Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2609.24156v1 Announce Type: cross Abstract: Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Re...
The paper investigates an agentic framework for open‑world fake image detection that combines specialist detectors with per‑detector triage, prompting, and conflict‑aware evidence arbitration. Experiments across six configurations and three multimodal large language model backbones reveal that naive detector fusion yields high false‑positive rates, while triage and prompting consistently filter unreliable evidence. The most significant improvement comes from the reasoning component: a stronger judge markedly outperforms a weaker one, especially under distribution shift, and overall manipulation recall is nearly saturated, highlighting that the key challenge lies in calibrating trust and arbitrating conflicting forensic evidence rather than detecting manipulations themselves.
arXiv:2609.24485v1 Announce Type: new Abstract: Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction oft...
arXiv:2609.24487v1 Announce Type: new Abstract: In this work, we present a method for shape reconstruction and tracking from video via agentic analysis-by-synthesis. Unlike prior methods which first...
PrismGPT is a Vision‑Language Model that generates structured, region‑aware photo‑editing plans from a single image, without relying on commercial black‑box tools. It learns to diagnose aesthetic issues globally and locally while predicting precise editing parameters, using proxy‑guided learning with operation decomposition and region‑aware aesthetic ranking to bootstrap the model. A competence‑based dynamic scheduler shifts training focus from proxy tasks to the main editing task as skills improve, and all reasoning traces for fine‑tuning are self‑synthesized by the model itself. Experiments on MIT‑Adobe FiveK and a new professionally retouched benchmark, SPIRE, show PrismGPT achieves state‑of‑the‑art results using only about 6% of the training data required by previous methods.
Lingshu is a medical‑specialized multimodal large language model that addresses key limitations of existing medical MLLMs, such as narrow knowledge coverage, hallucinations, and weak reasoning. The authors curate a comprehensive dataset combining medical imaging, texts, and general‑domain data, then train Lingshu in multiple stages to embed medical expertise and improve task performance. They also introduce MedEvalKit, a unified evaluation framework, and demonstrate that Lingshu outperforms current open‑source multimodal models on multimodal QA, text‑based QA, and medical report generation.
arXiv:2507.22920v2 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data int...
The paper proposes a method to distill world‑model representations into compact Vision‑Language‑Action (VLA) policies. By adding a single feature‑alignment term during VLA training, a frozen world model’s internal features are cached and the student policy learns to match them, eliminating the need for a generative future‑rolling component. The resulting lightweight policy runs in 32 ms on an RTX 5090, achieving high performance on LIBERO and RoboCasa‑GR1, and transfers effectively to real robotic hardware.
This study explores whether spatial structure can be learned directly from pre-beamforming per-antenna range-Doppler (RD) radar measurements, bypassing traditional beamforming steps. Using a 6‑TX × 8‑RX automotive radar with a chirp‑sequence FMCW transmit scheme, the authors train a dual‑chirp shared‑weight encoder on raw RD tensors and evaluate spatial recoverability via bird’s‑eye‑view occupancy maps. Experiments across different transmit configurations (A‑only, B‑only, A+B) and receive apertures demonstrate that meaningful spatial structure is indeed recoverable through learned spatial mixing, without hand‑crafted signal‑processing stages.
arXiv:2609.23431v1 Announce Type: new Abstract: Human-object interaction (HOI) detection requires grounding an interacting human-object pair and recognizing the verb that links them, often under seve...
arXiv:2603.18532v3 Announce Type: replace-cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for f...
We introduce Qwen3.8-Omni-Flash, a natively multimodal agentic model for real-world multimodal productivity. Compared with previous omni models, which primarily emphasized perception and interaction,...
Degradations vary widely across images, so a practical restoration system has to handle many degradation types with one model. A recent and effective recipe adapts a large pretrained image-editing mod...
Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to satisfy prompts requiring specialized knowledge, sp...
Recent foundation models are moving toward native multimodal Vision-Language Models (VLMs), making VLMs a central form of next-generation foundation models. However, their large language backbones mak...
Challenging behaviors including aggression, self-injury, and property destruction are observed in 68% of autistic youth and pose risks to youth and caregivers. These episodes are preceded by agitation...
Thermography plays a vital role in military and broader thermal analysis applications. Recent progress in 3D thermal reconstruction has extended temperature analysis from 2D to 3D space, yet most exis...
Background: Microvascular invasion (MVI) predicts recurrence and survival in hepatocellular carcinoma (HCC) but requires postoperative histopathology for diagnosis. We developed and validated a model...
Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes substantial performance degradation. We...
Multimodal large language models (MLLMs) are increasingly explored as interfaces for scientific image analysis, where a visual question-answering (VQA) response may be paired with a spatial output tha...