arxiv_id
stringclasses
10 values
reached_out_success
float64
reached_out_note
stringclasses
0 values
num_models
float64
0
0
num_datasets
float64
0
0
num_spaces
float64
0
0
title
stringclasses
10 values
github
stringclasses
3 values
github_stars
float64
conference_name
stringclasses
0 values
upvotes
int64
2
105
num_comments
int64
1
7
github_mention_hf
float64
0
0
has_artifact
bool
1 class
submitted_by
stringclasses
9 values
github_issue_url
stringclasses
0 values
hf_pr_urls
stringclasses
0 values
date
stringclasses
1 value
gemini_results
dict
gemini_github_issue_url
stringclasses
3 values
gemini_github_url
stringclasses
5 values
gemini_model_name
stringclasses
1 value
gemini_new_datasets
stringclasses
1 value
gemini_new_model_checkpoints
stringclasses
1 value
gemini_note
stringclasses
3 values
gemini_project_page_url
stringclasses
2 values
gemini_reaching_out
stringclasses
4 values
gemini_reasoning
stringclasses
10 values
gemini_huggingface_pull_request_urls
null
2501.04519
null
null
0
0
0
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
null
null
null
105
7
0
false
lynazhang
null
null
2025-01-09
{ "github_issue_url": "", "github_url": "", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_CODE_YET", "project_page_url": "", "reaching_out": "Gemini decided to not reach out due to no Github URL.", "reasoning": "The paper introduces rStar-Math, a novel method for improving math reasoning capabilities of small language models (SLMs) using Monte Carlo Tree Search (MCTS) and self-evolution. The abstract clearly states, \"Code and data will be available at https://github.com/microsoft/rStar.\" However, the provided Github link is not functional. There is no project page and no Github README content, hence no information about pre-trained model checkpoints or datasets. Although the paper makes it clear that code and data will be released, they are not available yet. Therefore, the correct note is `NO_CODE_YET`.\nIt makes sense to reach out to the authors because they plan to release code and data related to their novel approach." }
gemini-2.0-flash-exp
[]
[]
NO_CODE_YET
Gemini decided to not reach out due to no Github URL.
The paper introduces rStar-Math, a novel method for improving math reasoning capabilities of small language models (SLMs) using Monte Carlo Tree Search (MCTS) and self-evolution. The abstract clearly states, "Code and data will be available at https://github.com/microsoft/rStar." However, the provided Github link is not functional. There is no project page and no Github README content, hence no information about pre-trained model checkpoints or datasets. Although the paper makes it clear that code and data will be released, they are not available yet. Therefore, the correct note is `NO_CODE_YET`. It makes sense to reach out to the authors because they plan to release code and data related to their novel approach.
null
2501.02772
null
null
0
0
0
GeAR: Generation Augmented Retrieval
null
null
null
11
1
0
false
noobimp
null
null
2025-01-09
{ "github_issue_url": "", "github_url": "", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_CODE_YET", "project_page_url": "", "reaching_out": "Gemini decided to not reach out due to no Github URL.", "reasoning": "The paper introduces GeAR, a new method for document retrieval that incorporates fine-grained semantic focus and interpretable generation capabilities. The abstract clearly states, \"The code, data, and models will be released after completing technical review to facilitate future research.\" This indicates that code and artifacts are planned to be released, but are not yet available. Thus, the appropriate note is `NO_CODE_YET`. Since no artifacts are currently available, `new_model_checkpoints` and `new_datasets` should be empty lists. It makes sense to reach out to the authors as the paper indicates they intend to release artifacts in the future." }
gemini-2.0-flash-exp
[]
[]
NO_CODE_YET
Gemini decided to not reach out due to no Github URL.
The paper introduces GeAR, a new method for document retrieval that incorporates fine-grained semantic focus and interpretable generation capabilities. The abstract clearly states, "The code, data, and models will be released after completing technical review to facilitate future research." This indicates that code and artifacts are planned to be released, but are not yet available. Thus, the appropriate note is `NO_CODE_YET`. Since no artifacts are currently available, `new_model_checkpoints` and `new_datasets` should be empty lists. It makes sense to reach out to the authors as the paper indicates they intend to release artifacts in the future.
null
2501.04575
null
null
0
0
0
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
https://github.com/reallm-labs/infiguiagent
null
null
14
1
0
false
pengxiang
null
null
2025-01-09
{ "github_issue_url": "https://github.com/Reallm-Labs/InfiGUIAgent/issues/1", "github_url": "https://github.com/reallm-labs/infiguiagent", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_CODE_YET", "project_page_url": "", "reaching_out": "{'title': 'Release InfiGUIAgent on Hugging Face', 'message': \"Hello @OS-Agent-Survey 🤗\\n\\nI'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2501.04575.\\nThe paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance),\\nyou can also claim the paper as yours which will show up on your public profile at HF.\\n\\nLooking forward to the code and data release. Would you like to host the model you've pre-trained on https://huggingface.co/models?\\nHosting on Hugging Face will give you more visibility/enable better discoverability. We can add tags in the model cards so that people find the models easier,\\nlink it to the paper page, etc.\\n\\nIf you're down, leaving a guide [here](https://huggingface.co/docs/hub/models-uploading). If it's a custom PyTorch model, you can use the [PyTorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin)\\nclass which adds `from_pretrained` and `push_to_hub` to the model which lets you to upload the model and people to download and use models right away.\\nIf you do not want this and directly want to upload model through UI or however you want, people can also use [hf_hub_download](https://huggingface.co/docs/huggingface_hub/en/guides/download#download-a-single-file).\\n\\nAfter uploaded, we can also link the models to the paper page (read [here](https://huggingface.co/docs/hub/en/model-cards#linking-a-paper)) so people can discover your model.\\n\\nYou can also build a demo for your model on [Spaces](https://huggingface.co/spaces), we can provide you a ZeroGPU [grant](https://huggingface.co/docs/hub/en/spaces-gpus#community-gpu-grants),\\nwhich gives you A100 GPUs for free.\\n\\nLet me know if you're interested/need any guidance :)\\n\\nKind regards,\\n\\nNiels\"}", "reasoning": "The paper introduces InfiGUIAgent, a multimodal LLM-based GUI agent, and describes a two-stage supervised fine-tuning approach. The abstract mentions a GitHub repository for resources. The Github README states \"Data and code are coming soon,\" indicating that neither code nor artifacts (model checkpoints or datasets) are currently available, but they are planned to be released. This corresponds to a NO_CODE_YET scenario. Reaching out is appropriate since they plan to release code and model checkpoints." }
https://github.com/Reallm-Labs/InfiGUIAgent/issues/1
https://github.com/reallm-labs/infiguiagent
gemini-2.0-flash-exp
[]
[]
NO_CODE_YET
{'title': 'Release InfiGUIAgent on Hugging Face', 'message': "Hello @OS-Agent-Survey 🤗\n\nI'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2501.04575.\nThe paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance),\nyou can also claim the paper as yours which will show up on your public profile at HF.\n\nLooking forward to the code and data release. Would you like to host the model you've pre-trained on https://huggingface.co/models?\nHosting on Hugging Face will give you more visibility/enable better discoverability. We can add tags in the model cards so that people find the models easier,\nlink it to the paper page, etc.\n\nIf you're down, leaving a guide [here](https://huggingface.co/docs/hub/models-uploading). If it's a custom PyTorch model, you can use the [PyTorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin)\nclass which adds `from_pretrained` and `push_to_hub` to the model which lets you to upload the model and people to download and use models right away.\nIf you do not want this and directly want to upload model through UI or however you want, people can also use [hf_hub_download](https://huggingface.co/docs/huggingface_hub/en/guides/download#download-a-single-file).\n\nAfter uploaded, we can also link the models to the paper page (read [here](https://huggingface.co/docs/hub/en/model-cards#linking-a-paper)) so people can discover your model.\n\nYou can also build a demo for your model on [Spaces](https://huggingface.co/spaces), we can provide you a ZeroGPU [grant](https://huggingface.co/docs/hub/en/spaces-gpus#community-gpu-grants),\nwhich gives you A100 GPUs for free.\n\nLet me know if you're interested/need any guidance :)\n\nKind regards,\n\nNiels"}
The paper introduces InfiGUIAgent, a multimodal LLM-based GUI agent, and describes a two-stage supervised fine-tuning approach. The abstract mentions a GitHub repository for resources. The Github README states "Data and code are coming soon," indicating that neither code nor artifacts (model checkpoints or datasets) are currently available, but they are planned to be released. This corresponds to a NO_CODE_YET scenario. Reaching out is appropriate since they plan to release code and model checkpoints.
null
2501.04227
null
null
0
0
0
Agent Laboratory: Using LLM Agents as Research Assistants
null
null
null
34
2
0
false
akhaliq
null
null
2025-01-09
{ "github_issue_url": "", "github_url": "https://github.com/SamuelSchmidgall/AgentLaboratory", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_ARTIFACTS", "project_page_url": "https://agentlaboratory.github.io/", "reaching_out": "{'title': '', 'message': 'No need to reach out since no artifacts are being released.'}", "reasoning": "The paper introduces Agent Laboratory, an autonomous LLM-based framework for completing the entire research process. The goal is to produce a code repository and a research report.\n\nThe abstract, paper page comments, and the first 2 pages of the PDF do not mention any new model checkpoints or datasets being released.\nThe Github README also does not mention any new model checkpoints or datasets.\nThe focus of the framework is on assisting researchers with their existing ideas and not on introducing new datasets or model checkpoints. The framework takes as input a research idea and outputs a code repository and a research report.\n\nTherefore, the most common and correct scenario is `NO_ARTIFACTS`." }
https://github.com/SamuelSchmidgall/AgentLaboratory
gemini-2.0-flash-exp
[]
[]
NO_ARTIFACTS
https://agentlaboratory.github.io/
{'title': '', 'message': 'No need to reach out since no artifacts are being released.'}
The paper introduces Agent Laboratory, an autonomous LLM-based framework for completing the entire research process. The goal is to produce a code repository and a research report. The abstract, paper page comments, and the first 2 pages of the PDF do not mention any new model checkpoints or datasets being released. The Github README also does not mention any new model checkpoints or datasets. The focus of the framework is on assisting researchers with their existing ideas and not on introducing new datasets or model checkpoints. The framework takes as input a research idea and outputs a code repository and a research report. Therefore, the most common and correct scenario is `NO_ARTIFACTS`.
null
2501.04682
null
null
0
0
0
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though
null
null
null
43
1
0
false
akhaliq
null
null
2025-01-09
{ "github_issue_url": "", "github_url": "", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_CODE", "project_page_url": "", "reaching_out": "Gemini decided to not reach out due to no Github URL.", "reasoning": "The paper introduces Meta Chain-of-Thought (Meta-CoT), a novel framework that extends traditional Chain-of-Thought (CoT) by explicitly modeling the underlying reasoning required to arrive at a particular CoT. The paper explores methods for producing Meta-CoT via process supervision, synthetic data generation, and search algorithms. The authors outline a pipeline for training a model to produce Meta-CoTs, incorporating instruction tuning and reinforcement learning.\n\nNo Github repository or project page URL is mentioned in the provided text, including the abstract, paper page, and first two pages of the Arxiv PDF. There is no mention of code or datasets being released either in the current form or in the near future.\nHence, no code or artifacts are available or planned to be released at this time. Therefore, the most appropriate scenario is `NO_CODE`." }
gemini-2.0-flash-exp
[]
[]
NO_CODE
Gemini decided to not reach out due to no Github URL.
The paper introduces Meta Chain-of-Thought (Meta-CoT), a novel framework that extends traditional Chain-of-Thought (CoT) by explicitly modeling the underlying reasoning required to arrive at a particular CoT. The paper explores methods for producing Meta-CoT via process supervision, synthetic data generation, and search algorithms. The authors outline a pipeline for training a model to produce Meta-CoTs, incorporating instruction tuning and reinforcement learning. No Github repository or project page URL is mentioned in the provided text, including the abstract, paper page, and first two pages of the Arxiv PDF. There is no mention of code or datasets being released either in the current form or in the near future. Hence, no code or artifacts are available or planned to be released at this time. Therefore, the most appropriate scenario is `NO_CODE`.
null
2501.03271
null
null
0
0
0
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
null
null
null
5
1
0
false
amanchadha
null
null
2025-01-09
{ "github_issue_url": "", "github_url": "", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_CODE", "project_page_url": "", "reaching_out": "Gemini decided to not reach out due to no Github URL.", "reasoning": "The paper introduces DPO-Kernels, a novel approach to direct preference optimization (DPO) by incorporating kernel methods and alternative divergence measures.\nThe abstract mentions \"Comprehensive resources are available to facilitate further research and application of DPO-Kernels.\" but this is very vague.\nThere is no mention of code or data in the abstract or paper page.\nNo Github repository or project page URL is provided, and after inspecting the first two pages of the Arxiv PDF, it's evident that the paper is method-centric with no mention of releasing any artifacts.\nTherefore, the most appropriate note is NO_CODE. It doesn't make sense to reach out to the authors at this point." }
gemini-2.0-flash-exp
[]
[]
NO_CODE
Gemini decided to not reach out due to no Github URL.
The paper introduces DPO-Kernels, a novel approach to direct preference optimization (DPO) by incorporating kernel methods and alternative divergence measures. The abstract mentions "Comprehensive resources are available to facilitate further research and application of DPO-Kernels." but this is very vague. There is no mention of code or data in the abstract or paper page. No Github repository or project page URL is provided, and after inspecting the first two pages of the Arxiv PDF, it's evident that the paper is method-centric with no mention of releasing any artifacts. Therefore, the most appropriate note is NO_CODE. It doesn't make sense to reach out to the authors at this point.
null
2501.04306
null
null
0
0
0
LLM4SR: A Survey on Large Language Models for Scientific Research
https://github.com/du-nlp-lab/llm4sr
null
null
18
1
0
false
ZonglinY
null
null
2025-01-09
{ "github_issue_url": "", "github_url": "https://github.com/du-nlp-lab/llm4sr", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_ARTIFACTS", "project_page_url": "", "reaching_out": "{'title': '', 'message': 'No need to reach out since no artifacts are being released.'}", "reasoning": "The paper is a survey on the use of Large Language Models (LLMs) in scientific research. It does not introduce new pre-trained models or datasets, instead focusing on reviewing existing literature and methods. The paper mentions a Github repository, which upon inspection, appears to be a curated list of resources, papers, and code related to the topic, and does not contain new artifacts or any indications that they will be released.\nAll colleagues have indicated the scenario to be `NO_ARTIFACTS`. This is a clear consensus and there is no evidence to the contrary. Therefore, I agree with the other parsing results that the scenario is `NO_ARTIFACTS`. It does not make sense to reach out, as no new artifacts have been created and released as part of this work." }
https://github.com/du-nlp-lab/llm4sr
gemini-2.0-flash-exp
[]
[]
NO_ARTIFACTS
{'title': '', 'message': 'No need to reach out since no artifacts are being released.'}
The paper is a survey on the use of Large Language Models (LLMs) in scientific research. It does not introduce new pre-trained models or datasets, instead focusing on reviewing existing literature and methods. The paper mentions a Github repository, which upon inspection, appears to be a curated list of resources, papers, and code related to the topic, and does not contain new artifacts or any indications that they will be released. All colleagues have indicated the scenario to be `NO_ARTIFACTS`. This is a clear consensus and there is no evidence to the contrary. Therefore, I agree with the other parsing results that the scenario is `NO_ARTIFACTS`. It does not make sense to reach out, as no new artifacts have been created and released as part of this work.
null
2501.04144
null
null
0
0
0
Chirpy3D: Continuous Part Latents for Creative 3D Bird Generation
https://github.com/kamwoh/chirpy3d
null
null
9
2
0
false
kamwoh
null
null
2025-01-09
{ "github_issue_url": "https://github.com/kamwoh/chirpy3d/issues/1", "github_url": "https://github.com/kamwoh/chirpy3d", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_CODE_YET", "project_page_url": "", "reaching_out": "{'title': 'Release Chirpy3D on Hugging Face', 'message': \"Hello @kamwoh 🤗\\n\\nI'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2501.04144.\\nThe paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance),\\nyou can also claim the paper as yours which will show up on your public profile at HF.\\n\\nLooking forward to the code and model release. Would you like to host the model you've pre-trained on https://huggingface.co/models?\\nHosting on Hugging Face will give you more visibility/enable better discoverability. We can add tags in the model cards so that people find the models easier,\\nlink it to the paper page, etc.\\n\\nIf you're down, leaving a guide [here](https://huggingface.co/docs/hub/models-uploading). If it's a custom PyTorch model, you can use the [PyTorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin)\\nclass which adds `from_pretrained` and `push_to_hub` to the model which lets you to upload the model and people to download and use models right away.\\nIf you do not want this and directly want to upload model through UI or however you want, people can also use [hf_hub_download](https://huggingface.co/docs/huggingface_hub/en/guides/download#download-a-single-file).\\n\\nAfter uploaded, we can also link the models to the paper page (read [here](https://huggingface.co/docs/hub/en/model-cards#linking-a-paper)) so people can discover your model.\\n\\nYou can also build a demo for your model on [Spaces](https://huggingface.co/spaces), we can provide you a ZeroGPU [grant](https://huggingface.co/docs/hub/en/spaces-gpus#community-gpu-grants),\\nwhich gives you A100 GPUs for free.\\n\\nLet me know if you're interested/need any guidance :)\\n\\nKind regards,\\n\\nNiels\"}", "reasoning": "The paper introduces Chirpy3D, a method for generating novel 3D objects with fine-grained details, using birds as an example. The abstract mentions \"Code will be released at https://github.com/kamwoh/chirpy3d\". The Github README states \"Code coming soon!\". This indicates the authors intend to release the code but it is not yet available, thus it falls under the `NO_CODE_YET` category. There is no mention of new datasets or model checkpoints being released, only that the code is coming soon. Therefore, it would be useful to reach out to the authors to check if they plan to also release their pre-trained models and/or dataset, once they have released their code." }
https://github.com/kamwoh/chirpy3d/issues/1
https://github.com/kamwoh/chirpy3d
gemini-2.0-flash-exp
[]
[]
NO_CODE_YET
{'title': 'Release Chirpy3D on Hugging Face', 'message': "Hello @kamwoh 🤗\n\nI'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2501.04144.\nThe paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance),\nyou can also claim the paper as yours which will show up on your public profile at HF.\n\nLooking forward to the code and model release. Would you like to host the model you've pre-trained on https://huggingface.co/models?\nHosting on Hugging Face will give you more visibility/enable better discoverability. We can add tags in the model cards so that people find the models easier,\nlink it to the paper page, etc.\n\nIf you're down, leaving a guide [here](https://huggingface.co/docs/hub/models-uploading). If it's a custom PyTorch model, you can use the [PyTorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin)\nclass which adds `from_pretrained` and `push_to_hub` to the model which lets you to upload the model and people to download and use models right away.\nIf you do not want this and directly want to upload model through UI or however you want, people can also use [hf_hub_download](https://huggingface.co/docs/huggingface_hub/en/guides/download#download-a-single-file).\n\nAfter uploaded, we can also link the models to the paper page (read [here](https://huggingface.co/docs/hub/en/model-cards#linking-a-paper)) so people can discover your model.\n\nYou can also build a demo for your model on [Spaces](https://huggingface.co/spaces), we can provide you a ZeroGPU [grant](https://huggingface.co/docs/hub/en/spaces-gpus#community-gpu-grants),\nwhich gives you A100 GPUs for free.\n\nLet me know if you're interested/need any guidance :)\n\nKind regards,\n\nNiels"}
The paper introduces Chirpy3D, a method for generating novel 3D objects with fine-grained details, using birds as an example. The abstract mentions "Code will be released at https://github.com/kamwoh/chirpy3d". The Github README states "Code coming soon!". This indicates the authors intend to release the code but it is not yet available, thus it falls under the `NO_CODE_YET` category. There is no mention of new datasets or model checkpoints being released, only that the code is coming soon. Therefore, it would be useful to reach out to the authors to check if they plan to also release their pre-trained models and/or dataset, once they have released their code.
null
2501.04694
null
null
0
0
0
EpiCoder: Encompassing Diversity and Complexity in Code Generation
null
null
null
4
1
0
false
lx865712528
null
null
2025-01-09
{ "github_issue_url": "", "github_url": "", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_CODE", "project_page_url": "", "reaching_out": "Gemini decided to not reach out due to no Github URL.", "reasoning": "The paper introduces a novel feature tree-based framework to generate diverse code data for instruction tuning. They fine-tuned base models and created the EpiCoder series achieving SOTA performance. \n\nThere is no Github or project page URL mentioned in the abstract, paper comments, or the first 2 pages of the Arxiv PDF. Therefore, there is no evidence of code or artifact release. This is consistent with the majority vote of my colleagues, who all selected the `NO_CODE` note.\n\nIt does not make sense to reach out to the authors at this stage, since no code or artifacts have been released." }
gemini-2.0-flash-exp
[]
[]
NO_CODE
Gemini decided to not reach out due to no Github URL.
The paper introduces a novel feature tree-based framework to generate diverse code data for instruction tuning. They fine-tuned base models and created the EpiCoder series achieving SOTA performance. There is no Github or project page URL mentioned in the abstract, paper comments, or the first 2 pages of the Arxiv PDF. Therefore, there is no evidence of code or artifact release. This is consistent with the majority vote of my colleagues, who all selected the `NO_CODE` note. It does not make sense to reach out to the authors at this stage, since no code or artifacts have been released.
null
2501.04652
null
null
0
0
0
Multi-task retriever fine-tuning for domain-specific and efficient RAG
null
null
null
2
1
0
false
patricebechard
null
null
2025-01-09
{ "github_issue_url": "", "github_url": "", "model_name": "gemini-2.0-flash-exp", "new_datasets": "[]", "new_model_checkpoints": "[]", "note": "NO_CODE", "project_page_url": "", "reaching_out": "Gemini decided to not reach out due to no Github URL.", "reasoning": "The paper introduces a method for instruction fine-tuning a small retriever encoder for use in RAG applications. The goal is to have a single retriever that can handle multiple domain-specific tasks. The authors fine-tune the mGTE model and compare it with BM25, mE5, and mGTE.\nThere's no mention of a Github repository or project page, and no explicit mention of releasing new datasets or model checkpoints in the paper or the comments.\nTherefore, the most accurate note would be `NO_CODE`, since it is the most common answer and because there is no clear indication of code being released.\nIt does not make sense to reach out since no artifacts are being released." }
gemini-2.0-flash-exp
[]
[]
NO_CODE
Gemini decided to not reach out due to no Github URL.
The paper introduces a method for instruction fine-tuning a small retriever encoder for use in RAG applications. The goal is to have a single retriever that can handle multiple domain-specific tasks. The authors fine-tune the mGTE model and compare it with BM25, mE5, and mGTE. There's no mention of a Github repository or project page, and no explicit mention of releasing new datasets or model checkpoints in the paper or the comments. Therefore, the most accurate note would be `NO_CODE`, since it is the most common answer and because there is no clear indication of code being released. It does not make sense to reach out since no artifacts are being released.
null
README.md exists but content is empty.
Downloads last month
7