Yedidia AGNIMO
Yedson54
AI & ML interests
Reinforcement Learning, Federated Learning
Organizations
AI-Generated Content Detection
Artificial General Intelligence [AGI]
Education
Federated Learning (FL) - Decentralized Scheme
-
Towards Building the Federated GPT: Federated Instruction Tuning
Paper • 2305.05644 • Published • 5 -
Low-Resource Machine Translation through the Lens of Personalized Federated Learning
Paper • 2406.12564 • Published • 3 -
Towards a Personal Health Large Language Model
Paper • 2406.06474 • Published • 24 -
Analytic Federated Learning
Paper • 2405.16240 • Published
Interpretability and Analysis
Long Context
-
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Paper • 2407.02490 • Published • 27 -
Can Few-shot Work in Long-Context? Recycling the Context to Generate Demonstrations
Paper • 2406.13632 • Published • 5 -
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
Paper • 2406.15319 • Published • 64 -
Make Your LLM Fully Utilize the Context
Paper • 2404.16811 • Published • 55
Model Training - Learning Scheme
-
Instruction Pre-Training: Language Models are Supervised Multitask Learners
Paper • 2406.14491 • Published • 95 -
Pre-training Small Base LMs with Fewer Tokens
Paper • 2404.08634 • Published • 35 -
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
Paper • 2405.15319 • Published • 29 -
Can LLMs Learn by Teaching? A Preliminary Study
Paper • 2406.14629 • Published • 21
Multimodal LMs
-
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Paper • 2406.16860 • Published • 63 -
PaliGemma: A versatile 3B VLM for transfer
Paper • 2407.07726 • Published • 72 -
E5-V: Universal Embeddings with Multimodal Large Language Models
Paper • 2407.12580 • Published • 41 -
Emu3: Next-Token Prediction is All You Need
Paper • 2409.18869 • Published • 95
Prompt Engineering - InContext Learning
Reinforcement Learning (RL / RLHF)
-
RLHF Workflow: From Reward Modeling to Online RLHF
Paper • 2405.07863 • Published • 71 -
Understanding and Diagnosing Deep Reinforcement Learning
Paper • 2406.16979 • Published • 10 -
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 62 -
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
Paper • 2407.00617 • Published • 7
Self-Supervised Learning
-
Learning and Leveraging World Models in Visual Representation Learning
Paper • 2403.00504 • Published • 33 -
To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review
Paper • 2304.09355 • Published • 5 -
A Cookbook of Self-Supervised Learning
Paper • 2304.12210 • Published • 6
Small Language Model - Mobile Phone
Transfer Learning - FineTuning SFT - Instruction
-
Training Task Experts through Retrieval Based Distillation
Paper • 2407.05463 • Published • 10 -
Instruction Pre-Training: Language Models are Supervised Multitask Learners
Paper • 2406.14491 • Published • 95 -
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
Paper • 2409.12903 • Published • 22 -
A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
Paper • 2410.13841 • Published • 17
Vision-language model (VLMs)
-
What matters when building vision-language models?
Paper • 2405.02246 • Published • 103 -
An Introduction to Vision-Language Modeling
Paper • 2405.17247 • Published • 90 -
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
Paper • 2407.03320 • Published • 95 -
Building and better understanding vision-language models: insights and future directions
Paper • 2408.12637 • Published • 133
xAI
Deep Learning
Times Series
Factuality - Faithfulness - Hallucination
-
Training Language Models to Self-Correct via Reinforcement Learning
Paper • 2409.12917 • Published • 140 -
FactAlign: Long-form Factuality Alignment of Large Language Models
Paper • 2410.01691 • Published • 9 -
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Paper • 2410.02707 • Published • 47 -
ECon: On the Detection and Resolution of Evidence Conflicts
Paper • 2410.04068 • Published
Coding LLMs
Alignment and Unlearning
-
Learn Your Reference Model for Real Good Alignment
Paper • 2404.09656 • Published • 89 -
Aligning Teacher with Student Preferences for Tailored Training Data Generation
Paper • 2406.19227 • Published • 25 -
Self-Play Preference Optimization for Language Model Alignment
Paper • 2405.00675 • Published • 27 -
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues
Paper • 2404.03820 • Published • 26
Synthetic Data Generation
Efficient LMs
-
How to Train Data-Efficient LLMs
Paper • 2402.09668 • Published • 42 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 74 -
SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning
Paper • 2407.07523 • Published • 6 -
Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models
Paper • 2407.12327 • Published • 79
Fundational - Deep Learning
-
Just How Flexible are Neural Networks in Practice?
Paper • 2406.11463 • Published • 7 -
Not All Language Model Features Are Linear
Paper • 2405.14860 • Published • 41 -
KAN: Kolmogorov-Arnold Networks
Paper • 2404.19756 • Published • 115 -
An Interactive Agent Foundation Model
Paper • 2402.05929 • Published • 30
Surveys - Literature Reviews
-
A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models
Paper • 2406.11289 • Published • 5 -
Best Practices and Lessons Learned on Synthetic Data for Language Models
Paper • 2404.07503 • Published • 31 -
Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models
Paper • 2407.12327 • Published • 79 -
Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges
Paper • 2408.08946 • Published • 12
Model Evolution - Updates - Compatibility
Architectures
-
Associative Recurrent Memory Transformer
Paper • 2407.04841 • Published • 36 -
Mixture-of-Agents Enhances Large Language Model Capabilities
Paper • 2406.04692 • Published • 60 -
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Paper • 2405.21060 • Published • 67 -
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Paper • 2404.14219 • Published • 259
Optimization
Reasoning
-
Chain-of-Knowledge: Integrating Knowledge Reasoning into Large Language Models by Learning from Knowledge Graphs
Paper • 2407.00653 • Published • 13 -
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Paper • 2406.18629 • Published • 42 -
Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities
Paper • 2406.14562 • Published • 28 -
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Paper • 2406.04271 • Published • 30
ReadLater
Sequence Modeling
Tabular Data - SpreadSheets
Uncertainty Quantification
Models
-
Qwen2-Audio Technical Report
Paper • 2407.10759 • Published • 62 -
Qwen2 Technical Report
Paper • 2407.10671 • Published • 167 -
Gemma 2: Improving Open Language Models at a Practical Size
Paper • 2408.00118 • Published • 79 -
EXAONE 3.0 7.8B Instruction Tuned Language Model
Paper • 2408.03541 • Published • 35
FUN
-
Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names
Paper • 2408.00298 • Published • 11 -
Achieving Human Level Competitive Robot Table Tennis
Paper • 2408.03906 • Published • 28 -
Learning to Move Like Professional Counter-Strike Players
Paper • 2408.13934 • Published • 23 -
DrawingSpinUp: 3D Animation from Single Character Drawings
Paper • 2409.08615 • Published • 19
Applications
-
SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
Paper • 2408.15545 • Published • 38 -
InkubaLM: A small language model for low-resource African languages
Paper • 2408.17024 • Published • 14 -
From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents
Paper • 2409.03512 • Published • 29 -
Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
Paper • 2409.04109 • Published • 48
Scientific Research - Discovery
-
Can Large Language Models Unlock Novel Scientific Research Ideas?
Paper • 2409.06185 • Published • 14 -
Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
Paper • 2409.04109 • Published • 48 -
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
Paper • 2408.06292 • Published • 126
Theoretical
Coding LLMs
AI-Generated Content Detection
Alignment and Unlearning
-
Learn Your Reference Model for Real Good Alignment
Paper • 2404.09656 • Published • 89 -
Aligning Teacher with Student Preferences for Tailored Training Data Generation
Paper • 2406.19227 • Published • 25 -
Self-Play Preference Optimization for Language Model Alignment
Paper • 2405.00675 • Published • 27 -
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues
Paper • 2404.03820 • Published • 26
Artificial General Intelligence [AGI]
Synthetic Data Generation
Education
Efficient LMs
-
How to Train Data-Efficient LLMs
Paper • 2402.09668 • Published • 42 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 74 -
SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning
Paper • 2407.07523 • Published • 6 -
Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models
Paper • 2407.12327 • Published • 79
Federated Learning (FL) - Decentralized Scheme
-
Towards Building the Federated GPT: Federated Instruction Tuning
Paper • 2305.05644 • Published • 5 -
Low-Resource Machine Translation through the Lens of Personalized Federated Learning
Paper • 2406.12564 • Published • 3 -
Towards a Personal Health Large Language Model
Paper • 2406.06474 • Published • 24 -
Analytic Federated Learning
Paper • 2405.16240 • Published
Fundational - Deep Learning
-
Just How Flexible are Neural Networks in Practice?
Paper • 2406.11463 • Published • 7 -
Not All Language Model Features Are Linear
Paper • 2405.14860 • Published • 41 -
KAN: Kolmogorov-Arnold Networks
Paper • 2404.19756 • Published • 115 -
An Interactive Agent Foundation Model
Paper • 2402.05929 • Published • 30
Interpretability and Analysis
Surveys - Literature Reviews
-
A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models
Paper • 2406.11289 • Published • 5 -
Best Practices and Lessons Learned on Synthetic Data for Language Models
Paper • 2404.07503 • Published • 31 -
Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models
Paper • 2407.12327 • Published • 79 -
Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges
Paper • 2408.08946 • Published • 12
Long Context
-
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Paper • 2407.02490 • Published • 27 -
Can Few-shot Work in Long-Context? Recycling the Context to Generate Demonstrations
Paper • 2406.13632 • Published • 5 -
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
Paper • 2406.15319 • Published • 64 -
Make Your LLM Fully Utilize the Context
Paper • 2404.16811 • Published • 55
Model Evolution - Updates - Compatibility
Model Training - Learning Scheme
-
Instruction Pre-Training: Language Models are Supervised Multitask Learners
Paper • 2406.14491 • Published • 95 -
Pre-training Small Base LMs with Fewer Tokens
Paper • 2404.08634 • Published • 35 -
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
Paper • 2405.15319 • Published • 29 -
Can LLMs Learn by Teaching? A Preliminary Study
Paper • 2406.14629 • Published • 21
Architectures
-
Associative Recurrent Memory Transformer
Paper • 2407.04841 • Published • 36 -
Mixture-of-Agents Enhances Large Language Model Capabilities
Paper • 2406.04692 • Published • 60 -
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Paper • 2405.21060 • Published • 67 -
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Paper • 2404.14219 • Published • 259
Multimodal LMs
-
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Paper • 2406.16860 • Published • 63 -
PaliGemma: A versatile 3B VLM for transfer
Paper • 2407.07726 • Published • 72 -
E5-V: Universal Embeddings with Multimodal Large Language Models
Paper • 2407.12580 • Published • 41 -
Emu3: Next-Token Prediction is All You Need
Paper • 2409.18869 • Published • 95
Optimization
Prompt Engineering - InContext Learning
Reasoning
-
Chain-of-Knowledge: Integrating Knowledge Reasoning into Large Language Models by Learning from Knowledge Graphs
Paper • 2407.00653 • Published • 13 -
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Paper • 2406.18629 • Published • 42 -
Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities
Paper • 2406.14562 • Published • 28 -
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Paper • 2406.04271 • Published • 30
Reinforcement Learning (RL / RLHF)
-
RLHF Workflow: From Reward Modeling to Online RLHF
Paper • 2405.07863 • Published • 71 -
Understanding and Diagnosing Deep Reinforcement Learning
Paper • 2406.16979 • Published • 10 -
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 62 -
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
Paper • 2407.00617 • Published • 7
ReadLater
Self-Supervised Learning
-
Learning and Leveraging World Models in Visual Representation Learning
Paper • 2403.00504 • Published • 33 -
To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review
Paper • 2304.09355 • Published • 5 -
A Cookbook of Self-Supervised Learning
Paper • 2304.12210 • Published • 6
Sequence Modeling
Small Language Model - Mobile Phone
Tabular Data - SpreadSheets
Transfer Learning - FineTuning SFT - Instruction
-
Training Task Experts through Retrieval Based Distillation
Paper • 2407.05463 • Published • 10 -
Instruction Pre-Training: Language Models are Supervised Multitask Learners
Paper • 2406.14491 • Published • 95 -
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
Paper • 2409.12903 • Published • 22 -
A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
Paper • 2410.13841 • Published • 17
Uncertainty Quantification
Vision-language model (VLMs)
-
What matters when building vision-language models?
Paper • 2405.02246 • Published • 103 -
An Introduction to Vision-Language Modeling
Paper • 2405.17247 • Published • 90 -
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
Paper • 2407.03320 • Published • 95 -
Building and better understanding vision-language models: insights and future directions
Paper • 2408.12637 • Published • 133
Models
-
Qwen2-Audio Technical Report
Paper • 2407.10759 • Published • 62 -
Qwen2 Technical Report
Paper • 2407.10671 • Published • 167 -
Gemma 2: Improving Open Language Models at a Practical Size
Paper • 2408.00118 • Published • 79 -
EXAONE 3.0 7.8B Instruction Tuned Language Model
Paper • 2408.03541 • Published • 35
xAI
FUN
-
Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names
Paper • 2408.00298 • Published • 11 -
Achieving Human Level Competitive Robot Table Tennis
Paper • 2408.03906 • Published • 28 -
Learning to Move Like Professional Counter-Strike Players
Paper • 2408.13934 • Published • 23 -
DrawingSpinUp: 3D Animation from Single Character Drawings
Paper • 2409.08615 • Published • 19
Deep Learning
Applications
-
SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
Paper • 2408.15545 • Published • 38 -
InkubaLM: A small language model for low-resource African languages
Paper • 2408.17024 • Published • 14 -
From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents
Paper • 2409.03512 • Published • 29 -
Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
Paper • 2409.04109 • Published • 48
Times Series
Scientific Research - Discovery
-
Can Large Language Models Unlock Novel Scientific Research Ideas?
Paper • 2409.06185 • Published • 14 -
Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
Paper • 2409.04109 • Published • 48 -
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
Paper • 2408.06292 • Published • 126
Factuality - Faithfulness - Hallucination
-
Training Language Models to Self-Correct via Reinforcement Learning
Paper • 2409.12917 • Published • 140 -
FactAlign: Long-form Factuality Alignment of Large Language Models
Paper • 2410.01691 • Published • 9 -
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Paper • 2410.02707 • Published • 47 -
ECon: On the Detection and Resolution of Evidence Conflicts
Paper • 2410.04068 • Published