CounterVid introduces a scalable counterfactual video generation framework that creates videos differing only in actions or temporal structure while keeping scene context intact. The approach uses multimodal LLMs for action proposals and diffusion models for editing, producing a synthetic dataset of ~26k preference pairs for action recognition and sequence ordering. With the MixDPO optimization method, the authors demonstrate significant improvements in action recognition and temporal ordering on Qwen2.5‑VL and InternVL3 backbones, while maintaining overall video understanding.
By Tobia Poppi, Burak Uzkent, Amanmeet Garg, Lucas Porto, Garin Kessler, Yezhou Yang, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara, Florian Schiffers
Chart2SVG is a multimodal large language model that transforms static raster chart images into editable SVGs enriched with semantic structure. By embedding chart‑specific semantic tokens into a vision‑language framework and training on the Beagle+ dataset of 33K distilled chart samples, the model captures both geometric primitives and their functional roles. The resulting SVGs are visually accurate and structurally consistent, and the accompanying Chart Structure Graph (CSG) exposes visual dependencies for interactive exploration, chart repurposing, and layout reuse.
By Jinning Cui, Lu Chen, Haoyan Shi, Yue He, Chenglong Wang, Mengyu Zhou, Weidong Huang, Yunhai Wang
The paper introduces Inverted Asymmetric Fusion (IAF) to address strong-modality collapse in multimodal learning, where dominant modalities are degraded during fusion. IAF preserves the dominant modality by passing it unchanged and letting weaker modalities attend to it, while also strengthening weaker modalities via Modality-Aware Knowledge Distillation. Experiments on MultiHuSE, UR-FUNNY, and MUStARD show that IAF maintains unimodal performance and improves over the best unimodal baseline by up to 8.25%.
By Mary Ogbuka Kenneth, Foaad Khosmood, Abbas Edalat
The paper introduces Composed Gait Retrieval (CoGR), a task that retrieves a target gait sequence using a reference sequence and a natural language modification query. To support this, the authors create the first gait-language datasets—Language‑Augmented CCPG and Language‑Augmented CASIA‑B—via an automated annotation pipeline powered by large vision‑language models. They propose ComposeGait, an identity‑anchored composition framework with a Part‑aware Identity Adapter that injects identity tokens into a shared Q‑Former, achieving state‑of‑the‑art retrieval performance on both benchmarks.
By Jingchen Fei, Zengbin Wang, Yukun Liu, Muyi Sun, Shibiao Xu, Man Zhang
The paper shows that a plain Transformer can serve as an effective graph learner by adding three lightweight modifications: simplified L₂ attention, adaptive RMS normalization, and an MLP-based positional encoding stem. These changes preserve token magnitude and enable the model to achieve high expressivity on graph benchmarks, outperforming more complex graph transformer variants. The results suggest that plain Transformers can act as a unified backbone for multimodal learning across language, vision, and graph domains.
By Liheng Ma, Soumyasundar Pal, Yingxue Zhang, Philip H. S. Torr, Mark Coates
The paper introduces a self‑supervised framework that maps text, audio, image, and video into a shared 256‑dimensional embedding space and uses iterative clustering to uncover aesthetic structure. It examines how AI’s cluster assignments diverge from human affective labels on a weakly supervised multimodal dataset. The study highlights implications for cross‑modal similarity, media organization for Retrieval‑Augmented Generation, and automated data labeling.
By Corey D. C. Heath
The paper surveys the state of Explainable AI (XAI) in Arabic NLP, highlighting three gaps: a method gap where Arabic XAI relies mainly on limited post‑hoc techniques; a task gap with most work focused on classification tasks and little on generation, retrieval, or dialogue; and a linguistic gap where explanations rarely address Arabic‑specific phenomena such as morphology, dialects, and diglossia. It proposes a taxonomy of tasks, methods, linguistic units, and evaluation practices, and outlines a research agenda for linguistically grounded Arabic XAI.
By Salima Lamsiyah, Ruslan Mitkov
CultureVidBench is a new benchmark that evaluates how well text‑to‑video generation models capture cultural details. It contains 1,000 prompts spanning 12 countries, 6 continents, 8 cultural regions, and 14 cultural aspects, grouped into material culture, social practice & performance, and ritual & ceremony. Human studies and automated assessments show that while current models perform well on semantic adherence and visual quality, they often miss fine‑grained cultural details, especially for underrepresented regions and multimodal cues.
By Xianjing Han, Yuhan Su, Yang Deng, Dong Ma, Wee Peng Tay, Bin Zhu
Aphanta is an automated framework that diagnoses how well image editors can produce task‑aligned visual intermediates for multimodal large language models (MLLMs). It evaluates three reasoning conditions—direct, editor‑generated, and idealized intermediate—to distinguish visual potential from practical editor performance across 20 tasks and various editor–MLLM pairs. The study finds that image editing benefits certain tasks like visual cue injection and grounding, but is less reliable for symbol‑sensitive or structural tasks, and demonstrates measurable performance gains with a Qwen pipeline.
By Hengyuan Xu, Wei Cheng, Yumeng Ji, Xuanyang Zhang, Xianfang Zeng, Gang Yu, Xingjun Ma
The paper introduces Configured Failure Trapping, a new backdoor attack targeting Vision‑Language‑Action (VLA) models that activates through subtle textual triggers and forces the robot to fail in a specific, controlled manner. It presents a data engine for generating high‑quality target trajectories, an automated evaluation suite, and two benchmarks—Trap‑LIBERO and Trap‑RoboTwin—covering four failure modes. The authors propose TrapVLA, a method that learns trigger‑induced action residuals to steer policies toward the desired failure behavior, demonstrating effectiveness in both simulation and real‑world robotic experiments while maintaining performance on clean data.
By Jun-Hui Liu, Kun-Yu Lin, Yi-Lin Wei, Xu-Han Chen, Yinghao Li, Zhuohao Li, Yuan-Ming Li, Qing Zhang, Xiaoyi Fan, Dongmei Jiang, Yan Li, Wei-Shi Zheng
The paper introduces GSM8K‑V, a new benchmark that converts the GSM8K grade‑school math word problems into multi‑image sequences while preserving semantic equivalence. It requires vision‑language models to extract quantities through visual perception and reconstruct reasoning chains by integrating implicit cues across scenes. Evaluation of 34 VLMs shows a large modality gap: most models score above 90 % on text, but the best reaches only 59 % on GSM8K‑V, highlighting a distinct challenge in implicit visual inference.
By Fan Yuan, Yuchen Yan, Yifan Jiang, Haoran Zhao, Tao Feng, Jinyan Chen, Yanwei Lou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
SAGE is a CLIP-based framework that augments vision‑language time series forecasting by incorporating variable‑specific semantic and statistical information. It processes frequency‑enhanced patches and variable tokens through a CLIP text encoder, while a frozen CLIP vision encoder aligns rendered series with temporal representations via a contrastive objective. The approach achieves state‑of‑the‑art accuracy on eight long‑term benchmarks and M4, with ablations showing complementary gains from multimodal alignment and variable‑level knowledge.
By Haizhao Fan, Xinyi Le
AraMS-28k is the largest publicly released line‑level dataset of genuine historical Arabic manuscripts, containing 14 books, 3,043 pages, and 28,600 annotated text lines (27,971 main‑text and 629 margin). The dataset spans three script traditions—Naskh, Ruq'ah, and Maghrebi—and includes a lithographed printed edition for format diversity. Each line is labeled as main‑text or margin, with margin lines that have a clear attachment point annotated with an insertion anchor to recover the manuscript’s true non‑linear reading order; both fully vocalized and diacritic‑normalized transcriptions are provided, and the data was produced via the RefLAM pipeline combining OCR, clean transcriptions, and human review.
"whyItMatters":"The dataset’s comprehensive line‑level annotations, including reading‑order anchors and dual transcription formats, enable reproducible research on Arabic manuscript recognition, layout analysis, and reading‑order recovery under a CC BY‑NC‑SA 4.0 license."
By Mohamed Guechaoui, Mohamed Diaa Zellagui, Souleyman Chaib, Sahraoui Dhelim
The paper introduces SARA, a framework that separates action induction from runtime authorization in tool‑augmented LLM agents. By treating these as distinct roles, SARA uses an Action Probe to record action provenance and only authorizes tool calls that align with the user objective and past successful executions. Experiments on AgentDojo and AgentDyn show that SARA reduces action‑to‑side‑effect risk to below 0.63% while preserving task performance.
By Xiaokun Guo, Zhen Xu, Dongdong Huo, Yanqiu Zhang, Wei Wang, Qinfu Yang, Dongjin Yu, Yu Wang
PACE introduces a training‑free Condense‑and‑Extract framework that speeds up Vision‑Language Model inference by first adaptively downsampling visual inputs before encoding and then selectively retaining essential tokens during decoding. The Adaptive Pixel Compressor (APC) reduces encoder workload while preserving global context, and the Dynamic Dual‑Attention Extractor (DDAE) keeps task‑critical details by fusing visual and language signals. Applied to Qwen2.5‑VL‑7B, PACE maintains 93.8% of performance using only 10% of visual tokens, achieving a 3.1× speedup in time to first token.
By Junjie Liu, Shengyuan Ye, Xu Chen
The paper introduces a unified phoneme‑based TTS‑to‑ASR augmentation pipeline that uses a multilingual TTS model with language‑ID conditioning and incorporates grapheme‑to‑phoneme conversion, reference‑speech filtering, and candidate‑text selection. It proposes phoneme‑frequency‑guided selection (PFGS) to rank sentences based on phoneme frequencies from real ASR labels, and demonstrates that random augmentation and PFGS both improve ASR performance across Arabic, French, Italian, and Portuguese test sets, with PFGS yielding up to a 19.3% relative WER reduction. The study also shows that filtering reference speech can further lower WER by up to 0.59 points on certain datasets.
By Zhen Wang, TianRui Wu, RongQi Han, Hao Wu, Wei Liang
ET‑Prune is a training‑free framework that dynamically allocates visual token budgets in multimodal large language models based on question‑conditioned evidence. It protects text‑like spatial regions, converts evidence uncertainty into a token floor, and progressively prunes concentrated evidence while retaining diffuse or text‑dense tokens. In six backbone‑benchmark comparisons, ET‑Prune matches or outperforms other pruned methods while keeping roughly half the visual tokens, achieving notable gains on OCRBench‑v2 and MMBench v1.1.
By Zizhong Ding, Junxian Li, Kai Liu, Shaoqiu Zhang, Xiao Xiao, Linghe Kong, Yulun Zhang
The paper introduces a zero‑shot video restoration and enhancement framework that leverages a text‑to‑image latent diffusion model along with multi‑modal references. It employs dual prompt tuning inversion and sampling to cut inference time to about one‑third of the original, while also strengthening performance and temporal consistency. Additional techniques such as texture‑aware video token merging, referenced self‑attention, and referenced token merging further improve temporal coherence across frames.
By Cong Cao, Huanjing Yue, Xin Liu, Jingyu Yang
The paper introduces LAC (Light Actor, deep Critic), an offline reinforcement learning approach that allocates model capacity to a deep critic rather than a complex actor to improve inference efficiency. It addresses three failure modes—optimization, bootstrap-noise amplification, and value-range drift—using a residual MLP backbone, n‑step bootstrap targets, and a categorical cross‑entropy loss. Experiments on OGBench show LAC matches state‑of‑the‑art diffusion and flow‑matching baselines while reducing inference latency by up to four times.
By Guhyeon Kang, Jaehwi Lee, Minhae Kwon
LLaVAFlow is an information‑theoretic distillation framework designed to preserve cross‑modal alignment in Multimodal Large Language Models during visual instruction tuning. It compresses the mutual information between extracted relations and MLLM embeddings to refine alignment flow, and then maximizes mutual information between pretrained and fine‑tuned alignment flows to transfer compact alignment information. Experiments demonstrate that LLaVAFlow effectively maintains alignment flow, improving downstream performance and generalization.
By Muyao Yuan, Muyan Jiao, Jiangyong Ying, Weizhan Zhang, Yuanhong Zhang, Lan Ma, Yuan Gao, Haipeng Du