—
ABot-Earth 0.5 Generative 3D Model of the Earth
—
@_akhaliq
-
ABot-Earth 0.5: Generative 3D Model of the Earth
By
–
-
Latent Spatial Memory for Video World Models
By
–
Latent Spatial Memory for Video World Models pic.twitter.com/sJIpofmrmQ
— AK (@_akhaliq) 9 juin 2026Latent Spatial Memory for World Models
-
Evaluation of interaction and spatial reasoning of multimodal agents
By
–
SpatialWorld Evaluation of interaction and spatial reasoning of multimodal agents in real-world tasks
-
Code2LoRA: Hypernetwork Adapters for Code Models
By
–
Code2LoRA
— AK (@_akhaliq) 5 juin 2026
Hypernetwork-Generated Adapters for Code Language Models under Software Evolution pic.twitter.com/e4vq1C83mYCode2LoRA
Hypernetwork-Generated Adapters for Code Language Models under Software Evolution -
ArcANE: Do Role-Playing Agents Stay in Character at Right Time?
By
–
ArcANE Do Role-Playing Language Agents Stay in Character at the Right Time?
-
Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching
By
–
Bootstrap Your Generator Unpaired Visual Editing with Flow Matching
-
VLMs: Do They Know When Not to Answer Spatial Questions?
By
–
Seeing Isn't Knowing Do VLMs Know When Not to Answer Spatial Questions (and Why)?
-
GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization
By
–
GPU Forecasters Language Models as Selective Surrogates for Kernel Runtime Optimization
-
Crafter: Multi-Agent Harness for Editable Scientific Figure Generation
By
–
Crafter A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
-
GrepSeek: Training Search Agents for Direct Corpus Interaction
By
–
GrepSeek Training Search Agents for Direct Corpus Interaction