Firehose

Filtered to Papers, tagged “vision-language models” · clear filters

Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives

All People Companies Papers Podcasts Hacker News

Browse by tag

continual learning 31 reinforcement learning 10 language models 4 robotics 4 agents 3 large language models 3 recursive self-improvement 3 vision-language models 3

17 SEP 2026 · Paper

Region-Level Policy Optimization for Fine-grained MLLM Perception

This paper optimizes the performance of large language models (LLMs) on fine-grained visual perception tasks by learning to selectively focus on relevant regions of the image, rather than relying on high-resolution visual encoding. By doing so, it can improve accuracy with fewer visual tokens, making it more efficient and effective for real-world applications.

vision-encoding region proposal networks reinforcement learning continual learning vision-language models

16 SEP 2026 · Paper

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

This paper develops a new method for image captioning that also grounds each phrase with a specific region of the image, allowing for more accurate and detailed descriptions. Practitioners might care about this work if they're building AI systems that need to understand and interact with the physical world.

vision-language models panoptic segmentation captioning grounding mask proposals

16 SEP 2026 · Paper

In-Context Robot Learning with VLM Agents

This paper develops a framework for robots to learn from context without relying on pre-programmed demonstrations, allowing them to adapt to new environments. Practitioners might care because this technology could enable robots to perform tasks more efficiently and effectively in real-world situations.

embodied AI vision-language models continual learning robot learning robotics