#VisionLanguageModels
Trending Vision-Language Models This Week

The 10 most-trending Vision-Language models on Hugging Face this week — Kimi-K3.1-Pro, Qwen3.8-27B, DeepSeek-V4.1-Flash-1017 and more — with size, license,…

#science #AI #MachineLearning #VisionLanguageModels
Trending Vision-Language Models This Week
The 10 most-trending Vision-Language models on Hugging Face this week — Kimi-K3.1-Pro, Qwen3.8-27B, DeepSeek-V4.1-Flash-1017 and more — with size, license,…
sciherald.com
November 9, 2026 at 4:45 AM
New preprint! 🚀

How well do the internal representations of VLMs organize visual information for #unsupervised #imageclustering?

We explore this over 252 configurations, with some interesting results!

arxiv.org/abs/2610.33265

#VLM #visionlanguagemodels #INESCINOV #ULusófona #FCUL #LASIGE
Image Clustering with Vision-Language Model Embeddings
Pretrained vision-language models provide image representations whose suitability for clustering may vary with feature extraction, image domain, and partitioning algorithm. We compare nine representat...
arxiv.org
October 27, 2026 at 5:13 PM
Singapore University of Technology and Design is recruiting a Research Fellow for vision-language models and efficient AI for drones.

mlscientist.com/research-fel...

#visionlanguagemodels
October 16, 2026 at 2:53 AM
VLMs and geospatial reasoning are now being benchmarked against a decade of crowdsourced disaster photos for cross-view geolocalization in GeoAI research. This highlights how emerging GeoAI models are…

#GeoAI #DisasterMapping #VisionLanguageModels #Crowdsourcing
https://arxiv.org/abs/2610.15403
October 15, 2026 at 10:01 PM
Small vision-language models often read external evidence well but struggle to retrieve it. Harness Compilation adapts the division of work between a frozen small VLM and its harness using teacher traces,…

#HarnessCompilation #VisionLanguageModels #VQA #SmallVLMs
https://arxiv.org/abs/2610.11231
October 10, 2026 at 10:00 AM
A new benchmark called VisionQ evaluates vision-language models on criterion-conditioned visual discrimination, using 1,800+ figures from peer-reviewed CVPR and ICCV papers to ground judgments in…

#VisionLanguageModels #ComputerVision #Benchmark #AIResearch
https://arxiv.org/abs/2610.00666
October 2, 2026 at 12:01 PM
natural-language instructions.

Two exciting steps forward at the intersection of robotics, AI, computer vision and simulation.

#WAF2026 #Robotics #ArtificialIntelligence #ComputerVision #DigitalTwin #VisionLanguageModels #AutonomousRobots
September 28, 2026 at 1:59 PM
Liquid AI zeigt LFM2.5-VL-DSpark: ein Vision-Language-Modell, das auf Tempo getrimmt ist. Bei VLMs entscheidet längst nicht mehr nur Qualität – sondern ob die Latenz eine echte Pipeline zulässt. #VisionLanguageModels

Mehr von mir: linkedin.com/in/maurice-putinas
September 26, 2026 at 6:00 AM
Manchester Metropolitan University is offering a funded PhD studentship in vision language models for micro-expression...

mlscientist.com/phd-students...

#PhDstudentship #visionlanguagemodels #microexpressionanalysis
September 21, 2026 at 12:53 AM
July 23, 2025 at 4:22 PM
July 3, 2025 at 2:40 PM
Figure AI’s Humanoid Robots Now Follow Voice Commands With New Helix Vision-Language-Action Model #AI #Robotics #MachineLearning #Automation #VisionLanguageModels #FigureAI
Figure AI’s Humanoid Robots Now Follow Voice Commands With New Helix Vision-Language-Action Model - WinBuzzer
Figure AI's Helix AI model allows humanoid robots to understand speech, adapt to new objects, and collaborate in real time.
buff.ly
February 21, 2025 at 5:33 PM
DeepSeek AI has released DeepSeek-VL2, a family of high-performing Vision-Language Models that are now available open-source licenses. #AI #VisionAI #DeepSeekVL2 #VisionLanguageModels #OpenSourceAI #OCR #MultimodalAI #AIResearch #AIModels #Deepseek @DeepSeek
DeepSeek AI Open Sources VL2 Series of Vision Language Models - WinBuzzer
DeepSeek AI has released DeepSeek-VL2, a family of Vision-Language Models (VLMs) that are now available under open-source licenses. The series introduces three variants—Tiny, Small, and the standard...
buff.ly
December 16, 2024 at 5:49 PM
"CheXthought" introduces a global multimodal dataset with 103k radiologist chain-of-thought traces and 6.6M visual attention annotations for chest X-ray interpretation, improving grounding, uncertainty communication, and temporal reasoning in medical #VisionLanguageModels. arxiv.org/html/2604.26...
1 Introduction
Content selection saved. Describe the issue below:
arxiv.org
May 13, 2026 at 7:03 PM
Reason-RFT improves visual reasoning in vision-language models, according to the announcement. Read more: https://getnews.me/reason-rft-improves-visual-reasoning-in-vision-language-models/ #reasonrft #visionlanguagemodels #visualreasoning
October 8, 2025 at 6:22 PM
MetaSpatial says it improves 3D spatial reasoning in vision-language models. Read more: https://getnews.me/metaspatial-improves-3d-spatial-reasoning-in-vision-language-models/ #metaspatial #3dspatial #visionlanguagemodels
October 8, 2025 at 6:17 PM
VLMCountBench shows vision‑language models count objects when only one shape type (triangles, circles or squares) appears, but accuracy drops on scenes with multiple shapes. Read more: https://getnews.me/vision-language-models-struggle-with-compositional-counting/ #visionlanguagemodels #counting
October 8, 2025 at 1:15 AM
A new framework pairs vision‑language models with an action expert that refines sparse 3‑D waypoints into collision‑free motion plans, trained on synthetic and real point‑cloud data. https://getnews.me/vision-language-models-linked-to-action-expert-for-robot-planning/ #visionlanguagemodels #robotics
October 7, 2025 at 8:32 PM
DepthLM equips vision-language models with metric depth prediction, matching the accuracy of dedicated depth estimators, per the paper submitted on 1 Oct 2025. Read more: https://getnews.me/depthlm-achieves-accurate-metric-depth-with-vision-language-models/ #depthlm #visionlanguagemodels
October 3, 2025 at 11:54 AM
CoFFT, a training-free technique, lifts Vision Language Model accuracy by 3.1%–5.8% and debuted on 1 Oct 2025, iteratively sharpening visual focus during inference. https://getnews.me/cofft-boosts-vision-language-models-with-iterative-focused-reasoning/ #visionlanguagemodels #cofft
October 3, 2025 at 10:37 AM
Three new diagnostics—PSI, CMB, RoPE probe—show VLMs favor visual tokens; reducing visual token norms raised PSI and improved spatial reasoning. Read more: https://getnews.me/vision-language-models-restore-spatial-awareness-with-new-diagnostic-tools/ #visionlanguagemodels #spatialreasoning
October 3, 2025 at 7:26 AM
EDCT audits VLM explanation faithfulness on 120 OK‑VQA examples, showing many explanations are plausible but not causally linked to answers. Read more: https://getnews.me/explanation-driven-counterfactual-testing-boosts-faithfulness-of-vision-language-model-explanations/ #edct #visionlanguagemodels
October 2, 2025 at 7:25 PM
CADC reduces required training data to about 5% of the original set while still outperforming full-data models on multimodal benchmarks, the authors report. Read more: https://getnews.me/capability-attributed-data-curation-improves-vision-language-models/ #visionlanguagemodels #capabilitycuration
October 2, 2025 at 7:21 PM
GSM8K‑V adds visual format to 1,319 grade‑school math problems. Gemini‑2.5‑Pro scores 95.22% on text but only 46.93% on the visual version, showing a gap for VLMs. https://getnews.me/gsm8k-v-shows-vision-language-models-lag-on-visual-math-problems/ #gsm8kv #visionlanguagemodels
October 1, 2025 at 3:46 AM