Fahad Shahbaz Khan

A single visual world model can now execute complex procedural tasks end-to-end, adapting its generation to the actual outcome of each predicted action.

Frontier generalist systems have effectively mastered high-level visual semantics and spatial reasoning, yet they still stubbornly fail to displace dedicated models on metric geometry, dense temporal tracking, and fine-grained visual fidelity.

Achieving GPS-level accuracy in USV position estimation by leveraging horizon line extraction from panoramic images could revolutionize navigation in complex coastal environments.

Achieving a staggering 79x reduction in decoding latency, Parallel Tube Decoding redefines efficiency in spatio-temporal video grounding.

Multi-view MRI inputs can enhance spatial localization but may compromise temporal reasoning, revealing critical limitations in current foundation models for clinical use.

Expensive end-to-end omni pre-training degrades foundational reasoning and vision, yet simply routing timestamped ASR transcripts into a frozen VLM matches or beats native omni architectures across 56 benchmarks.

Navigating the deluge of scientific papers just got easier: Paper Circle uses multi-agent LLMs to automate research discovery and knowledge graph construction, promising faster literature reviews and deeper insights.

Forget choosing just one vision encoder – fusing CLIP and DINO representations unlocks a significant performance boost in vision-language tasks.

Forget cloud GPUs – a new model brings unified multimodal understanding and generation to your iPhone, running 6x faster than alternatives.

Geospatial agents can now reason more effectively about satellite imagery thanks to a new framework that aligns models with verified multi-step tool interactions and explicit reasoning traces.