michal.i/o
- 2023-04-14 - Combined Scaling for Zero-shot Transfer Learning
- 2023-12-04 - MobileCLIP - Fast Image-Text Models through Multi-Modal Reinforced Training
- 2023-12-04 - Rejuvenating image-GPT as Strong Visual Representation Learners
- 2023-12-05 - Mamba Linear-Time Sequence Modeling with Selective State Spaces
- 2023-12-09 - SILC Improving Vision Language Pretraining with Self-Distillation
- 2023-12-09 - Text as Image Learning Transferable Adapter for Multi-Label Classification
- 2023-12-17 - Stable and low-precision training for large-scale vision-language models
- 2024-10-04 - Movie Gen A Cast of Media Foundation Models
- 2024-10-10 - Pixtral 12B
- 2024-11-03 - GATED DELTA NETWORKS IMPROVING MAMBA2 WITH DELTA RULE
- 2024-11-03 - On the Efficiency of Convolutional Neural Networks
- 2024-11-03 - ReMoE FULLY DIFFERENTIABLE MIXTURE-OF-EXPERTS WITH RELU ROUTING
- 2024-11-03 - TokenFormer - RETHINKING TRANSFORMER SCAL-ING WITH TOKENIZED MODEL PARAMETERS
- 2024-11-17 - Mixture-of-Transformers A Sparse and Scalable Architecture for Multi-Modal Foundation Models
- Bad apples for label noise early stopping
- Early Fusion Multimodal Encoder Models
- Latent Transformers with small vocabularies
- Learn to Initialize from OS Models
- Learning Skip Layers
- Multi Modal Learning to Rank as a replacement for CLIP
- Recurrent Computation with Transformers by repeating layers
- Remove all the things
- Sapiens for Robotics
- Small Proxy model to predict loss for given sample
- SSMs 4 Rec
- Task Routing for Multimodal LLMs
- Tiny Foundational model by distilling from a lot of SOTA models
- Tiny LLMs with rag in the middle
- Two Stream SSMs
- Universal embedding space for popular foundational models (or adapters)
- Untitled
- VLMs for better Vision Backbones
- White space separated conv text encoder
- 3d
- A glossary of all the ways ML models fail to train
- Active Learning
- Alignment and Post Training
- Approximate Nearest Neighbor Search
- autograd
- benchmarks
- CLIP
- Cloud GPUs
- cnns
- Code LLMs
- compilers
- compression
- Computer Graphics
- Computer Vision Backbones
- contrastive
- Data Formats for ML
- Data Loading
- datasets
- Decoder Transformer Inference
- Deepspeed
- detection
- Diffusion Models
- distill
- Distributed Training
- Embedding Models
- Evaluation Metrics
- Extreme Classification
- FairScale
- feature-stores
- Few Shot Learning
- fine-tuning
- Flow Matching
- GPUs
- graphs
- Human Pose Estimation and Human Modeling
- Image Generation
- Image Recognition
- Imitation Learning
- Instance Recognition and Retrieval
- Instance Retrieval and Instance Recognition
- jax
- Label Noise
- Learning to Rank
- LLM Reasoning and Test Time Compute
- LLM Training and Tuning
- logsumexp
- Long Context Transformers
- Long Tail Classification and Class Imbalance
- Machine Learning Tricks and Best Practices
- maes
- Mamba
- matryoshka embeddings
- medical
- mixture of experts
- ML Conferences
- ML for Math
- ML Infrastructure
- ML Scaling
- MLX
- Mobile Inference
- Model Routing
- Multi Label Classification
- multi-modal
- multi-task
- Natural Language Processing
- nerf
- Networking
- Normalization
- Numerics
- ocr
- paper-params
- Parameter Efficient Fine Tuning (PEFT)
- PrefixLM
- Quantization
- recommenders
- resources
- Retrieval Augmented Generation (RAG)
- Retrieval Augmented Models
- rl
- RL for LMs
- Robotics
- segmentation
- semantic-search
- semisup
- Server Inference
- SLAM
- Small Foundational Models
- softmax
- speech
- State Space Models (SSMs)
- Storage
- Synthetic Data
- Tabular Machine Learning
- Tensor Tricks
- Text Embeddings
- text2sql
- torch compile
- Transformer Alternatives (mostly SSMs)
- Transformer Properties
- transformers
- tricks
- triton
- video
- Video Generation
- Vision - Language Models
- Vision Transformers
- Visual Search
- xformers
- xlstm
torch compile
- 2023-04-14 - Combined Scaling for Zero-shot Transfer Learning
- 2023-12-04 - MobileCLIP - Fast Image-Text Models through Multi-Modal Reinforced Training
- 2023-12-04 - Rejuvenating image-GPT as Strong Visual Representation Learners
- 2023-12-05 - Mamba Linear-Time Sequence Modeling with Selective State Spaces
- 2023-12-09 - SILC Improving Vision Language Pretraining with Self-Distillation
- 2023-12-09 - Text as Image Learning Transferable Adapter for Multi-Label Classification
- 2023-12-17 - Stable and low-precision training for large-scale vision-language models
- 2024-10-04 - Movie Gen A Cast of Media Foundation Models
- 2024-10-10 - Pixtral 12B
- 2024-11-03 - GATED DELTA NETWORKS IMPROVING MAMBA2 WITH DELTA RULE
- 2024-11-03 - On the Efficiency of Convolutional Neural Networks
- 2024-11-03 - ReMoE FULLY DIFFERENTIABLE MIXTURE-OF-EXPERTS WITH RELU ROUTING
- 2024-11-03 - TokenFormer - RETHINKING TRANSFORMER SCAL-ING WITH TOKENIZED MODEL PARAMETERS
- 2024-11-17 - Mixture-of-Transformers A Sparse and Scalable Architecture for Multi-Modal Foundation Models
- Bad apples for label noise early stopping
- Early Fusion Multimodal Encoder Models
- Latent Transformers with small vocabularies
- Learn to Initialize from OS Models
- Learning Skip Layers
- Multi Modal Learning to Rank as a replacement for CLIP
- Recurrent Computation with Transformers by repeating layers
- Remove all the things
- Sapiens for Robotics
- Small Proxy model to predict loss for given sample
- SSMs 4 Rec
- Task Routing for Multimodal LLMs
- Tiny Foundational model by distilling from a lot of SOTA models
- Tiny LLMs with rag in the middle
- Two Stream SSMs
- Universal embedding space for popular foundational models (or adapters)
- Untitled
- VLMs for better Vision Backbones
- White space separated conv text encoder
- 3d
- A glossary of all the ways ML models fail to train
- Active Learning
- Alignment and Post Training
- Approximate Nearest Neighbor Search
- autograd
- benchmarks
- CLIP
- Cloud GPUs
- cnns
- Code LLMs
- compilers
- compression
- Computer Graphics
- Computer Vision Backbones
- contrastive
- Data Formats for ML
- Data Loading
- datasets
- Decoder Transformer Inference
- Deepspeed
- detection
- Diffusion Models
- distill
- Distributed Training
- Embedding Models
- Evaluation Metrics
- Extreme Classification
- FairScale
- feature-stores
- Few Shot Learning
- fine-tuning
- Flow Matching
- GPUs
- graphs
- Human Pose Estimation and Human Modeling
- Image Generation
- Image Recognition
- Imitation Learning
- Instance Recognition and Retrieval
- Instance Retrieval and Instance Recognition
- jax
- Label Noise
- Learning to Rank
- LLM Reasoning and Test Time Compute
- LLM Training and Tuning
- logsumexp
- Long Context Transformers
- Long Tail Classification and Class Imbalance
- Machine Learning Tricks and Best Practices
- maes
- Mamba
- matryoshka embeddings
- medical
- mixture of experts
- ML Conferences
- ML for Math
- ML Infrastructure
- ML Scaling
- MLX
- Mobile Inference
- Model Routing
- Multi Label Classification
- multi-modal
- multi-task
- Natural Language Processing
- nerf
- Networking
- Normalization
- Numerics
- ocr
- paper-params
- Parameter Efficient Fine Tuning (PEFT)
- PrefixLM
- Quantization
- recommenders
- resources
- Retrieval Augmented Generation (RAG)
- Retrieval Augmented Models
- rl
- RL for LMs
- Robotics
- segmentation
- semantic-search
- semisup
- Server Inference
- SLAM
- Small Foundational Models
- softmax
- speech
- State Space Models (SSMs)
- Storage
- Synthetic Data
- Tabular Machine Learning
- Tensor Tricks
- Text Embeddings
- text2sql
- torch compile
- Transformer Alternatives (mostly SSMs)
- Transformer Properties
- transformers
- tricks
- triton
- video
- Video Generation
- Vision - Language Models
- Vision Transformers
- Visual Search
- xformers
- xlstm
Backlinks
- No backlinks found