Rohan-Paul-AI

Follow me on 🐦 TWITTER: twitter.com/rohanpaul_ai - to remain on the bleeding edge of AI

You can find me here:

**********************************************
🐦 TWITTER: twitter.com/rohanpaul_ai
👨🏻‍💼 LINKEDIN: www.linkedin.com/in/rohan-paul-b27285129/
👨‍💻 GITHUB: github.com/rohan-paul
👨‍🔧 KAGGLE: www.kaggle.com/paulrohan2020

**********************************************

View channel on YouTube

Switch Invidious Instance

Videos

Shorts

Posts

newest

oldest

popular

14:18

My AI newsletter for today (2024-Nov-26) - Google NotebookLM Podcast

Rohan-Paul-AI

Shared 1 year ago

217 views

5:15

Differential Transformer- Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

476 views

11:34

Intelligence at the Edge of Chaos - Google NotebookLM Podcast

Rohan-Paul-AI

Shared 2 years ago

1.3K views

5:08

LLMs + Persona-Plug = Personalized LLMs - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

476 views

5:51

Deep Learning for Options Trading: An End-To-End Approach - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

541 views

5:39

CogniDual Framework: Self-Training Large Language Models- Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

115 views

4:04

N-gram Prediction and Word Difference Representations for Language - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

159 views

5:21

Patched MOA: optimizing inference for diverse software development tasks - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

101 views

6:18

RATIONALYST Pre-training Process Supervision for Improving Reasoning - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

86 views

4:01

RecurrentGemma: Moving Past Transformers for Efficient Open LLM - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

92 views

7:52

RoleBreak Character Hallucination as a Jailbreak Attack in Role-Playing - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

109 views

6:11

Selective Attention improves LLM performance across model sizes - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

187 views

6:19

SpotDiffusion: A Fast Approach For Seamless Panorama Generation" - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

122 views

6:23

FAN: Fourier Analysis Network can replace MLP layers in various models - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

688 views

7:35

Platonic Representation, All LLMs are converging towards the same point 🤔- Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

330 views

4:40

Human-like Affective Cognition in Foundation Models - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

105 views

5:19

Exploring the Compositional Deficiency of LLMs in Mathematical Reasoning - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

68 views

4:57

Comprehensive Evaluation of Quantized Instruction-Tuned LLMs - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

76 views

5:55

Adaptive k-Nearest Neighbor Classifier Based on Local Shape Operator - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

123 views

6:46

Rejection Sampling IMLE: Better Few-Shot Image Synthesis - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

76 views

5:59

Were RNNs All We Needed - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

632 views

14:06

Meta's ans to SORA 🎬 Movie Gen: - Google NotebookLM Podcast

Rohan-Paul-AI

Shared 2 years ago

298 views

5:38

Trans-LoRA: data-free Transferable Parameter Efficient Finetuning - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

199 views

5:22

The Perfect Blend: Redefining RLHF with Mixture of Judges - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

145 views

5:22

MASSIVE Paper "ADDITION IS ALL YOU NEED" - Reduce energy costs by 95% - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

1.3K views

5:32

NVIDIA Paper - "MaskedMimic: Unified Physics-Based Character Control - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

312 views

6:25

NVLM: Open Frontier-Class Multimodal LLMs - NVIDIA Paper - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

1K views

5:59

Archon: An Architecture Search Framework for Inference-Time Techniques - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

949 views

5:54

RAGProbe: An Automated Approach for Evaluating RAG - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

285 views

5:16

Paper - RED QUEEN : Safeguarding LLMs against Concealed Jailbreaking - Google Illuminate Podcast

Rohan-Paul-AI

Shared 2 years ago

487 views

10:13

The classic "The AI Scientist" Paper by NotebookLM - Audio Podcast by Google NotebookLM

Rohan-Paul-AI

Shared 2 years ago

267 views

7:32

Training Large Language Models for Reasoning through Reverse Curriculum RL - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

219 views

6:18

Self-Taught Evaluators - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

108 views

6:17

MedPromptExtract (Medical Data Extraction Tool) - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

140 views

8:27

MASAI: Modular Architecture for Software-engineering AI agents - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

198 views

7:04

Imitating Language via Scalable Inverse Reinforcement Learning - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

251 views

6:30

GraphInstruct: Empowering LLMs with Graph Understanding and Reasoning Capability- Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

130 views

7:52

Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

105 views

6:40

Adaptive Self-Supervised Learning Strategies For On-Device LLM Personalization - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

159 views

5:49

The Impact of Initialization on LoRA Finetuning Dynamics - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

73 views

5:07

LoRAMoE: Alleviate World Knowledge Forgetting in LLMs via MoE-Style Plugin - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

105 views

4:11

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

73 views

7:25

LoRA+ Efficient Low Rank Adaptationof Large Models - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

146 views

5:49

ReFT: Representation Finetuning for Language Models - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

84 views

6:22

Leave No Context Behind-Efficient Infinite Context Transformers - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

146 views

6:24

Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

95 views

5:47

TextGrad: Automatic "Differentiation" via Text - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

156 views

6:16

Paper - "REFT: Reasoning with Reinforced Fine-Tuning - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

106 views

5:32

Paper - "Adaptable Logical Control for Large Language Models" - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

86 views

7:42

Paper - Breaking reCAPTCHAv2 - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

103 views

7:32

Paper - "ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning" - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

130 views

7:30

Paper - "Agents in Software Engineering: Survey, Landscape, and Vision" - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

118 views

6:18

SCHRODINGER’S MEMORY: LARGE LANGUAGE MODELS - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

125 views

6:38

LLMs Still Cant Plan Can LRMs? - OpenAIs o1 on PlanBench - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

185 views

8:14

AI Paper Writing in the Margins - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

66 views

7:42

Sam Altman's newly published personal blog about the AI future. Audio Podcast by NotebookLM

Rohan-Paul-AI

Shared 2 years ago

1.1K views

8:11

Secret behind SambaNova superfast LLM Inferencing Speed - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

267 views

5:35

First open-source multimodal math dataset boosts MLLM performance - Podcast

Rohan-Paul-AI

Shared 2 years ago

122 views

9:18

New Harvard Business School study shows that AI girlfriends reduce loneliness - Audio Podcast

Rohan-Paul-AI

Shared 2 years ago

163 views

5:48

Paper Podcast - LLM Pruning and Distillation by NVIDIA

Rohan-Paul-AI

Shared 2 years ago

508 views