Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
Prompt-based agent memory inevitably saturates the context window, but alternating fast in-context skill distillation with slow parametric consolidation turns ephemeral interaction traces into durable model competence.
Aggressive 4-bit quantization can cripple MLLM performance, but a novel residual reconstruction technique recovers lost capabilities with minimal overhead.
