Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue
Paper • 2606.31719 • Published • 4
陈凯
donasalva
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue upvoted a paper 12 days ago
Looped World Models liked a dataset 13 days ago
PegasusJEsus/Code_DatasetOrganizations
None yet
upvoted a paper about 5 hours ago
upvoted a paper 12 days ago
upvoted a paper 15 days ago
upvoted 3
papers about 1 month ago
SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control
Paper • 2605.27891 • Published • 8
LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
Paper • 2605.29888 • Published • 34
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 196
upvoted a paper about 2 months ago
upvoted 4
papers 3 months ago
Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
Paper • 2604.01618 • Published • 15
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 509
Falcon Perception
Paper • 2603.27365 • Published • 16
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 353
upvoted 4
papers 4 months ago
InCoder-32B: Code Foundation Model for Industrial Scenarios
Paper • 2603.16790 • Published • 312
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
Paper • 2602.22859 • Published • 150
A Very Big Video Reasoning Suite
Paper • 2602.20159 • Published • 526
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper • 2602.10693 • Published • 221