HOPE for keeping AI experts partnered
HOPE partners AI experts to keep them together in the ecosystem.
Stories per day · 30 days
2 RSS
Relateddinov32elastic-inference2sparsity2transformers2alignment1autoencoder1efficiency1experts1hardware-guidance1huggingface1jailbreak1llm-compression1llm-safety1nemotron1neuron-removal1quantization1qwen1reasoning1
17 stories, newest first · one card per story
Stories tagged #pruning
AutoCompress Framework for Hardware-Guided Model Compression
AutoCompress optimizes LLM architectures for latency and memory constraints, improving accuracy over Minitron by up to 6.57 percentage points.
Addition by Subtraction strengthens LLM safety alignment against pruning and jailbreaks
Addition by Subtraction removes safety-critical neurons during finetuning to produce models robust to sparsity-based attacks and black-box jailbreaks.
WISD self-distills reasoning models using a deliberately weaker copy
Pruning raises Qwen3.5-4B from 57.7% to 70.5% on HMMT 2025 and from 39.1% to 56.7% on LiveCodeBench v6.
New pruning method balances quality and diversity for reasoning models
Direct pass@k optimization selects partial solutions to maximize correct final answers while penalizing redundancy in test-time scaling.
Your Transformer Is Secretly Elastic
A retraining-free method turns transformers into elastic models that prune smoothly up to 60% sparsity.
Your Transformer Is Secretly Elastic
A retraining-free method makes pretrained transformers elastic, pruning smoothly to 60% sparsity with small accuracy loss.
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
SparseDecoding prunes LLMs using decoding activations, speeding generation up to 1.48x.
DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency
DeCoPrune cuts over 85% of video-diffusion KV tokens while preserving long-range recall.
Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs
Pruning SLAM-ASR audio encoders widens demographic WER gaps that aggregate error rates hide.
Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery
Six Whisper encoder layers are pruned and partly recovered with label-free distillation.
Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem
Multiverse Computing frames LLM block pruning as an Ising optimization problem.
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Neural Spectral Capacity scores architectures from their specs alone and prunes LLaMA-7B to 5.7B without calibration data.
Higher-order pruning of experts in mixture-of-experts language models
New HOPE method uses second-order objectives to prune Mixture-of-Experts LLMs, outperforming REAP at 50% pruning on models up to 122B parameters.
What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity
Pruning study across four LLM architectures finds dense models degrade sharply on smart-home tool calling while MoE models tolerate far more.
SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions
SQS unifies weight pruning and low-bit quantization via Bayesian variational learning, compressing Llama3.2 and Qwen2.5 at higher rates with comparable accuracy.
Lightweight Vision Transformer Compression for On-Device Plant Disease Detection in Resource-Constrained Agricultural Field Conditions
A unified ViT compression pipeline (H-BAC pruning, quantization, distillation) cuts plant-disease models 54.5x to 6.01 MB while keeping 95.13% accuracy.