Papers

Filtered to visual perception · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them

21 upvotes · 30 JUL 2026 · Yang Zhou, Zixuan Huang, Sunzhu Li et al.

This paper develops a framework, SpatialCLI, to help vision-language models (VLMs) better understand and use visual tools to make better decisions. By training VLMs to reason with spatial tools and then internalize those capabilities, SpatialCLI can improve the performance of VLMs in tasks that require visual reasoning.

vision-language modelsspatial reasoningvisual perceptionembodied agentsreinforcement learning

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models

13 upvotes · 27 JUL 2026 · Zichao Lin, Yifeng Xie, Bowen Qu et al.

This paper introduces a benchmark to evaluate the atomic visual perception capabilities of large language models, which are often unable to accurately perceive visual information. Practitioners may care about this research because it provides a standardized way to measure and diagnose the limitations of visual perception in MLLMs.

multimodal large language modelsvisual perceptionatomic capabilitiesbenchmarkingperceptual errors