From cc1c65667a6e445aaa3a88f48deca0194bcdea80 Mon Sep 17 00:00:00 2001 From: Chansung Date: Tue, 30 Jan 2024 13:03:27 +0000 Subject: [PATCH] Automated report --- ...orrect+for+Compositional+Text-to-Image+Generation.yaml | 0 ...+and+Comprehension+in+Vision-Language+Large+Model.yaml | 0 ...Animation+Generation+With+Multi-Modality+Guidance.yaml | 0 ...xture+of+Experts+for+Large+Vision-Language+Models.yaml | 0 ...-Modal+Mobile+Device+Agent+with+Visual+Perception.yaml | 0 ...to-Video+Generation+with+Explicit+Motion+Modeling.yaml | 0 ...xt-to-Image+Diffusion+with+Prototypical+Embedding.yaml | 0 ...-Language+Model+Finetuning+for+OOD+Generalization.yaml | 0 ...+for+Compute+and+Data-Efficient+Language+Modeling.yaml | 0 ...r+Sample-Efficient+Robotic+Reinforcement+Learning.yaml | 0 ...3A+Inserting+Anybody+into+Anywhere+at+First+Sight.yaml | 0 tags/Computer Vision.md | 8 ++++++++ tags/Deep Learning.md | 8 ++++++++ tags/Emerging Applications of Machine Learning.md | 2 ++ tags/Explainable AI and Interpretability.md | 1 + ...uman-Computer Interaction (HCI) and User Interfaces.md | 1 + tags/Natural Language Processing.md | 5 +++++ tags/Reinforcement Learning.md | 1 + tags/Robotics and Control.md | 1 + tags/Supervised Learning.md | 5 +++++ 20 files changed, 32 insertions(+) rename current/2024-01-30 Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation.yaml => archive/14/2024-01-30+Divide+and+Conquer%3A+Language+Models+can+Plan+and+Self-Correct+for+Compositional+Text-to-Image+Generation.yaml (100%) rename current/2024-01-30 InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model.yaml => archive/14/2024-01-30+InternLM-XComposer2%3A+Mastering+Free-form+Text-Image+Composition+and+Comprehension+in+Vision-Language+Large+Model.yaml (100%) rename current/2024-01-30 Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance.yaml => archive/14/2024-01-30+Media2Face%3A+Co-speech+Facial+Animation+Generation+With+Multi-Modality+Guidance.yaml (100%) rename current/2024-01-30 MoE-LLaVA: Mixture of Experts for Large Vision-Language Models.yaml => archive/14/2024-01-30+MoE-LLaVA%3A+Mixture+of+Experts+for+Large+Vision-Language+Models.yaml (100%) rename current/2024-01-30 Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception.yaml => archive/14/2024-01-30+Mobile-Agent%3A+Autonomous+Multi-Modal+Mobile+Device+Agent+with+Visual+Perception.yaml (100%) rename current/2024-01-30 Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling.yaml => archive/14/2024-01-30+Motion-I2V%3A+Consistent+and+Controllable+Image-to-Video+Generation+with+Explicit+Motion+Modeling.yaml (100%) rename current/2024-01-30 Object-Driven One-Shot Fine-tuning of Text-to-Image Diffusion with Prototypical Embedding.yaml => archive/14/2024-01-30+Object-Driven+One-Shot+Fine-tuning+of+Text-to-Image+Diffusion+with+Prototypical+Embedding.yaml (100%) rename current/2024-01-30 Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization.yaml => archive/14/2024-01-30+Overcoming+the+Pitfalls+of+Vision-Language+Model+Finetuning+for+OOD+Generalization.yaml (100%) rename current/2024-01-30 Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling.yaml => archive/14/2024-01-30+Rephrasing+the+Web%3A+A+Recipe+for+Compute+and+Data-Efficient+Language+Modeling.yaml (100%) rename current/2024-01-30 SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning.yaml => archive/14/2024-01-30+SERL%3A+A+Software+Suite+for+Sample-Efficient+Robotic+Reinforcement+Learning.yaml (100%) rename current/2024-01-30 StableIdentity: Inserting Anybody into Anywhere at First Sight.yaml => archive/14/2024-01-30+StableIdentity%3A+Inserting+Anybody+into+Anywhere+at+First+Sight.yaml (100%) diff --git a/current/2024-01-30 Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation.yaml b/archive/14/2024-01-30+Divide+and+Conquer%3A+Language+Models+can+Plan+and+Self-Correct+for+Compositional+Text-to-Image+Generation.yaml similarity index 100% rename from current/2024-01-30 Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation.yaml rename to archive/14/2024-01-30+Divide+and+Conquer%3A+Language+Models+can+Plan+and+Self-Correct+for+Compositional+Text-to-Image+Generation.yaml diff --git a/current/2024-01-30 InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model.yaml b/archive/14/2024-01-30+InternLM-XComposer2%3A+Mastering+Free-form+Text-Image+Composition+and+Comprehension+in+Vision-Language+Large+Model.yaml similarity index 100% rename from current/2024-01-30 InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model.yaml rename to archive/14/2024-01-30+InternLM-XComposer2%3A+Mastering+Free-form+Text-Image+Composition+and+Comprehension+in+Vision-Language+Large+Model.yaml diff --git a/current/2024-01-30 Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance.yaml b/archive/14/2024-01-30+Media2Face%3A+Co-speech+Facial+Animation+Generation+With+Multi-Modality+Guidance.yaml similarity index 100% rename from current/2024-01-30 Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance.yaml rename to archive/14/2024-01-30+Media2Face%3A+Co-speech+Facial+Animation+Generation+With+Multi-Modality+Guidance.yaml diff --git a/current/2024-01-30 MoE-LLaVA: Mixture of Experts for Large Vision-Language Models.yaml b/archive/14/2024-01-30+MoE-LLaVA%3A+Mixture+of+Experts+for+Large+Vision-Language+Models.yaml similarity index 100% rename from current/2024-01-30 MoE-LLaVA: Mixture of Experts for Large Vision-Language Models.yaml rename to archive/14/2024-01-30+MoE-LLaVA%3A+Mixture+of+Experts+for+Large+Vision-Language+Models.yaml diff --git a/current/2024-01-30 Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception.yaml b/archive/14/2024-01-30+Mobile-Agent%3A+Autonomous+Multi-Modal+Mobile+Device+Agent+with+Visual+Perception.yaml similarity index 100% rename from current/2024-01-30 Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception.yaml rename to archive/14/2024-01-30+Mobile-Agent%3A+Autonomous+Multi-Modal+Mobile+Device+Agent+with+Visual+Perception.yaml diff --git a/current/2024-01-30 Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling.yaml b/archive/14/2024-01-30+Motion-I2V%3A+Consistent+and+Controllable+Image-to-Video+Generation+with+Explicit+Motion+Modeling.yaml similarity index 100% rename from current/2024-01-30 Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling.yaml rename to archive/14/2024-01-30+Motion-I2V%3A+Consistent+and+Controllable+Image-to-Video+Generation+with+Explicit+Motion+Modeling.yaml diff --git a/current/2024-01-30 Object-Driven One-Shot Fine-tuning of Text-to-Image Diffusion with Prototypical Embedding.yaml b/archive/14/2024-01-30+Object-Driven+One-Shot+Fine-tuning+of+Text-to-Image+Diffusion+with+Prototypical+Embedding.yaml similarity index 100% rename from current/2024-01-30 Object-Driven One-Shot Fine-tuning of Text-to-Image Diffusion with Prototypical Embedding.yaml rename to archive/14/2024-01-30+Object-Driven+One-Shot+Fine-tuning+of+Text-to-Image+Diffusion+with+Prototypical+Embedding.yaml diff --git a/current/2024-01-30 Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization.yaml b/archive/14/2024-01-30+Overcoming+the+Pitfalls+of+Vision-Language+Model+Finetuning+for+OOD+Generalization.yaml similarity index 100% rename from current/2024-01-30 Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization.yaml rename to archive/14/2024-01-30+Overcoming+the+Pitfalls+of+Vision-Language+Model+Finetuning+for+OOD+Generalization.yaml diff --git a/current/2024-01-30 Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling.yaml b/archive/14/2024-01-30+Rephrasing+the+Web%3A+A+Recipe+for+Compute+and+Data-Efficient+Language+Modeling.yaml similarity index 100% rename from current/2024-01-30 Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling.yaml rename to archive/14/2024-01-30+Rephrasing+the+Web%3A+A+Recipe+for+Compute+and+Data-Efficient+Language+Modeling.yaml diff --git a/current/2024-01-30 SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning.yaml b/archive/14/2024-01-30+SERL%3A+A+Software+Suite+for+Sample-Efficient+Robotic+Reinforcement+Learning.yaml similarity index 100% rename from current/2024-01-30 SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning.yaml rename to archive/14/2024-01-30+SERL%3A+A+Software+Suite+for+Sample-Efficient+Robotic+Reinforcement+Learning.yaml diff --git a/current/2024-01-30 StableIdentity: Inserting Anybody into Anywhere at First Sight.yaml b/archive/14/2024-01-30+StableIdentity%3A+Inserting+Anybody+into+Anywhere+at+First+Sight.yaml similarity index 100% rename from current/2024-01-30 StableIdentity: Inserting Anybody into Anywhere at First Sight.yaml rename to archive/14/2024-01-30+StableIdentity%3A+Inserting+Anybody+into+Anywhere+at+First+Sight.yaml diff --git a/tags/Computer Vision.md b/tags/Computer Vision.md index 626e4922..ae1c2311 100644 --- a/tags/Computer Vision.md +++ b/tags/Computer Vision.md @@ -75,3 +75,11 @@ - [From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+From+GPT-4+to+Gemini+and+Beyond%3A+Assessing+the+Landscape+of+MLLMs+on+Generalizability%2C+Trustworthiness+and+Causality+through+Four+Modalities.yaml) / 2024-01-29 - [TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+TIP-Editor%3A+An+Accurate+3D+Editor+Following+Both+Text-Prompts+And+Image-Prompts.yaml) / 2024-01-29 - [Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+Taiyi-Diffusion-XL%3A+Advancing+Bilingual+Text-to-Image+Generation+with+Large+Vision-Language+Model+Support.yaml) / 2024-01-29 +- [Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Divide+and+Conquer%3A+Language+Models+can+Plan+and+Self-Correct+for+Compositional+Text-to-Image+Generation.yaml) / 2024-01-30 +- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+InternLM-XComposer2%3A+Mastering+Free-form+Text-Image+Composition+and+Comprehension+in+Vision-Language+Large+Model.yaml) / 2024-01-30 +- [Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Media2Face%3A+Co-speech+Facial+Animation+Generation+With+Multi-Modality+Guidance.yaml) / 2024-01-30 +- [Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Mobile-Agent%3A+Autonomous+Multi-Modal+Mobile+Device+Agent+with+Visual+Perception.yaml) / 2024-01-30 +- [Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Motion-I2V%3A+Consistent+and+Controllable+Image-to-Video+Generation+with+Explicit+Motion+Modeling.yaml) / 2024-01-30 +- [Object-Driven One-Shot Fine-tuning of Text-to-Image Diffusion with Prototypical Embedding](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Object-Driven+One-Shot+Fine-tuning+of+Text-to-Image+Diffusion+with+Prototypical+Embedding.yaml) / 2024-01-30 +- [Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Overcoming+the+Pitfalls+of+Vision-Language+Model+Finetuning+for+OOD+Generalization.yaml) / 2024-01-30 +- [StableIdentity: Inserting Anybody into Anywhere at First Sight](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+StableIdentity%3A+Inserting+Anybody+into+Anywhere+at+First+Sight.yaml) / 2024-01-30 diff --git a/tags/Deep Learning.md b/tags/Deep Learning.md index 156b5e4a..889e9b6e 100644 --- a/tags/Deep Learning.md +++ b/tags/Deep Learning.md @@ -108,3 +108,11 @@ - [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+SliceGPT%3A+Compress+Large+Language+Models+by+Deleting+Rows+and+Columns.yaml) / 2024-01-29 - [TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+TIP-Editor%3A+An+Accurate+3D+Editor+Following+Both+Text-Prompts+And+Image-Prompts.yaml) / 2024-01-29 - [Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+Taiyi-Diffusion-XL%3A+Advancing+Bilingual+Text-to-Image+Generation+with+Large+Vision-Language+Model+Support.yaml) / 2024-01-29 +- [Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Divide+and+Conquer%3A+Language+Models+can+Plan+and+Self-Correct+for+Compositional+Text-to-Image+Generation.yaml) / 2024-01-30 +- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+InternLM-XComposer2%3A+Mastering+Free-form+Text-Image+Composition+and+Comprehension+in+Vision-Language+Large+Model.yaml) / 2024-01-30 +- [Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Media2Face%3A+Co-speech+Facial+Animation+Generation+With+Multi-Modality+Guidance.yaml) / 2024-01-30 +- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+MoE-LLaVA%3A+Mixture+of+Experts+for+Large+Vision-Language+Models.yaml) / 2024-01-30 +- [Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Motion-I2V%3A+Consistent+and+Controllable+Image-to-Video+Generation+with+Explicit+Motion+Modeling.yaml) / 2024-01-30 +- [Object-Driven One-Shot Fine-tuning of Text-to-Image Diffusion with Prototypical Embedding](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Object-Driven+One-Shot+Fine-tuning+of+Text-to-Image+Diffusion+with+Prototypical+Embedding.yaml) / 2024-01-30 +- [Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Overcoming+the+Pitfalls+of+Vision-Language+Model+Finetuning+for+OOD+Generalization.yaml) / 2024-01-30 +- [StableIdentity: Inserting Anybody into Anywhere at First Sight](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+StableIdentity%3A+Inserting+Anybody+into+Anywhere+at+First+Sight.yaml) / 2024-01-30 diff --git a/tags/Emerging Applications of Machine Learning.md b/tags/Emerging Applications of Machine Learning.md index 7afa34b2..c20d4291 100644 --- a/tags/Emerging Applications of Machine Learning.md +++ b/tags/Emerging Applications of Machine Learning.md @@ -14,3 +14,5 @@ - [CreativeSynth: Creative Blending and Synthesis of Visual Arts based on Multimodal Diffusion](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/11/2024-01-26+CreativeSynth%3A+Creative+Blending+and+Synthesis+of+Visual+Arts+based+on+Multimodal+Diffusion.yaml) / 2024-01-26 - [Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/12/2024-01-29+Taiyi-Diffusion-XL%3A+Advancing+Bilingual+Text-to-Image+Generation+with+Large+Vision-Language+Model+Support.yaml) / 2024-01-29 - [Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+Taiyi-Diffusion-XL%3A+Advancing+Bilingual+Text-to-Image+Generation+with+Large+Vision-Language+Model+Support.yaml) / 2024-01-29 +- [Object-Driven One-Shot Fine-tuning of Text-to-Image Diffusion with Prototypical Embedding](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Object-Driven+One-Shot+Fine-tuning+of+Text-to-Image+Diffusion+with+Prototypical+Embedding.yaml) / 2024-01-30 +- [StableIdentity: Inserting Anybody into Anywhere at First Sight](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+StableIdentity%3A+Inserting+Anybody+into+Anywhere+at+First+Sight.yaml) / 2024-01-30 diff --git a/tags/Explainable AI and Interpretability.md b/tags/Explainable AI and Interpretability.md index 78f64c3d..1ab0c28c 100644 --- a/tags/Explainable AI and Interpretability.md +++ b/tags/Explainable AI and Interpretability.md @@ -16,3 +16,4 @@ - [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/12/2024-01-29+EAGLE%3A+Speculative+Sampling+Requires+Rethinking+Feature+Uncertainty.yaml) / 2024-01-29 - [From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/12/2024-01-29+From+GPT-4+to+Gemini+and+Beyond%3A+Assessing+the+Landscape+of+MLLMs+on+Generalizability%2C+Trustworthiness+and+Causality+through+Four+Modalities.yaml) / 2024-01-29 - [From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+From+GPT-4+to+Gemini+and+Beyond%3A+Assessing+the+Landscape+of+MLLMs+on+Generalizability%2C+Trustworthiness+and+Causality+through+Four+Modalities.yaml) / 2024-01-29 +- [Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Motion-I2V%3A+Consistent+and+Controllable+Image-to-Video+Generation+with+Explicit+Motion+Modeling.yaml) / 2024-01-30 diff --git a/tags/Human-Computer Interaction (HCI) and User Interfaces.md b/tags/Human-Computer Interaction (HCI) and User Interfaces.md index ca0671e6..9059297f 100644 --- a/tags/Human-Computer Interaction (HCI) and User Interfaces.md +++ b/tags/Human-Computer Interaction (HCI) and User Interfaces.md @@ -1,2 +1,3 @@ - [Towards Conversational Diagnostic AI](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/3/2024-01-12+Towards+Conversational+Diagnostic+AI.yaml) / 2024-01-12 - [Rambler: Supporting Writing With Speech via LLM-Assisted Gist Manipulation](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/7/2024-01-22+Rambler%3A+Supporting+Writing+With+Speech+via+LLM-Assisted+Gist+Manipulation.yaml) / 2024-01-22 +- [Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Media2Face%3A+Co-speech+Facial+Animation+Generation+With+Multi-Modality+Guidance.yaml) / 2024-01-30 diff --git a/tags/Natural Language Processing.md b/tags/Natural Language Processing.md index f34f5bf8..92dd0623 100644 --- a/tags/Natural Language Processing.md +++ b/tags/Natural Language Processing.md @@ -85,3 +85,8 @@ - [Generative Expressive Robot Behaviors using Large Language Models](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+Generative+Expressive+Robot+Behaviors+using+Large+Language+Models.yaml) / 2024-01-29 - [TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+TIP-Editor%3A+An+Accurate+3D+Editor+Following+Both+Text-Prompts+And+Image-Prompts.yaml) / 2024-01-29 - [Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+Taiyi-Diffusion-XL%3A+Advancing+Bilingual+Text-to-Image+Generation+with+Large+Vision-Language+Model+Support.yaml) / 2024-01-29 +- [Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Divide+and+Conquer%3A+Language+Models+can+Plan+and+Self-Correct+for+Compositional+Text-to-Image+Generation.yaml) / 2024-01-30 +- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+InternLM-XComposer2%3A+Mastering+Free-form+Text-Image+Composition+and+Comprehension+in+Vision-Language+Large+Model.yaml) / 2024-01-30 +- [Object-Driven One-Shot Fine-tuning of Text-to-Image Diffusion with Prototypical Embedding](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Object-Driven+One-Shot+Fine-tuning+of+Text-to-Image+Diffusion+with+Prototypical+Embedding.yaml) / 2024-01-30 +- [Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Overcoming+the+Pitfalls+of+Vision-Language+Model+Finetuning+for+OOD+Generalization.yaml) / 2024-01-30 +- [Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Rephrasing+the+Web%3A+A+Recipe+for+Compute+and+Data-Efficient+Language+Modeling.yaml) / 2024-01-30 diff --git a/tags/Reinforcement Learning.md b/tags/Reinforcement Learning.md index 4497350e..5a2730c3 100644 --- a/tags/Reinforcement Learning.md +++ b/tags/Reinforcement Learning.md @@ -8,3 +8,4 @@ - [Self-Rewarding Language Models](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/6/2024-01-19+Self-Rewarding+Language+Models.yaml) / 2024-01-19 - [WARM: On the Benefits of Weight Averaged Reward Models](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/8/2024-01-23+WARM%3A+On+the+Benefits+of+Weight+Averaged+Reward+Models.yaml) / 2024-01-23 - [Large-scale Reinforcement Learning for Diffusion Models](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/9/2024-01-24+Large-scale+Reinforcement+Learning+for+Diffusion+Models.yaml) / 2024-01-24 +- [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+SERL%3A+A+Software+Suite+for+Sample-Efficient+Robotic+Reinforcement+Learning.yaml) / 2024-01-30 diff --git a/tags/Robotics and Control.md b/tags/Robotics and Control.md index 2323f792..3e488cd7 100644 --- a/tags/Robotics and Control.md +++ b/tags/Robotics and Control.md @@ -5,3 +5,4 @@ - [Adaptive Mobile Manipulation for Articulated Objects In the Open World](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/11/2024-01-26+Adaptive+Mobile+Manipulation+for+Articulated+Objects+In+the+Open+World.yaml) / 2024-01-26 - [Generative Expressive Robot Behaviors using Large Language Models](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/12/2024-01-29+Generative+Expressive+Robot+Behaviors+using+Large+Language+Models.yaml) / 2024-01-29 - [Generative Expressive Robot Behaviors using Large Language Models](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+Generative+Expressive+Robot+Behaviors+using+Large+Language+Models.yaml) / 2024-01-29 +- [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+SERL%3A+A+Software+Suite+for+Sample-Efficient+Robotic+Reinforcement+Learning.yaml) / 2024-01-30 diff --git a/tags/Supervised Learning.md b/tags/Supervised Learning.md index 5fae2c86..8c334d16 100644 --- a/tags/Supervised Learning.md +++ b/tags/Supervised Learning.md @@ -37,3 +37,8 @@ - [Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/12/2024-01-29+Taiyi-Diffusion-XL%3A+Advancing+Bilingual+Text-to-Image+Generation+with+Large+Vision-Language+Model+Support.yaml) / 2024-01-29 - [Learning Universal Predictors](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+Learning+Universal+Predictors.yaml) / 2024-01-29 - [Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/13/2024-01-29+Taiyi-Diffusion-XL%3A+Advancing+Bilingual+Text-to-Image+Generation+with+Large+Vision-Language+Model+Support.yaml) / 2024-01-29 +- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+InternLM-XComposer2%3A+Mastering+Free-form+Text-Image+Composition+and+Comprehension+in+Vision-Language+Large+Model.yaml) / 2024-01-30 +- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+MoE-LLaVA%3A+Mixture+of+Experts+for+Large+Vision-Language+Models.yaml) / 2024-01-30 +- [Object-Driven One-Shot Fine-tuning of Text-to-Image Diffusion with Prototypical Embedding](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Object-Driven+One-Shot+Fine-tuning+of+Text-to-Image+Diffusion+with+Prototypical+Embedding.yaml) / 2024-01-30 +- [Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Overcoming+the+Pitfalls+of+Vision-Language+Model+Finetuning+for+OOD+Generalization.yaml) / 2024-01-30 +- [Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling](https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/archive/14/2024-01-30+Rephrasing+the+Web%3A+A+Recipe+for+Compute+and+Data-Efficient+Language+Modeling.yaml) / 2024-01-30