World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal
1
AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios
Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
Transferring the Intelligence of VLMs to Robotic Control
DiaVLo: Diagnosing Behaviours of Vision-Language Models
Perception, Layout, and Validation: Calibrated Confidence for Reliable Straight-Through Processing of Financial Documents
Robot Visions: Breaking reCAPTCHA at Zero Cost and Zero Shot
1
In-Context Robot Learning with VLM Agents
1
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs
1
Show-Harness: Just a VLM Agent Can Play Robots
Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization
1
Canonical Color as a Lens into Concept Decodability in Vision Encoders and VLMs
1
VoT: Vision-of-Thought for Unified Multimodal Representation Alignment
1
Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models
1
TaichuAI/ZDTaichu5.0-9B — new model trending #30 on Hugging Face
15 min1
Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection
SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution
Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation
AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition
