Today's task: model compression!!
🆕 New at IWSLT! But no less exciting 🔥
🎯 Goal: Compress a large, general-purpose multimodal model, making speech translation more efficient ⚡️, deployable 📲, and sustainable ♻️, while preserving translation quality ⭐️
#AI #SpeechTech #ModelCompression #LLMcompression
🆕 New at IWSLT! But no less exciting 🔥
🎯 Goal: Compress a large, general-purpose multimodal model, making speech translation more efficient ⚡️, deployable 📲, and sustainable ♻️, while preserving translation quality ⭐️
#AI #SpeechTech #ModelCompression #LLMcompression
January 29, 2025 at 4:47 PM
Today's task: model compression!!
🆕 New at IWSLT! But no less exciting 🔥
🎯 Goal: Compress a large, general-purpose multimodal model, making speech translation more efficient ⚡️, deployable 📲, and sustainable ♻️, while preserving translation quality ⭐️
#AI #SpeechTech #ModelCompression #LLMcompression
🆕 New at IWSLT! But no less exciting 🔥
🎯 Goal: Compress a large, general-purpose multimodal model, making speech translation more efficient ⚡️, deployable 📲, and sustainable ♻️, while preserving translation quality ⭐️
#AI #SpeechTech #ModelCompression #LLMcompression
Below 4 bits, the quality drops sharply, and 2-bit models often produce visibly degraded text. If you are choosing a quant, aim for 4-bit to maximize efficiency without sacrificing coherence. #gpuoptimization #batchinference #selfhosting #quantization #llm #modelcompression 2/2
September 25, 2026 at 9:20 PM
Below 4 bits, the quality drops sharply, and 2-bit models often produce visibly degraded text. If you are choosing a quant, aim for 4-bit to maximize efficiency without sacrificing coherence. #gpuoptimization #batchinference #selfhosting #quantization #llm #modelcompression 2/2
See you at #EACL2026 in Rabat 🕌!
#UKPLab #NLProc #ResponsibleAI #Quantization #MLSafety #Fairness #TrustworthyAI #ModelCompression #LLMSafety #EthicalAI #NLP #AIResearch @cs-tudarmstadt.bsky.social @proloewe.bsky.social
#UKPLab #NLProc #ResponsibleAI #Quantization #MLSafety #Fairness #TrustworthyAI #ModelCompression #LLMSafety #EthicalAI #NLP #AIResearch @cs-tudarmstadt.bsky.social @proloewe.bsky.social
March 27, 2026 at 9:36 AM
Tiny LLMs like Bonsai 2 27B bring powerful AI to your phone. #LLMCompression #TinyAI #DeviceAI #PrismML #AI #ModelCompression #Bonsai27B https://thedailytechfeed.com/prismmls-tiny-llm-could-bring-advanced-ai-everywhere/
September 17, 2026 at 11:18 PM
Tiny LLMs like Bonsai 2 27B bring powerful AI to your phone. #LLMCompression #TinyAI #DeviceAI #PrismML #AI #ModelCompression #Bonsai27B https://thedailytechfeed.com/prismmls-tiny-llm-could-bring-advanced-ai-everywhere/
Reducing a neural network’s complexity through pruning, quantization, distillation, or matrix factorization enhances efficiency and scalability, allowing AI systems to deliver comparable performance with lighter architectures and optimized resource use.
#ModelCompression #EdgeAI
#ModelCompression #EdgeAI
January 1, 2026 at 2:30 PM
Reducing a neural network’s complexity through pruning, quantization, distillation, or matrix factorization enhances efficiency and scalability, allowing AI systems to deliver comparable performance with lighter architectures and optimized resource use.
#ModelCompression #EdgeAI
#ModelCompression #EdgeAI
🚀 New Shared Task: Model Compression for Machine Translation at hashtag#WMT2026 (co-located with hashtag#EMNLP2026)!
📅 Test data out on June 18th, submissions by July 2nd!
Can you shrink an LLM and keep translation quality high? 🧠🔧
👉 www2.statmt.org/wmt26/model-... #NLP #ML #LLM #ModelCompression
📅 Test data out on June 18th, submissions by July 2nd!
Can you shrink an LLM and keep translation quality high? 🧠🔧
👉 www2.statmt.org/wmt26/model-... #NLP #ML #LLM #ModelCompression
LinkedIn
This link will take you to a page that’s not on LinkedIn
lnkd.in
April 15, 2026 at 12:30 PM
🚀 New Shared Task: Model Compression for Machine Translation at hashtag#WMT2026 (co-located with hashtag#EMNLP2026)!
📅 Test data out on June 18th, submissions by July 2nd!
Can you shrink an LLM and keep translation quality high? 🧠🔧
👉 www2.statmt.org/wmt26/model-... #NLP #ML #LLM #ModelCompression
📅 Test data out on June 18th, submissions by July 2nd!
Can you shrink an LLM and keep translation quality high? 🧠🔧
👉 www2.statmt.org/wmt26/model-... #NLP #ML #LLM #ModelCompression
Below 4 bits, the quality drops sharply, and 2-bit models often produce visibly degraded text. If you are choosing a quant, aim for 4-bit to maximize efficiency without sacrificing coherence. #gpuoptimization #batchinference #selfhosting #quantization #llm #modelcompression 2/2
September 21, 2026 at 5:20 PM
Below 4 bits, the quality drops sharply, and 2-bit models often produce visibly degraded text. If you are choosing a quant, aim for 4-bit to maximize efficiency without sacrificing coherence. #gpuoptimization #batchinference #selfhosting #quantization #llm #modelcompression 2/2
@cshlnews.bsky.social @princetonneuro.bsky.social
@cmu-neuroscience.bsky.social
#neuroAI #compneuro #neuroscience #visualcortex #closedloop #activelearning #modelcompression #distillation #pruning
www.cshl.edu/ai-monkey-br...
@cmu-neuroscience.bsky.social
#neuroAI #compneuro #neuroscience #visualcortex #closedloop #activelearning #modelcompression #distillation #pruning
www.cshl.edu/ai-monkey-br...
AI, monkey brains, and the virtue of small thinking | Cold Spring Harbor Laboratory
What does it take to make AI that can pass as human? Try massive clusters of supercomputers. To build human-like intelligence, computer scientists think big. However, for neuroscientists who want to u...
www.cshl.edu
February 26, 2026 at 10:32 PM
By the numbers:
16-bit to 8-bit: Statistically indistinguishable outputs
4-bit: The knee of the curve where quality loss remains small
3-bit: Noticeably worse performance
2-bit: Visibly degraded text
#gpuoptimization #batchinference #selfhosting #quantization #llm #modelcompression
16-bit to 8-bit: Statistically indistinguishable outputs
4-bit: The knee of the curve where quality loss remains small
3-bit: Noticeably worse performance
2-bit: Visibly degraded text
#gpuoptimization #batchinference #selfhosting #quantization #llm #modelcompression
September 24, 2026 at 11:35 PM
By the numbers:
16-bit to 8-bit: Statistically indistinguishable outputs
4-bit: The knee of the curve where quality loss remains small
3-bit: Noticeably worse performance
2-bit: Visibly degraded text
#gpuoptimization #batchinference #selfhosting #quantization #llm #modelcompression
16-bit to 8-bit: Statistically indistinguishable outputs
4-bit: The knee of the curve where quality loss remains small
3-bit: Noticeably worse performance
2-bit: Visibly degraded text
#gpuoptimization #batchinference #selfhosting #quantization #llm #modelcompression
We propose Redundant Information Distillation which maximizes the task-relevant common information between teacher and student using a new alternating optimization: #explainability #informationtheory #distillation #modelcompression
May 2, 2025 at 10:45 PM
We propose Redundant Information Distillation which maximizes the task-relevant common information between teacher and student using a new alternating optimization: #explainability #informationtheory #distillation #modelcompression
AI model compression isn't just a technical refinement but a strategic choice that aligns cost reduction, sustainability, and operational agility with the pressing demands of today's rapidly evolving digital landscape.
#AI #ModelCompression #Efficiency
#AI #ModelCompression #Efficiency
March 22, 2025 at 2:30 PM
AI model compression isn't just a technical refinement but a strategic choice that aligns cost reduction, sustainability, and operational agility with the pressing demands of today's rapidly evolving digital landscape.
#AI #ModelCompression #Efficiency
#AI #ModelCompression #Efficiency
Ever wonder how a tiny student net can match a massive ensemble? This paper shows knowledge distillation keeps the student’s capacity just right, squeezing performance without bloat. Dive in for the tricks behind smarter model compression! #KnowledgeDistillation #ModelCompression #EnsembleLearning
April 11, 2026 at 11:15 AM
Ever wonder how a tiny student net can match a massive ensemble? This paper shows knowledge distillation keeps the student’s capacity just right, squeezing performance without bloat. Dive in for the tricks behind smarter model compression! #KnowledgeDistillation #ModelCompression #EnsembleLearning
June 24, 2025 at 6:24 AM
Dynamic expert clustering cuts MoE model parameters by about 80% and boosts throughput 10‑20% while keeping quality on GLUE and WikiText‑103. https://getnews.me/dynamic-expert-clustering-boosts-efficiency-of-moe-large-language-models/ #moe #modelcompression #nlp
October 6, 2025 at 4:27 AM
Dynamic expert clustering cuts MoE model parameters by about 80% and boosts throughput 10‑20% while keeping quality on GLUE and WikiText‑103. https://getnews.me/dynamic-expert-clustering-boosts-efficiency-of-moe-large-language-models/ #moe #modelcompression #nlp
The new LWIQ method cuts tensor‑train rank‑search time by 63.2% and yields a model 3.2× smaller with only a 0.86% drop in top‑1 accuracy on CIFAR‑10 ResNet‑56. https://getnews.me/adaptive-tensor-train-decomposition-improves-network-compression/ #modelcompression #tensortrain #deeplearning
September 18, 2025 at 8:47 PM
The new LWIQ method cuts tensor‑train rank‑search time by 63.2% and yields a model 3.2× smaller with only a 0.86% drop in top‑1 accuracy on CIFAR‑10 ResNet‑56. https://getnews.me/adaptive-tensor-train-decomposition-improves-network-compression/ #modelcompression #tensortrain #deeplearning
PITOME Revolutionizes Transformers by Merging Tokens to Save Memory and Boost Speed 🔬🚀🧠 www.azoai.com/news/2024111... #AI #Innovation #MachineLearning #DeepLearning #TokenMerging #Transformers #GraphTheory #DataEfficiency #ModelCompression #ImageProcessing @arxiv-stat-ml.bsky.social
PITOME Revolutionizes Transformers by Merging Tokens to Save Memory and Boost Speed
Researchers unveil PITOME, a novel token merging technique that accelerates transformer models while preserving critical information for enhanced AI efficiency.
www.azoai.com
November 13, 2024 at 2:26 AM
PITOME Revolutionizes Transformers by Merging Tokens to Save Memory and Boost Speed 🔬🚀🧠 www.azoai.com/news/2024111... #AI #Innovation #MachineLearning #DeepLearning #TokenMerging #Transformers #GraphTheory #DataEfficiency #ModelCompression #ImageProcessing @arxiv-stat-ml.bsky.social
Needle 2: 45M-Parameter Tool-Calling Model Released
#AI #ModelCompression #EdgeAI
https://singulism.com/en/2026-08-15-needle-2-tool-calling-model
#AI #ModelCompression #EdgeAI
https://singulism.com/en/2026-08-15-needle-2-tool-calling-model
Needle 2: 45M-Parameter Tool-Calling Model Released
Cactus Compute releases Needle 2, a 45M-parameter tool-calling model. Runs in 28MB RAM from a 14MB binary.
singulism.com
August 15, 2026 at 2:17 PM
Needle 2: 45M-Parameter Tool-Calling Model Released
#AI #ModelCompression #EdgeAI
https://singulism.com/en/2026-08-15-needle-2-tool-calling-model
#AI #ModelCompression #EdgeAI
https://singulism.com/en/2026-08-15-needle-2-tool-calling-model
FiD-GP reduces Bayesian training cost by orders of magnitude and halves parameter counts, shrinking model size by three-quarters, keeping state-of-the-art accuracy. Read more: https://getnews.me/flow-induced-diagonal-gaussian-processes-enhance-ai-model-compression/ #bayesiandeep #modelcompression
October 6, 2025 at 3:43 PM
FiD-GP reduces Bayesian training cost by orders of magnitude and halves parameter counts, shrinking model size by three-quarters, keeping state-of-the-art accuracy. Read more: https://getnews.me/flow-induced-diagonal-gaussian-processes-enhance-ai-model-compression/ #bayesiandeep #modelcompression
In‑training compression trims SSM hidden dimensions during training, preserving performance while speeding up optimization; paper submitted Oct 2025. Read more: https://getnews.me/in-training-compression-improves-efficiency-of-state-space-models/ #statespacemodels #modelcompression
October 6, 2025 at 8:09 AM
In‑training compression trims SSM hidden dimensions during training, preserving performance while speeding up optimization; paper submitted Oct 2025. Read more: https://getnews.me/in-training-compression-improves-efficiency-of-state-space-models/ #statespacemodels #modelcompression
BALF enables fine-tuning-free compression, cutting FLOPs of ResNeXt-101 by about 45% while incurring only a 1-point top-1 accuracy drop. The paper was submitted in September 2025. Read more: https://getnews.me/balf-enables-fine-tuning-free-neural-network-compression/ #balf #modelcompression
October 1, 2025 at 3:22 AM
BALF enables fine-tuning-free compression, cutting FLOPs of ResNeXt-101 by about 45% while incurring only a 1-point top-1 accuracy drop. The paper was submitted in September 2025. Read more: https://getnews.me/balf-enables-fine-tuning-free-neural-network-compression/ #balf #modelcompression
RMT‑KD leverages random matrix theory for knowledge distillation, trimming up to 80% of model parameters with just ~2% accuracy loss and 2.8× faster inference. https://getnews.me/random-matrix-theory-powers-new-ai-model-compression-technique/ #randommatrixtheory #modelcompression
September 30, 2025 at 12:58 AM
RMT‑KD leverages random matrix theory for knowledge distillation, trimming up to 80% of model parameters with just ~2% accuracy loss and 2.8× faster inference. https://getnews.me/random-matrix-theory-powers-new-ai-model-compression-technique/ #randommatrixtheory #modelcompression
COSPADI compresses large language models without additional training, using calibration‑guided sparse dictionary factorization to achieve 20‑50% reduction while preserving accuracy. https://getnews.me/cospadi-sparse-dictionary-learning-boosts-llm-compression/ #llm #modelcompression #sparselearning
September 29, 2025 at 11:36 AM
COSPADI compresses large language models without additional training, using calibration‑guided sparse dictionary factorization to achieve 20‑50% reduction while preserving accuracy. https://getnews.me/cospadi-sparse-dictionary-learning-boosts-llm-compression/ #llm #modelcompression #sparselearning
SlimDiff compresses diffusion models without training, achieving up to 35% faster inference and removing about 100 million parameters while maintaining quality. https://getnews.me/slimdiff-enables-training-free-compression-of-diffusion-models/ #slimdiff #diffusionmodels #modelcompression
September 29, 2025 at 5:50 AM
SlimDiff compresses diffusion models without training, achieving up to 35% faster inference and removing about 100 million parameters while maintaining quality. https://getnews.me/slimdiff-enables-training-free-compression-of-diffusion-models/ #slimdiff #diffusionmodels #modelcompression
A unified framework merges tensor decomposition with automatic rank selection, cutting manual grid searches and using continuous optimization to compress models while keeping accuracy. https://getnews.me/unified-framework-for-neural-network-compression-with-rank-selection/ #modelcompression #nn
September 25, 2025 at 1:11 PM
A unified framework merges tensor decomposition with automatic rank selection, cutting manual grid searches and using continuous optimization to compress models while keeping accuracy. https://getnews.me/unified-framework-for-neural-network-compression-with-rank-selection/ #modelcompression #nn
Location‑aware discriminant analysis compresses detectors, cutting model size while preserving accuracy; on KITTI and COCO the pruned models matched or beat the originals. https://getnews.me/location-aware-discriminant-analysis-improves-visual-detector-compression/ #locationaware #modelcompression
September 25, 2025 at 5:08 AM
Location‑aware discriminant analysis compresses detectors, cutting model size while preserving accuracy; on KITTI and COCO the pruned models matched or beat the originals. https://getnews.me/location-aware-discriminant-analysis-improves-visual-detector-compression/ #locationaware #modelcompression