Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University, Shanghai Innovation Institute
4
0
6
Agentic AI inference can be accelerated by 2-6x with history-free speculative decoding that eliminates KV cache overhead and boosts acceptance rates by up to 70%.
Key contribution not extracted.
Adapter design can make or break coding performance in OpenClaw-style agents, with a full adapter boosting success rates by over 50 percentage points.
Infini Memory redefines long-term memory for LLMs, achieving a 64.7% score on MemoryAgentBench by structuring memory as topic documents that evolve over time.