HodgeCover isolates the harmonic kernel of a simplicial Laplacian on an expert 2-complex to identify irreducible merge cycles and selects experts for aggressive compression, matching or exceeding baselines on open-weight MoE models.
hub Baseline reference
Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 64(9):99–106
Baseline reference. 60% of citing Pith papers use this work as a benchmark or comparison.
17
Pith papers citing it
Baseline
60% of classified citations
hub tools
citation-role summary
dataset 3
background 2
citation-polarity summary
representative citing papers
Allowing each quantization group to select among multiple 4-bit grids improves accuracy over single-grid FP4 for both post-training and pre-training of LLMs.
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
DCDM replaces positional blocks with learnable semantic chunks via differentiable Chunking Attention, yielding consistent gains over block and unstructured diffusion baselines up to 1.5B parameters.
Complete-muE combines active-width μP and activated-expert scaling to transfer hyperparameters across dense FFN, dense MoE, and sparse MoE while covering changes in experts, capacity, width, depth, batch size, and duration.
Nonlinear Bipolar Compensation with Bipolar Logarithmic Transformation reduces outlier effects in post-training quantization by performing compensation in a compressed transformed space.
Bell-shaped time sampling accelerates masked diffusion language model training by roughly 4x on LM1B by countering locality bias in language data.
PARSE trains a prompt-aware linear router on dense-model outputs to select dynamic SVD ranks, improving accuracy up to 10% at 0.6 compression ratio on LLaMA-7B while delivering 2.5x prefill and 2.4x decode speedups.
A shared global expert pool in MoE improves validation loss over per-layer experts and allows sublinear expert-parameter growth with depth.
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
HyLo upcycles Transformer LLMs into hybrids with MLA and Mamba2/Gated DeltaNet blocks via staged training and distillation, extending context to 2M tokens and outperforming prior upcycled hybrids on long-context benchmarks.
ScaLoRA analytically derives per-update column scalings that let low-rank increments accumulate into high-rank weight updates, yielding faster convergence and higher accuracy than prior LoRA variants on LLMs up to 12B parameters.
TAH-Quant introduces tile-wise adaptive Hadamard quantization for activations in pipeline parallelism, achieving 3-4 bit compression with up to 4.3x throughput speedup and O(1/sqrt(T)) convergence matching SGD.
FINCH is a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average during LLM fine-tuning while matching standard task performance across several benchmarks.
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
Cubit replaces Transformer's attention with a closed-form Kernel Ridge Regression token mixer and reports larger gains as training sequence length increases.
LoPT splits LLM post-training at the midpoint with task loss on the second half and feature reconstruction on the first half to reduce cost and interference.
citing papers explorer
No citing papers match the current filters.