Entities · Models
Qwen2.5-VL-3B
7 articles tagged with this entity.
-
Can OCR-VLMs Read Devanagari? A Stress-Test Benchmark and Post-Correction Study
-
Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models
-
GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models
-
RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning
-
SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics
-
Once-For-All: A Train-Once and Select-Anytime Framework for Multimodal Instruction Tuning
-
DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models