Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
Paper • 2605.09681 • Published • 6
Jason Ji
JasonTTY
AI & ML interests
None yet
Recent Activity
submitted a paper about 5 hours ago
Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models authored a paper about 23 hours ago
AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement authored a paper about 23 hours ago
Token Economics for LLM Agents: A Dual-View Study from Computing and EconomicsOrganizations
None yet
submitted a
paper to Daily Papers about 5 hours ago
authored 3
papers about 23 hours ago
AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement
Paper • 2511.23475 • Published • 43
Token Economics for LLM Agents: A Dual-View Study from Computing and Economics
Paper • 2605.09104 • Published • 5
Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
Paper • 2605.09681 • Published • 6