SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.
Xing , title =
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
An RL agent learns domain re-weighting policies from evaluation feedback to improve balanced performance in continual pre-training of LLMs across source and target domains.
A new 30k-instance semantic segmentation dataset plus block distillation with sink tokens, dropout, and weighted loss lets block-attention models reach near full-attention performance on long texts.
LLMs exhibit three geometric phases in next-token prediction—seeding multiplexing, hoisting overriding, and focal convergence—where predictive subspaces rise, stabilize, and converge across layers.
A3 splits Transformer layers into QK, OV, and MLP components and derives analytical low-rank approximations that reduce hidden dimensions while minimizing each component's functional loss, yielding better perplexity than prior low-rank methods on LLaMA models.
Pretraining data determines loss-to-loss scaling laws in LLMs, while model size, optimization, tokenizer, and architecture have limited impact.
Setting β in balanced Adam to achieve a refresh count R_β ≈1000 based on effective learning horizon T_ES improves validation robustness over fixed-β baselines across 11 vision and language experiments.
SEDD delivers a distributed GPU deduplication system that reports up to 158x speedup over CPU baselines and 7.8x over NeMo Curator on 30M documents while preserving MinHash fidelity above 0.95 Jaccard.
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.
citing papers explorer
-
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.
-
Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training
An RL agent learns domain re-weighting policies from evaluation feedback to improve balanced performance in continual pre-training of LLMs across source and target domains.
-
Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation
A new 30k-instance semantic segmentation dataset plus block distillation with sink tokens, dropout, and weighted loss lets block-attention models reach near full-attention performance on long texts.
-
A Geometric Perspective on Next-Token Prediction in Large Language Models: Three Emerging Phases
LLMs exhibit three geometric phases in next-token prediction—seeding multiplexing, hoisting overriding, and focal convergence—where predictive subspaces rise, stabilize, and converge across layers.
-
A3 : an Analytical Low-Rank Approximation Framework for Attention
A3 splits Transformer layers into QK, OV, and MLP components and derives analytical low-rank approximations that reduce hidden dimensions while minimizing each component's functional loss, yielding better perplexity than prior low-rank methods on LLaMA models.
-
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
Pretraining data determines loss-to-loss scaling laws in LLMs, while model size, optimization, tokenizer, and architecture have limited impact.
-
Refresh-Scaling the Memory of Balanced Adam
Setting β in balanced Adam to achieve a refresh count R_β ≈1000 based on effective learning horizon T_ES improves validation robustness over fixed-β baselines across 11 vision and language experiments.
-
SEDD: Scalable and Efficient Dataset Deduplication with GPUs
SEDD delivers a distributed GPU deduplication system that reports up to 158x speedup over CPU baselines and 7.8x over NeMo Curator on 30M documents while preserving MinHash fidelity above 0.95 Jaccard.
-
A Survey of Large Language Models
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
-
Bias in Large Language Models: Origin, Evaluation, and Mitigation
A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.