SlideShare a Scribd company logo
http://deeplearning.jp/
RLCD: Reinforcement Learning from Contrast Distillation for
Language Model Alignment
〜 Human Feedbackを使用しないRLHF 〜
高城 頌太(東京大学 工学系研究科 松尾研 M2)
DEEP LEARNING JP
[DL Papers]
1
書誌情報
RLCD: Reinforcement Learning from Contrast Distillation for Language Model
Alignment
https://arxiv.org/abs/2307.12950
タイトル:
著者:
人間のフィードバックデータを使用せずに人間の好みに合わせて言語モデルを調整する方法である,コ
ントラスト蒸留による強化学習 (RLCD) という手法を提案
概要:
2
Kevin Yang, Dan Klein, Asli Celikyilmaz, Nanyun Peng, Yuandong Tian
UC Berkeley, Meta AI, UCLA
• Reinforcement Learning with Human Feedback (RLHF) は,人間の好みに合わせて
調整(Alignment)するために用いられる(無害性,有用性,真実性など)
背景
3
• 通常のRLHFでは,人間がラベル付けしたデータを用いてReward Model(Preference
Model)を学習するが,RLの学習がこのモデルに大きく依存してしまう
• 人間がラベル付けしたデータ、特に高品質のデータの収集は、大規模になると費用と
時間のコストが莫大になる
– そもそもアノテーターの選定はどうするのか
– ラベル付けされたデータの品質はどうやって担保するのか
背景
4
• これらの問題に対処するために,AI Feedbackからの強化学習 (RLAIF) やコンテキス
ト蒸留など,人間による注釈なしでラベルを取得するアプローチが提案されている
RLAIF: 事前モデル(かそれより強いLLM)を用いて,
回答の改善+Preference Score算出
コンテキスト蒸留: コンテキストがなくても同じ回答になるようにFine-Tuningする
背景
5
Constitutional AI: Harmlessness from AI Feedback
• しかしいくつかの問題点が存在する
RLAIF:
同じプロンプトを用いて生成すると解答が似通ってしまい,
S/N比が低くなってしまう( output Aのスコア: 0.54 vs output Bのスコア: 0.46)
→ つまりノイズの割合が増えてしまう
コンテキスト蒸留:
単一の出力しかないため,ランキングが考慮されない
→ 悪い出力を悪いと認識する情報が欠損している(Contrastive Objectiveがない)
背景
6
Constitutional AI: Harmlessness from AI Feedback
• RLAIFとコンテキスト蒸留を組み合わせてAI FeedbackによるRLの性能を改善させたい
• 本論文では,LLaMA 7Bの性能改善を目指す
(特にharmless outputs, helpful outputs, high-quality story outlinesについて)
→ より強い”オラクル”LLMにアクセスせずに,Reward Model学習のためのデータを生成
する方法を提案(Reinforcement Learning from Contrast Distillation: RLCD)
目的
7
• ポジティブプロンプト,ネガティブプロンプトを作成し,生成データに対して0,1を割り当て
る(だけ)
手法
8
ここが違うだけ
ポジティブプロンプト,ネガティブプロンプトにつける接尾辞一覧
(harmlessness task)
9
出力例
10
• Harmlessness
攻撃的な,あるいは社会的に受け入れがたいテキストを含む対話かどうか
"ありがとう!"や "ごめんなさい "のような無意味な応答ではなく、会話に役立ち,関連
性のある出力でなければならない
• Helpfulness
一般的に人間に情報やアドバイスを与える対話かどうか
• Outlining
人間がストーリーの前提を提供し,アウトラインを与える対話かどうか
評価軸
11
• 人間による評価(8段階のリッカード尺度, 正規化されているので高い方が良い)
• LLaMa7B, 30Bを用いており,Reward Modelの学習データ生成にみに使用
人間による評価結果
12
人間によるアノテーション方法
13
GPT-4に評価させた結果
14
• RLCD30B vs RLAIF30Bの結果のみ人間の評価と異なる
GPT-4に評価するためのプロンプト
15
たしかに提案手法が良さげ ↓ LLaMA2での結果
定性評価
16
• 人間によってランク付けされたデータを用いて正解率を算出
• 提案手法の方がより人間のPreferenceに近いスコアを出力している?
さらなる分析
17
• ポジティブプロンプト,ネガティブプロンプトを用いてRLAIFと同じスコアリングプロンプト
で学習(RLCD-Rescore)
• 0-1ラベルの方が良い?
さらなる分析
18
まとめ & 感想
19
まとめ
- Reward Modelの学習データセットを自動生成するための手法
- 既存手法(RLAIF)よりも高いスコアを達成
感想
- 結局何にalignmentしてるのかよくわからない
- 接尾辞を付けることで,人間が決めた評価軸方向の出力を強化しているということなのか
- Reward Modelの学習考えると,クラス分類の決定境界面付近のデータはノイズが多く
なるので,それを除いて,極端なデータだけ学習させることで精度がよくなる?
- 決定境界付近のデータの精度はどうなってるのか気になる
- あと普通のRLHFとの比較が欲しい
Thank you.
20
Ad

More Related Content

What's hot (20)

XGBoostからNGBoostまで
XGBoostからNGBoostまでXGBoostからNGBoostまで
XGBoostからNGBoostまで
Tomoki Yoshida
 
[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models
Deep Learning JP
 
深層生成モデルと世界モデル(2020/11/20版)
深層生成モデルと世界モデル(2020/11/20版)深層生成モデルと世界モデル(2020/11/20版)
深層生成モデルと世界モデル(2020/11/20版)
Masahiro Suzuki
 
[DL輪読会]Life-Long Disentangled Representation Learning with Cross-Domain Laten...
[DL輪読会]Life-Long Disentangled Representation Learning with Cross-Domain Laten...[DL輪読会]Life-Long Disentangled Representation Learning with Cross-Domain Laten...
[DL輪読会]Life-Long Disentangled Representation Learning with Cross-Domain Laten...
Deep Learning JP
 
[DL輪読会]Relational inductive biases, deep learning, and graph networks
[DL輪読会]Relational inductive biases, deep learning, and graph networks[DL輪読会]Relational inductive biases, deep learning, and graph networks
[DL輪読会]Relational inductive biases, deep learning, and graph networks
Deep Learning JP
 
Triplet Loss 徹底解説
Triplet Loss 徹底解説Triplet Loss 徹底解説
Triplet Loss 徹底解説
tancoro
 
[DL輪読会]Pay Attention to MLPs (gMLP)
[DL輪読会]Pay Attention to MLPs	(gMLP)[DL輪読会]Pay Attention to MLPs	(gMLP)
[DL輪読会]Pay Attention to MLPs (gMLP)
Deep Learning JP
 
[DL輪読会]Learning Latent Dynamics for Planning from Pixels
[DL輪読会]Learning Latent Dynamics for Planning from Pixels[DL輪読会]Learning Latent Dynamics for Planning from Pixels
[DL輪読会]Learning Latent Dynamics for Planning from Pixels
Deep Learning JP
 
[DL輪読会]Convolutional Conditional Neural Processesと Neural Processes Familyの紹介
[DL輪読会]Convolutional Conditional Neural Processesと Neural Processes Familyの紹介[DL輪読会]Convolutional Conditional Neural Processesと Neural Processes Familyの紹介
[DL輪読会]Convolutional Conditional Neural Processesと Neural Processes Familyの紹介
Deep Learning JP
 
Domain Adaptation 発展と動向まとめ(サーベイ資料)
Domain Adaptation 発展と動向まとめ(サーベイ資料)Domain Adaptation 発展と動向まとめ(サーベイ資料)
Domain Adaptation 発展と動向まとめ(サーベイ資料)
Yamato OKAMOTO
 
HiPPO/S4解説
HiPPO/S4解説HiPPO/S4解説
HiPPO/S4解説
Morpho, Inc.
 
【DL輪読会】How Much Can CLIP Benefit Vision-and-Language Tasks?
【DL輪読会】How Much Can CLIP Benefit Vision-and-Language Tasks? 【DL輪読会】How Much Can CLIP Benefit Vision-and-Language Tasks?
【DL輪読会】How Much Can CLIP Benefit Vision-and-Language Tasks?
Deep Learning JP
 
[DL輪読会]Control as Inferenceと発展
[DL輪読会]Control as Inferenceと発展[DL輪読会]Control as Inferenceと発展
[DL輪読会]Control as Inferenceと発展
Deep Learning JP
 
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Yusuke Uchida
 
[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...
[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...
[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...
Deep Learning JP
 
Generative Adversarial Imitation Learningの紹介(RLアーキテクチャ勉強会)
Generative Adversarial Imitation Learningの紹介(RLアーキテクチャ勉強会)Generative Adversarial Imitation Learningの紹介(RLアーキテクチャ勉強会)
Generative Adversarial Imitation Learningの紹介(RLアーキテクチャ勉強会)
Yusuke Nakata
 
【DL輪読会】ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
【DL輪読会】ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation【DL輪読会】ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
【DL輪読会】ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
Deep Learning JP
 
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
Deep Learning JP
 
[DL輪読会]Deep Learning 第15章 表現学習
[DL輪読会]Deep Learning 第15章 表現学習[DL輪読会]Deep Learning 第15章 表現学習
[DL輪読会]Deep Learning 第15章 表現学習
Deep Learning JP
 
[DL輪読会]GLIDE: Guided Language to Image Diffusion for Generation and Editing
[DL輪読会]GLIDE: Guided Language to Image Diffusion  for Generation and Editing[DL輪読会]GLIDE: Guided Language to Image Diffusion  for Generation and Editing
[DL輪読会]GLIDE: Guided Language to Image Diffusion for Generation and Editing
Deep Learning JP
 
XGBoostからNGBoostまで
XGBoostからNGBoostまでXGBoostからNGBoostまで
XGBoostからNGBoostまで
Tomoki Yoshida
 
[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models
Deep Learning JP
 
深層生成モデルと世界モデル(2020/11/20版)
深層生成モデルと世界モデル(2020/11/20版)深層生成モデルと世界モデル(2020/11/20版)
深層生成モデルと世界モデル(2020/11/20版)
Masahiro Suzuki
 
[DL輪読会]Life-Long Disentangled Representation Learning with Cross-Domain Laten...
[DL輪読会]Life-Long Disentangled Representation Learning with Cross-Domain Laten...[DL輪読会]Life-Long Disentangled Representation Learning with Cross-Domain Laten...
[DL輪読会]Life-Long Disentangled Representation Learning with Cross-Domain Laten...
Deep Learning JP
 
[DL輪読会]Relational inductive biases, deep learning, and graph networks
[DL輪読会]Relational inductive biases, deep learning, and graph networks[DL輪読会]Relational inductive biases, deep learning, and graph networks
[DL輪読会]Relational inductive biases, deep learning, and graph networks
Deep Learning JP
 
Triplet Loss 徹底解説
Triplet Loss 徹底解説Triplet Loss 徹底解説
Triplet Loss 徹底解説
tancoro
 
[DL輪読会]Pay Attention to MLPs (gMLP)
[DL輪読会]Pay Attention to MLPs	(gMLP)[DL輪読会]Pay Attention to MLPs	(gMLP)
[DL輪読会]Pay Attention to MLPs (gMLP)
Deep Learning JP
 
[DL輪読会]Learning Latent Dynamics for Planning from Pixels
[DL輪読会]Learning Latent Dynamics for Planning from Pixels[DL輪読会]Learning Latent Dynamics for Planning from Pixels
[DL輪読会]Learning Latent Dynamics for Planning from Pixels
Deep Learning JP
 
[DL輪読会]Convolutional Conditional Neural Processesと Neural Processes Familyの紹介
[DL輪読会]Convolutional Conditional Neural Processesと Neural Processes Familyの紹介[DL輪読会]Convolutional Conditional Neural Processesと Neural Processes Familyの紹介
[DL輪読会]Convolutional Conditional Neural Processesと Neural Processes Familyの紹介
Deep Learning JP
 
Domain Adaptation 発展と動向まとめ(サーベイ資料)
Domain Adaptation 発展と動向まとめ(サーベイ資料)Domain Adaptation 発展と動向まとめ(サーベイ資料)
Domain Adaptation 発展と動向まとめ(サーベイ資料)
Yamato OKAMOTO
 
【DL輪読会】How Much Can CLIP Benefit Vision-and-Language Tasks?
【DL輪読会】How Much Can CLIP Benefit Vision-and-Language Tasks? 【DL輪読会】How Much Can CLIP Benefit Vision-and-Language Tasks?
【DL輪読会】How Much Can CLIP Benefit Vision-and-Language Tasks?
Deep Learning JP
 
[DL輪読会]Control as Inferenceと発展
[DL輪読会]Control as Inferenceと発展[DL輪読会]Control as Inferenceと発展
[DL輪読会]Control as Inferenceと発展
Deep Learning JP
 
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Yusuke Uchida
 
[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...
[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...
[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...
Deep Learning JP
 
Generative Adversarial Imitation Learningの紹介(RLアーキテクチャ勉強会)
Generative Adversarial Imitation Learningの紹介(RLアーキテクチャ勉強会)Generative Adversarial Imitation Learningの紹介(RLアーキテクチャ勉強会)
Generative Adversarial Imitation Learningの紹介(RLアーキテクチャ勉強会)
Yusuke Nakata
 
【DL輪読会】ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
【DL輪読会】ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation【DL輪読会】ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
【DL輪読会】ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
Deep Learning JP
 
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
Deep Learning JP
 
[DL輪読会]Deep Learning 第15章 表現学習
[DL輪読会]Deep Learning 第15章 表現学習[DL輪読会]Deep Learning 第15章 表現学習
[DL輪読会]Deep Learning 第15章 表現学習
Deep Learning JP
 
[DL輪読会]GLIDE: Guided Language to Image Diffusion for Generation and Editing
[DL輪読会]GLIDE: Guided Language to Image Diffusion  for Generation and Editing[DL輪読会]GLIDE: Guided Language to Image Diffusion  for Generation and Editing
[DL輪読会]GLIDE: Guided Language to Image Diffusion for Generation and Editing
Deep Learning JP
 

More from Deep Learning JP (20)

【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
Deep Learning JP
 
【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて
Deep Learning JP
 
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
Deep Learning JP
 
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
Deep Learning JP
 
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
Deep Learning JP
 
【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM
Deep Learning JP
 
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo... 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
Deep Learning JP
 
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
Deep Learning JP
 
【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?
Deep Learning JP
 
【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について
Deep Learning JP
 
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
Deep Learning JP
 
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
Deep Learning JP
 
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
Deep Learning JP
 
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
Deep Learning JP
 
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
Deep Learning JP
 
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
Deep Learning JP
 
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
Deep Learning JP
 
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
Deep Learning JP
 
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
Deep Learning JP
 
【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...
【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...
【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...
Deep Learning JP
 
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
Deep Learning JP
 
【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて
Deep Learning JP
 
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
Deep Learning JP
 
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
Deep Learning JP
 
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
Deep Learning JP
 
【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM
Deep Learning JP
 
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo... 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
Deep Learning JP
 
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
Deep Learning JP
 
【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?
Deep Learning JP
 
【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について
Deep Learning JP
 
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
Deep Learning JP
 
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
Deep Learning JP
 
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
Deep Learning JP
 
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
Deep Learning JP
 
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
Deep Learning JP
 
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
Deep Learning JP
 
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
Deep Learning JP
 
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
Deep Learning JP
 
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
Deep Learning JP
 
【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...
【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...
【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...
Deep Learning JP
 
Ad

【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language Model Alignment 〜 Human Feedbackを使用しないRLHF 〜