A diameter criterion tied to a potential function certifies convergence of difference inclusions, enabling discrete proofs for first-order optimization methods with diminishing steps.
Advances in neural information processing systems , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
A new dataset-level non-strict symmetry measure allows deriving bounded equivariance for restoration models and motivates an adaptive network that aligns with per-sample symmetry to reduce expected risk.
LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.
Human visual interestingness is linearly decodable from final-layer embeddings in Qwen3-VL-8B and becomes progressively more structured across vision and language layers without explicit supervision.
citing papers explorer
-
Convergence of difference inclusions via a diameter criterion
A diameter criterion tied to a potential function certifies convergence of difference inclusions, enabling discrete proofs for first-order optimization methods with diminishing steps.
-
Aligning Network Equivariance with Data Symmetry: A Theoretical Framework and Adaptive Approach for Image Restoration
A new dataset-level non-strict symmetry measure allows deriving bounded equivariance for restoration models and motivates an adaptive network that aligns with per-sample symmetry to reduce expected risk.
-
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.
-
Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers
Human visual interestingness is linearly decodable from final-layer embeddings in Qwen3-VL-8B and becomes progressively more structured across vision and language layers without explicit supervision.