Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs Paper • 2609.32259 • Published 13 days ago • 101
AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines Paper • 2610.01108 • Published 11 days ago • 14
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling Paper • 2609.38104 • Published 13 days ago • 10
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation Paper • 2610.00686 • Published 12 days ago • 12
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop Paper • 2610.00559 • Published 12 days ago • 43
abenzerps/Qwen-Image-2.1-Uncensored-Quantized Text-to-Image • 7B • Updated about 2 hours ago • 2.19M • 4.02k