PulseAugur
EN
LIVE 16:38:53
ENTITY vision-language model

vision-language model

PulseAugur coverage of vision-language model — every cluster mentioning vision-language model across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
195
195 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
188
188 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
TIMELINE
  1. 2026-05-19 research_milestone A new method is proposed to improve out-of-distribution visual document understanding in VLMs. source
SENTIMENT · 30D

25 day(s) with sentiment data

RECENT · PAGE 8/10 · 195 TOTAL
  1. RESEARCH · CL_27989 ·

    New UJEM-KL attack bypasses VLM safety measures with entropy maximization

    Researchers have developed a new method called Untargeted Jailbreak via Entropy Maximization (UJEM-KL) to bypass safety measures in vision-language models (VLMs). This technique focuses on manipulating high-entropy toke…

  2. TOOL · CL_27992 ·

    TINS method enhances OOD detection in vision-language models

    Researchers have developed TINS, a novel method for Out-of-Distribution (OOD) detection in vision-language models. TINS addresses limitations of static negative labels by learning dynamic negative semantics during test-…

  3. TOOL · CL_28024 ·

    New AI method simplifies images while keeping them photorealistic

    Researchers have developed a new framework for simplifying images while maintaining photorealism, moving beyond traditional non-photorealistic rendering techniques. Their method iteratively removes and inpaints elements…

  4. TOOL · CL_28030 ·

    New SleepWalk benchmark tests AI's 3D navigation and instruction grounding

    Researchers have introduced SleepWalk, a new benchmark designed to rigorously test instruction-guided vision-language navigation capabilities of AI models. This benchmark focuses on localized, interaction-centric embodi…

  5. RESEARCH · CL_26359 ·

    GPT-5 Mini leads Agentick benchmark, but no agent paradigm dominates

    The new Agentick benchmark, which assesses various AI agents across 37 tasks, shows GPT-5 Mini achieving the top score of 0.309. However, no single agent paradigm, including reinforcement learning, LLM, VLM, or hybrid a…

  6. TOOL · CL_25598 ·

    New SAEgis framework detects adversarial attacks on vision-language models

    Researchers have developed a new framework called SAEgis to detect adversarial attacks on vision-language models (VLMs). This method utilizes sparse autoencoders (SAEs) as a plug-and-play module, requiring no additional…

  7. TOOL · CL_22401 ·

    ChartZero uses synthetic data to extract chart data without real-world annotation

    Researchers have developed ChartZero, a novel framework designed to extract data from line charts with zero-shot capabilities. This approach bypasses the need for real-world annotations by training exclusively on synthe…

  8. TOOL · CL_22124 ·

    CompART training improves VLM multi-object grounding and visual understanding

    Researchers have developed a new training method called Compositional Attention-Regularized Training (CompART) to improve how Vision-Language Models (VLMs) handle complex, multi-object references. Current VLMs struggle …

  9. RESEARCH · CL_21791 ·

    GeoStack framework enables efficient VLM knowledge composition, preventing catastrophic forgetting.

    Researchers have developed GeoStack, a novel framework designed to enhance knowledge composition in Vision-Language Models (VLMs). This approach addresses the issue of catastrophic forgetting, where models lose previous…

  10. TOOL · CL_20775 ·

    Consensus Entropy improves VLM OCR accuracy by measuring inter-model agreement

    Researchers have developed a new metric called Consensus Entropy (CE) to assess the reliability of Optical Character Recognition (OCR) outputs from Vision-Language Models (VLMs). CE measures the agreement between multip…

  11. TOOL · CL_20754 ·

    Researchers propose new framework for generative recommendation systems

    Researchers have developed a new framework to improve the generation of Semantic IDs (SIDs) for generative recommendation systems. This approach addresses issues of information and semantic degradation by integrating de…

  12. RESEARCH · CL_20275 ·

    PhysForge generates physics-grounded 3D assets for virtual worlds and embodied AI

    Researchers have introduced PhysForge, a novel framework designed to generate physics-grounded 3D assets for interactive virtual worlds and embodied AI. This system addresses the limitations of existing methods by focus…

  13. RESEARCH · CL_20307 ·

    New AI models InterMesh and Anny-Fit advance 3D human pose and shape recovery

    Researchers have developed InterMesh, a new framework for multi-person human mesh recovery that explicitly incorporates human-environment interaction information. This approach enhances pose and shape estimation by enri…

  14. TOOL · CL_18874 ·

    VLM pipeline enables viewpoint-agnostic grasping for robots with partial observations

    Researchers have developed a new end-to-end pipeline for language-guided grasping that enhances the robustness of mobile manipulators in cluttered environments. This system uses visual-language models (VLMs) and partial…

  15. RESEARCH · CL_18576 ·

    Researchers unveil new stealthy backdoor attacks on AI models using diffusion and style features

    Researchers have developed new methods for backdoor attacks on advanced AI models, specifically targeting Vision-Language Models (VLMs) and Diffusion Models (DMs). One approach, CBV, uses diffusion models to create natu…

  16. RESEARCH · CL_18299 ·

    New GLANCE framework enhances VLM agents with curiosity-driven visual-linguistic exploration

    Researchers have developed a new framework called GLANCE to enhance the exploration capabilities of Visual-Linguistic Model (VLM) agents. This framework aims to improve how these agents navigate complex and partially ob…

  17. TOOL · CL_15782 ·

    New benchmark reveals video models forget long-term context

    Researchers have introduced SceneBench, a new benchmark designed to evaluate video understanding models' ability to retain context over long videos, particularly across different scenes. Their findings indicate that cur…

  18. TOOL · CL_15622 ·

    VISTA benchmark launched for advanced VLM spatio-temporal interaction analysis

    Researchers have introduced VISTA, a new benchmark designed to evaluate the spatio-temporal understanding capabilities of Vision-Language Models (VLMs). Unlike existing benchmarks that focus on simple actions and limite…

  19. TOOL · CL_15616 ·

    Researchers propose Gromov-Wasserstein distance for VLM vision encoder selection

    Researchers have developed a new method for selecting optimal vision encoders for Vision-Language Models (VLMs). Traditional approaches, like choosing encoders with high accuracy or large size, were found to be ineffect…

  20. TOOL · CL_15611 ·

    Chain of Evidence framework enables pixel-level visual attribution for retrieval-augmented generation

    Researchers have developed a new framework called Chain of Evidence (CoE) to improve iterative retrieval-augmented generation (iRAG) systems. CoE utilizes Vision-Language Models to directly analyze screenshots of retrie…