Entities · Models
Qwen3-VL-8B
14 articles tagged with this entity.
-
Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering
-
Can OCR-VLMs Read Devanagari? A Stress-Test Benchmark and Post-Correction Study
-
SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference
-
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
-
Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models
-
Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
-
ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation
-
Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval
-
AdaCodec: A Predictive Visual Code for Video MLLMs
-
Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers
-
SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification
-
RAPTOR+: A Visually Grounded Vision-Language Framework to Improve Clinical Trust and Auditability in Automated Cancer Referral Processing
-
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
-
ETCHR: Editing To Clarify and Harness Reasoning