QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models Paper • 2609.26425 • Published 8 days ago • 5
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation Paper • 2609.38839 • Published 6 days ago • 86
SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs Paper • 2606.20244 • Published Jun 19
VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection Paper • 2605.10229 • Published May 11
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation Paper • 2609.38839 • Published 6 days ago • 86
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation Paper • 2609.38839 • Published 6 days ago • 86
BadWAM: When World-Action Models Dream Right but Act Wrong Paper • 2607.15207 • Published Jul 16 • 45
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation Paper • 2607.07608 • Published Jul 8 • 57
Don't Forget the Nonlinearity: Unlocking Activation Functions in Efficient Fine-Tuning Paper • 2509.13240 • Published Sep 16, 2025 • 1
FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning Paper • 2511.17979 • Published Nov 22, 2025 • 1
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms Paper • 2604.23775 • Published Apr 26 • 45
SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology Paper • 2604.17503 • Published Apr 19
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment Paper • 2605.11882 • Published May 12 • 15
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment Paper • 2605.11882 • Published May 12 • 15
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling Paper • 2604.28185 • Published Apr 30 • 90
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms Paper • 2604.23775 • Published Apr 26 • 45