-sensing MLLMs.

cs.CV↗
arXiv2026

Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics

With the rapid proliferation of generative models on Machine Learning as a Service (MLaaS) platforms, reliably tracing the provenance of synthetic media without modifying generator architectures or parameters remains a major challenge. In this work, we propose a self-referential retrosynthesis framework for explainable AI provenance forensics under a fixed-generator setting. The framework leverages a jointly optimized encoder-decoder pair to implement a self-embedding mechanism that enables round-trip consistency verification. During inference, client inputs are first encoded and then processed by the generator to produce outputs with high visual fidelity. For forensic verification, the consistency between the resynthesized image and the query image is analyzed to determine whether the image originates from the target generative model. Our approach eliminates the need for watermark embedding or modifications to the generation process. Experimental results show that images generated from encoded inputs maintain visual quality comparable to original generator outputs, while decoded images reliably trace back to their corresponding source inputs. Furthermore, the framework provides interpretable evidence for generative content provenance, establishing a practical tool for explainable generative AI forensics.

cs.CR↗
arXiv2026

SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval

Recent advances in audio-language modeling have been driven by large-scale audio captioning datasets. However, existing datasets remain limited by low semantic diversity, generic descriptions lacking acoustic details, and one-to-one audio-caption mappings that poorly reflect the inherent ambiguity of auditory perception. We introduce SonicCaps, a large-scale audio captioning dataset comprising ~15M captions paired with ~700k audio clips, generated using a multi-modal large language model (Qwen3-Omni) conditioned on both audio and text. To explicitly promote diversity, we generate around 24 captions per audio via structured prompt engineering and few- shot generation, spanning main descriptions, rephrased variants (verbosity, style) and semantic tags. Human evaluation shows that SonicCaps is rated significantly higher than existing captioning datasets, with fine-grained analyses indicating that our captions are perceived as more descriptive and precise, which strongly correlates with quality judgments. Finally, training CLAP models on SonicCaps with a multi-caption sampling strategy consistently improves audio retrieval and zero-shot classification, with stronger generalization across public and commercial benchmarks. We release both SonicCaps and two specialized CLAP models on hugging face: https://huggingface.co/datasets/Zineb/SonicCaps.

cs.SD↗
arXiv2026

The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation

Joint audio-video generation models have made substantial progress in visual quality and audio-visual synchronization. However, they still provide limited control over when shot transitions occur and dialogue is spoken. This limitation constrains their application in script-driven content creation, where timing errors can undermine narrative coherence and the viewing experience. Current joint generators align video and audio representations on a shared temporal axis, yet the precise timing of shots and dialogue specified in a structured prompt is encoded only in the prompt's text representation and remains unaligned with the temporal coordinates of either modality. Consequently, video and audio may remain synchronized with each other while both fail to follow the script timeline. This mismatch motivates us to extend temporal alignment beyond video and audio to include the structured script. We therefore introduce Temporal Context Routing (TCR), which maps the script timing onto the shared temporal axis of video and audio generation and routes each prompt's guidance to the corresponding positions in both modalities. Compared with the baseline on 200 test scripts, TCR reduces Shot Boundary MAE by 96%, from 1.11 s to 0.042 s, and raises Dialogue Acc@0.5 s from 28.3% to 84.1%. TCR achieves these improvements while maintaining visual quality and audio-visual synchronization comparable to those of the baselines. A user study further shows that participants prefer TCR on all five evaluated dimensions.

cs.MM↗
arXiv2026

Taming Modality Entanglement in Continual Audio-Visual Segmentation

Recently, significant progress has been made in multi-modal continual learning, aiming to learn new tasks sequentially in multi-modal settings while preserving performance on previously learned ones. However, existing methods mainly focus on coarse-grained tasks, with limitations in addressing modality entanglement in fine-grained continual learning settings. To bridge this gap, we introduce a novel Continual Audio-Visual Segmentation (CAVS) task, aiming to continuously segment new classes guided by audio. Through comprehensive analysis, two critical challenges are identified: 1) multi-modal semantic drift, where a sounding objects is labeled as background in sequential tasks; 2) co-occurrence confusion, where frequent co-occurring classes tend to be confused. In this work, a Collision-based Multi-modal Rehearsal (CMR) framework is designed to address these challenges. Specifically, for multi-modal semantic drift, a Multi-modal Sample Selection (MSS) strategy is proposed to select samples with high modal consistency for rehearsal. Meanwhile, for co-occurence confusion, a Collision-based Sample Rehearsal (CSR) mechanism is designed, allowing for the increase of rehearsal sample frequency of those confusable classes during training process. Moreover, we construct three audio-visual incremental scenarios to verify effectiveness of our method. Comprehensive experiments demonstrate that our method significantly outperforms single-modal continual learning methods. Code can be seen at https://github.com/cqu-student/CAVS-CMR.

cs.MM↗
arXiv2026

Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges

Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural knowledge, and communicative intent rather than literal scene description. This survey focuses on visual humor understanding in single-image and multi-panel artifacts, while treating humor generation as an emerging downstream frontier. We position the literature against prior humor, sarcasm, and general MLLM surveys and organize it using a capability-centric hierarchy spanning recognition, interpretation and reasoning, and generation. Under this lens, we synthesize benchmark design, evaluation protocols, and modeling paradigms, tracing the field's shift from task-specific fusion models to large-model approaches based on multimodal alignment, evidence-grounded reasoning, and controlled generation. We conclude by highlighting the main barriers to progress: shortcut-prone evaluation, limited cultural and narrative coverage, weak evidence grounding, and unresolved safety and ownership concerns.

cs.CL↗
arXiv2026

EVEREST:Endogenous Vision-Language Reinforcement Reasoning Exploration for Urban Socio-Semantic Segmentation

Urban socio-semantic segmentation leverages digital and satellite imagery to provide critical spatial semantic information for downstream applications such as urban resource allocation. Although existing methods achieve high segmentation accuracy, they still suffer from inaccurate delineation of target boundaries. The underlying issue is that current models primarily rely on passively aggregated global cross-modal cues, lacking active exploration of the environment. To address this limitation, we propose the EVEREST model, which adopts an egocentric exploration strategy that enables the model to actively investigate boundary cues and perform self-correction. In addition, we formulate discrete natural-language prompts as pseudocode to regularize the execution logic. Reinforcement learning is further employed to implement this irreducible process and elicit the model's structured reasoning capability. Our EVEREST achieves optimal performance on all metrics in the real world urban socio-semantic dataset, demonstrating the superiority of our model. Codes are available at https://anonymous.4open.science/r/EVEREST-9D21/.

cs.MM↗
arXiv2026

EM^2Mem: Event-Centric Multimodal Memory for Large Language Models

Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as isolated fragments. Although searchable, such fragments are not generation-ready: language models must reconstruct cross-modal and temporal alignments at inference time, when context is limited and attribution is difficult. We propose EM^2Mem, an event-centric multimodal memory framework that binds heterogeneous evidence to event anchors during memory construction. Each event-indexed memory cell aligns multimodal records, temporal context, graph-linked relations, semantic facts, and provenance, enabling compact evidence readout over grounded multimodal events rather than modality-specific fragments. Across three long-video QA benchmarks, EM^2Mem improves average accuracy over the strongest memory baseline by 2.0, 2.4, and 3.7 points, improves strict event-level Top-5 evidence recall by 7.0 points, and reduces per-query latency by 4.67 times and total inference tokens by 63.66% (The code will be integrated into https://github.com/zjunlp/LightMem).

cs.CL↗
arXiv2026

Mind the Rift: Cross-Scale Coupling Mismatch for AI-Generated Video Detection

As AI video generators achieve cinematic realism, reliable detection becomes essential for safeguarding digital trust. We identify cross-scale coupling mismatch as a new forensic signal, where scale refers to the level of abstraction (semantic dynamics vs. pixel-level residuals): in natural videos, macro-level temporal dynamics and micro-level residual patterns are intrinsically coupled by the unified imaging physics pipeline, whereas AI generators, whose training objectives do not explicitly preserve this joint distribution, systematically violate this coupling. Detecting such mismatch is challenging because it requires independently extracting information at both scales while simultaneously quantifying their cross-scale relationship. We propose RIFT (Representation Inconsistency Forensics on Trajectories), an orthogonal forensic framework that addresses this through three interlocking components: a macro stream that builds a dynamic baseline of expected temporal evolution via differential geometry and persistent homology on learned manifold trajectories, a micro stream that acts as a sensitive forensic probe via steganalytic filtering and temporal modeling, and a coupling divergence module that measures the conditional dependency between the two streams. Gram-Schmidt orthogonality guarantees the information-theoretic validity of this measurement. Experiments on two benchmarks (VidProM, 120K videos, 7 generators; GenVidBench, 68K videos, 4 generators) demonstrate that RIFT achieves 99.33% and 99.72% F1-score respectively, with 97.87% unseen-generator detection rate in leave-one-out evaluation, while exhibiting encoder agnosticism: scaling from ViT-S/14 (22M) to ViT-L/14 (300M) changes F1 by less than 0.1%, and switching to a different encoder family (DINOv1) reduces F1 by only 0.73 pp. Code is available at https://github.com/Litsay/RIFT

cs.CV↗
arXiv2026

SwapRec: Warming Up Cold Items Through Training-Time Swaps

Interactions with cold items negatively impact real-time personalization of ID-based recommender systems. This is because the use of such interactions degrades user preference estimates, whereas excluding cold items from the user profile prevents real-time recommendation updates. In industrial scenarios, one heuristic often applied to address this shortcoming at inference time is to replace, i.e., "swap", cold-start items by their most similar "warm" neighbor, where similarity is inferred from the items' side information. In this paper, we demonstrate that sequential models, most often used for real-time personalization, are not robust to such swaps, and propose SwapRec, an approach to address this issue. SwapRec relies on using the same swap heuristics already at training time. We apply SwapRec to state-of-the-art models for sequential recommendation and analyze its impact by means of quantitative experiments in three recommendation domains (online shopping, movie, music). The experimental results show that, irrespective of the underlying sequential architecture, our easy-to-implement SwapRec approach allows for substantially more accurate recommendations when in presence of interactions with cold items, simultaneously leading to a larger percentage of cold items in the recommendation lists.

cs.IR↗
arXiv2026

TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models

Although pretrained joint audio-visual diffusion models offer rich control over \emph{what} to generate, they provide no explicit control over \emph{when} an utterance should occur. To address this, we study \emph{inference-time speech scheduling}, a novel task that places coupled speech and visual articulation within user-specified begin--end intervals without finetuning the backbone model. We uncover two intrinsic properties of the denoising process that enable this task. First, a timing-sensitive text-to-audio cross-attention head exposes each utterance's model-implied source span along the latent timeline. Second, the predicted clean latent already organizes coupled speech and visual articulation, allowing their temporal placement to be edited without regenerating the content. Building on these discoveries, we propose \textbf{TimeSteer}, a training-free framework that localizes each utterance's source span through \textbf{Source Span Localization} and transfers the associated audio-visual latent content from the source interval to the specified target interval through \textbf{Region-Aware Latent Remapping}. We further introduce \textbf{SpeechShift}, the first benchmark for interval-level speech scheduling in joint audio-visual generation. Experiments across two representative backbones show that TimeSteer substantially improves interval controllability over training-free baselines while maintaining competitive overall generation quality.

cs.CV↗
arXiv2026

Can LLMs Design Video Coding Tools? A Case Study on Planar Mode

This paper explores whether large language models (LLMs) can design video coding tools, a highly challenging task due to the intricate algorithmic coupling of tool modifications. In particular, we present an empirical case study on the Planar mode, a long-standing intra prediction tool in video coding standards. Our experiments operate within a generation-and-evaluation loop, with the LLM generating new Planar predictors, encoder trials evaluating their coding performance, and the LLM re-generating refined implementations based on the evaluation feedback. We first examine directly replacing the default Planar mode in the Fraunhofer Versatile Video Encoder (VVenC) under its faster preset. Experimental results demonstrate that the LLM-generated mode can outperform the conventional Planar mode on this lightweight toolset, achieving 0.18% bitrate savings with 0.4% complexity overhead on the standard benchmark. We further extend our evaluation to the Enhanced Compression Model (ECM). Leveraging newly introduced directional Planar modes, we investigate two integration strategies: directly replacing them, and introducing the LLM-generated predictor as an additional prediction mode with new syntax elements. The empirical results suggest that both strategies can yield coding gains under a constrained low-resolution setting. Overall, this study offers preliminary evidence and practical insights, highlighting both the potential and open challenges of LLM-based coding tool design.

cs.MM↗
arXiv2026

Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions

Large language models are increasingly used to simulate social media users and infer how individuals may respond to online discussions. However, it remains unclear whether these simulations reflect precise user-specific beliefs or whether they are highly sensitive to semantically independent changes in conversational contexts. In this work, we study counterfactual context revision as a framework for auditing LLM-based stance simulation. Given an original online conversation, we first infer a target user's stance toward a specific topic. We then apply controlled revision strategies to the conversational context and simulate the user's stance again under the revised context. We compare text-only revision strategies with a multimodal one that incorporates meme-based context and evaluate two main effectiveness metrics, i.e., average directional stance shift and stance transition rate. The results reveal effective and robust stance transitions in both text-only and multimodal strategies across different polarization-preference mechanisms. Our study contributes an evaluation framework for understanding the context sensitivity of LLM-based stance simulation (https://github.com/STARResearchLab/StanceShift). More broadly, it highlights both the promise and risk of using LLMs as proxies for social media users in social simulation.

cs.CL↗
arXiv2026

When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception

Multimodal information systems increasingly route generated visual content back through the same vision-language index that informed its production, so the output must remain retrievable by the queries it was meant to serve. When the scene contains entities at vastly different scales, existing language-guided generators condition on a single, globally pooled text embedding and quietly drop scale-specific concepts, breaking concept-query retrieval even when pixel fidelity is high. We formalise this failure as semantic collapse and propose CERES, a closed-loop multimodal indexing framework that builds a three-level semantic pyramid, mines implicit concepts via a co-occurrence-aware router, performs scale-routed cross-attention into a lightweight U-Net generator, and verifies coverage by re-indexing the generated image with the same frozen VLM. A continuously differentiable soft-Jaccard coverage objective returns dense gradients to the 0.39 M-parameter generator under explicit non-degeneracy conditions, and coverage is verified by an independent DINOv2 linear probe trained only on external scene and object labels. On four pansharpening benchmarks across seven settings, CERES delivers the new state of the art with the largest gains where scale variation is most extreme (+4.64% relative Q2n and +9.7 mAP for DOTA detection). It also improves concept-query retrieval Recall@5 by +14.0 points and image-text mean reciprocal rank by 0.19 over the strongest baseline, showing that the closed loop preserves queryable content rather than self-referential feature consistency.

cs.MM↗
arXiv2026

ReLViC: Loss-Resilient Learned Video Coding with Dispersed Packetization and Controllable Packet Dependencies

Packet loss can severely impair learned video coding because missing latent tokens compromise both spatial reconstruction and temporal prediction. We present ReLViC, a loss-resilient learned video coding framework that jointly addresses latent coding and packet-loss recovery. ReLViC disperses spatially adjacent latent tokens across packets and employs a dual-purpose Transformer to estimate entropy-model parameters during coding and reconstruct missing latent tokens at the receiver. It controls packet dependencies through a periodic-reset packet-context topology parameterized by the segment length, thereby tuning the trade-off between compression efficiency and error-propagation range without retraining. A three-stage progressive training procedure establishes single-frame coding, learns temporal context for entropy modeling, and then optimizes the recovery of masked latent tokens under simulated packet loss. Experiments using burst-loss traces evaluate ReLViC against H.265 protected by Reed--Solomon forward error correction (FEC) and GRACE, a loss-resilient learned video codec. ReLViC delivers more stable reconstruction and outperforms both baselines under severe packet loss.

eess.IV↗
arXiv2026

HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving

Recent advances in large language models and multimodal models have pushed remote sensing (RS) processing from simple perception models to agentic systems designed to tackle complex, long-horizon RS tasks. However, existing systems often rely on monolithic decision-making frameworks, which fail to accommodate the multi-stage, interdependent nature of RS tasks. This centralized approach leads to challenges such as unstable task execution, incorrect tool usage, and error propagation across stages. To address these issues, we propose HiRS-Agent, a hierarchical multi-agent system for long-horizon RS task solving. HiRS-Agent adopts a two-level collaborative architecture: the Manager Layer handles dynamic routing, step-level verification, replanning, and termination control, while the Specialist Layer organizes domain-specific tools according to the RS workflow and is responsible for subtask reasoning and tool execution. To further enhance the system's capability, we introduce a two-stage supervised tuning strategy and a verification-guided hierarchical reinforcement learning stage to jointly optimize coordination and tool-use policies. Experiments on Earth-Agent Benchmark and ThinkGeo show that HiRS-Agent substantially improves long-horizon tool-use capability and final-task correctness, demonstrating the effectiveness of structured multi-agent collaboration for reliable RS agents. The code is publicly available at https://github.com/IntelliSensing/HiRS-Agent.

cs.AI↗