L-layer transformers under Log-ICoT curriculum provably learn k-parity with poly(n) samples and log k stages, matching explicit CoT efficiency without inference overhead.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Depth-Attention mixes values from earlier layers into the current attention value by having the query attend to previous-layer keys at the same position, yielding lower perplexity and up to 2.3 points higher average accuracy than vanilla transformers on Qwen3-style models with negligible extra FLOPs
A transformer-encoded spherical normalizing flow achieves state-of-the-art angular resolution for IceCube neutrino tracks and showers, improving median resolution by factors of 1.3-2.5 over B-spline likelihoods at 100 TeV and outperforming prior ML methods for muons.
AOT-POT adaptively reshapes complex PDE solution operators via input-dependent transformations and parallel stream mixing to enable effective large-scale pre-training, yielding SOTA results on 12 benchmarks with minimal added parameters.
SiameseNorm is a two-stream architecture that reconciles Pre-Norm and Post-Norm in Transformers by coupling streams via shared residual blocks, yielding performance gains with maintained stability on language, vision, and diffusion models.
Hyper-Connections models show stream collapse to a dominant stream with near-identity residual mixing after seeding; symmetry-breaking initialization mitigates dominance and raises performance.
LLMs disperse meaning-preserving prompts internally instead of clustering them, which produces an excessively high upper bound on output log-probability differences via Taylor expansion and Cauchy-Schwarz.
citing papers explorer
-
Transformers Provably Learn to Internalize Chain-of-Thought
L-layer transformers under Log-ICoT curriculum provably learn k-parity with poly(n) samples and log k stages, matching explicit CoT efficiency without inference overhead.
-
Depth-Attention: Cross-Layer Value Mixing for Language Models
Depth-Attention mixes values from earlier layers into the current attention value by having the query attend to previous-layer keys at the same position, yielding lower perplexity and up to 2.3 points higher average accuracy than vanilla transformers on Qwen3-style models with negligible extra FLOPs
-
Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere
A transformer-encoded spherical normalizing flow achieves state-of-the-art angular resolution for IceCube neutrino tracks and showers, improving median resolution by factors of 1.3-2.5 over B-spline likelihoods at 100 TeV and outperforming prior ML methods for muons.
-
AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
AOT-POT adaptively reshapes complex PDE solution operators via input-dependent transformations and parallel stream mixing to enable effective large-scale pre-training, yielding SOTA results on 12 benchmarks with minimal added parameters.
-
SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
SiameseNorm is a two-stream architecture that reconciles Pre-Norm and Post-Norm in Transformers by coupling streams via shared residual blocks, yielding performance gains with maintained stability on language, vision, and diffusion models.
-
Analyzing Stream Collapse in Hyper-Connections: From Diagnosis to Mitigation
Hyper-Connections models show stream collapse to a dominant stream with near-identity residual mixing after seeding; symmetry-breaking initialization mitigates dominance and raises performance.
-
Understanding the Prompt Sensitivity
LLMs disperse meaning-preserving prompts internally instead of clustering them, which produces an excessively high upper bound on output log-probability differences via Taylor expansion and Cauchy-Schwarz.