Unverified50% confidenceFactExact time
DAQ (Decision-Aligned Post-Training Quantization) is a post-training quantization method for spiking Transformers that calibrates the quantizer to align neuron firing decisions.
1
Sources
50%
Confidence
Long-term
Relevance
11/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDAQ changes the calibration objective of the quantizer from minimizing numerical error to aligning firing decisions, making the neuron firing decisions after quantization as consistent as possible with the firing decisions of the floating-point reference model.79% similarUnverifiedDAQ constructs an objective function that encourages the quantized membrane variables to remain within the reference firing region along the quantized model's own state trajectory, thereby reducing the disruption of quantization to spike firing patterns.66% similarUnverifiedThe researchers propose Dynamics-aware Token Merging (DaTMe), a training-free acceleration strategy that bases token merging decisions on the dynamics of the diffusion process.64% similarUnverified有向无环图(DAG)能通过后门准则精确推导出控制混杂所需的最小变量集62% similarVerifiedA workflow is essentially a process orchestration in a Directed Acyclic Graph (DAG) structure, suitable for handling deterministic tasks with fixed steps and predictable logic.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1182843API
curl https://kongchang.com/api/v1/knowledge/claims/1182843MCP
get_claim(id=1182843)