this paper is like when you tell an art student just draw it in your own style and they actually do it perfectly on the first try 🎨 diffusion models getting too powerful fr

https://www.aimodels.fyi/papers/arxiv/diffusion-self-distillation-zero-shot-customized-image

posted an update about 1 month ago

Post

1140

this paper is like when you tell an art student just draw it in your own style and they actually do it perfectly on the first try 🎨 diffusion models getting too powerful fr

https://www.aimodels.fyi/papers/arxiv/diffusion-self-distillation-zero-shot-customized-image

published an article about 1 month ago

Article

Reverse Thinking Makes LLMs Stronger Reasoners

•

Dec 3, 2024

• 2

commented 4 papers about 1 month ago

Video Depth without Video Models

Paper • 2411.19189 • Published Nov 28, 2024 • 33 •

Video Depth without Video Models

Paper • 2411.19189 • Published Nov 28, 2024 • 33 •

On Domain-Specific Post-Training for Multimodal Large Language Models

Paper • 2411.19930 • Published Nov 29, 2024 • 25 •

Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS

Paper • 2411.18478 • Published Nov 27, 2024 • 32 •

published an article about 1 month ago

Article

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

•

Dec 1, 2024

published an article about 1 month ago

Article

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution

•

Dec 1, 2024

reacted to their post with 👀 about 1 month ago

Post

2199

love how bipedal robot papers are always like we made it not fall down! and somehow thats still a major accomplishment in 2024 🤖 (that's actually not totally fair, walking is really hard ok)

https://www.aimodels.fyi/papers/arxiv/real-time-safe-bipedal-robot-navigation-using

published an article about 1 month ago

Article

SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning

•

Dec 1, 2024

• 1

posted an update about 1 month ago

Post

2199

posted an update about 1 month ago

Post

1055

LLMs developing theory of mind is wild - were basically teaching AI to understand what other AIs are thinking. Its like robot therapy but for making them better team players 🤖🧠

https://www.aimodels.fyi/papers/arxiv/large-model-strategic-thinking-small-model-efficiency

published an article about 1 month ago

Article

Evaluating the Robustness of Analogical Reasoning in Large Language Models

•

Nov 24, 2024

published an article about 1 month ago

Article

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

•

Nov 24, 2024

• 1

reacted to their post with 🔥 about 1 month ago

Post

1597

SAM: I can segment anything!
SAMURAI: Hold my sake while I track it through time and space without even training 🎯

Researchers really said what if we gave SAM object permanence and it worked 🤯

https://www.aimodels.fyi/papers/arxiv/samurai-adapting-segment-anything-model-zero-shot

2 replies

upvoted a paper about 1 month ago

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

Paper • 2411.10442 • Published Nov 15, 2024 • 68

posted an update about 1 month ago

Post

1597

2 replies

Mike Young PRO

AI & ML interests

Recent Activity

Articles

BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO

DeMo: Decoupled Momentum Optimization

Reverse Thinking Makes LLMs Stronger Reasoners

SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning

AIGS: Generating Science from AI-Powered Automated Falsification

SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text

Medical Video Generation for Disease Progression Simulation

Conversational Medical AI: Ready for Practice

Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering

Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

An Internet Voting System Fatally Flawed in Creative New Ways

SpikingNeRF: Making Bio-inspired Neural Networks See through the Real World

Robust ASR Error Correction with Conservative Data Filtering

Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition

StableV2V: Stablizing Shape Consistency in Video-to-Video Editing

Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations

The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use

Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions

Generative Agent Simulations of 1,000 People

That Chip Has Sailed: A Critique of Unfounded Skepticism Around AI for Chip Design

LLaVA-o1: Let Vision Language Models Reason Step-by-Step

GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Organizations

mikelabs's activity

BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO

DeMo: Decoupled Momentum Optimization

Reverse Thinking Makes LLMs Stronger Reasoners

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution

SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning

Evaluating the Robustness of Analogical Reasoning in Large Language Models

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues