Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2609.01060v1 Announce Type: cross Abstract: Compact snapshot hyperspectral cameras provide rich instantaneous spectral measurements for ground-level machine vision, but at lower spatial resolut...
arXiv:2609.00709v1 Announce Type: cross Abstract: Large Vision-Language Models produce fluent image descriptions but offer limited semantic control: users cannot reliably specify whether captions sho...
CoMMET is a new multimodal benchmark designed to evaluate Theory of Mind (ToM) in Multimodal Large Language Models (MLLMs). It expands beyond existing text-only, belief-focused tests by covering a wider range of mental states, incorporating moral evaluation, and enabling multi-turn, open-ended interactions. The dataset is grounded in psychological theory and provides a comprehensive assessment across different model families and sizes, revealing strengths, limitations, and future improvement directions.
The paper introduces ModalShare, a bandwidth allocation method for multimodal split learning that assigns each modality a keep‑ratio based on its Shapley contribution score. Unlike existing compression schemes that split the uplink budget proportionally to activation size, ModalShare explicitly optimizes the split across modalities, requiring no extra uplink traffic or client computation. Experiments on CREMA‑D and MVSA datasets show that ModalShare improves accuracy by 12.4–15.4 percentage points over equal keep‑ratios under a 5× compression budget, outperforming three compressors across multiple datasets and budgets.
Qwen-Drive-1.0 is a vision‑language foundation model tailored for autonomous driving that builds on a pretrained VLM architecture. It incorporates a bird’s‑eye‑view perception head for 3D object detection, semantic occupancy prediction, and BEV map segmentation, and a Planning Expert that generates future ego trajectories from shared representations. Experiments show strong 3D perception, driving scene understanding, and competitive motion‑planning performance while largely preserving general vision‑language capabilities.
The paper introduces SARTM, a framework that adapts the Segment Anything Model (SAM) for RGB‑thermal (RGB‑T) semantic segmentation. It fine‑tunes SAM with LoRA layers, incorporates language guidance, and employs a Cross‑Modal Knowledge Distillation module to bridge modality gaps. The approach also modifies the segmentation head and adds an auxiliary semantic head, achieving superior performance on MFNET, PST900, and FMB benchmarks.
arXiv:2609.01433v1 Announce Type: new Abstract: Concept erasure aims to suppress unsafe, privacy-sensitive, or undesirable generations in text-to-image diffusion models while preserving benign semant...
arXiv:2609.00231v1 Announce Type: new Abstract: Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as o...
The paper introduces Pref‑MH, an exact Metropolis‑Hastings sampler that uses only stochastic binary pairwise comparisons from judges to sample from distributions conditioned on desired semantic properties. By linking the MH density ratio to the preference odds of the Bradley‑Terry model, the authors devise an accept/reject rule that guarantees convergence to the target distribution. Experiments on text, molecular, and image generation with large‑language‑model and vision‑language‑model judges show Pref‑MH as a practical, flexible method for conditional sampling when comparative feedback is readily available.
arXiv:2609.00378v1 Announce Type: new Abstract: Large language models pay a well-documented tax on non-English text: the same content costs several times more tokens, and because attention is quadrat...
UI‑Venus‑2 is a general‑purpose foundation GUI agent that operates across mobile, web, and desktop environments using a unified closed‑loop reasoning‑action framework. The report details how the system expands environment coverage to over 170 multilingual mobile apps and native desktop OSes, scales task generation through a deep‑research pipeline, and enhances verification with trace‑level and sample‑level evaluators that use visual keypoints and multi‑model voting. Safety‑aware mechanisms are also incorporated to control consequential actions, positioning UI‑Venus‑2 as an efficient, open‑source tool for more generalizable, verifiable, and self‑reflective agents in real‑world applications.
The paper identifies a problem in large language model (LLM) unlearning called forget‑set misalignment, where the set of data to be forgotten does not match what the model has actually memorized. Two failure modes are described: Under Unlearning, where memorized information is omitted from the forget set, and Out‑of‑Knowledge Unlearning, where the algorithm attempts to forget knowledge the model never learned, harming performance. The authors propose CONfs, a data‑blind framework that constructs model‑aligned forget sets by eliciting the model’s memorized knowledge, and demonstrate that it achieves near‑gold standard forgetting while preserving utility better than other data‑blind methods.
arXiv:2609.00476v1 Announce Type: new Abstract: Graphic designers often blend visual concepts to communicate multiple ideas within a single image, leveraging positive and negative space to create bal...
The study evaluates computer-use agents (CUAs) for blind users by conducting a three‑week diary study with eight participants using the OLLA prototype. Across 1,258 commands in 12 desktop applications, GPT‑5 achieved the highest success rate of 52.5%, while analysis uncovered failures in grounding, planning, constraint‑tracking, and termination. Interviews highlighted additional needs beyond automation for blind users.
The paper introduces a cross‑modal pseudo‑labeling pipeline for unsupervised domain adaptation in semantic segmentation, particularly for waste sorting. It combines SAM for class‑agnostic region proposals with EVA‑CLIP to assign semantic labels via region‑text similarity, applying confidence filtering to ensure reliable pseudo‑labels for self‑training. An optional BLIP‑based language‑grounded verification further refines ambiguous regions, and the method shows consistent improvements over source‑only baselines on synthetic‑to‑real driving and lab‑to‑factory waste sorting shifts.
The paper introduces DP-TabImage, a framework that synthesizes paired table–image data while preserving differential privacy. It factorizes the joint distribution into a private probabilistic graphical model for tables and a table‑conditioned diffusion model for images, using DP‑SGD and a privacy‑preserving warm‑up strategy. Experiments on three real datasets demonstrate a strong balance between table fidelity, image fidelity, and cross‑modal alignment.
arXiv:2609.00802v1 Announce Type: new Abstract: Multi-party interaction is a central setting for human communication and a necessary target for human-agent interaction systems that must participate i...
The paper examines RGB‑infrared fusion for binary wildfire segmentation using UAV imagery on the FLAME3 dataset. It compares RGB and infrared baselines with three fusion strategies across U‑Net, DeepLabV3+, and SegFormer architectures. Results show thermal data dominates segmentation performance, and feature‑level fusion with transformer‑based models yields the best results.
arXiv:2603.29852v2 Announce Type: replace-cross Abstract: We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, comp...
arXiv:2601.14121v2 Announce Type: replace Abstract: Identifying when and where a news image was taken is crucial for journalists and forensic experts to produce credible stories and debunk misinforma...